Model profile · xAI

Grok 4.3

Closed weightspremium · registry tag 2026 frontier revision

Verified but aging

Reads as verified but aging across the resolved source data. Capability fit excludes speed and cost.

Visible coverage: 63.7%
Verified coverage: 63.7%
Spread: 100%
Last verified: Oct 3, 2026

50%capability fit

textcodevisionsearchdocument11 aliases46 official source links

Open compare

Data version

Current snapshot.

Published Oct 3, 2026Model list checked4 stale sources105 claim warnings9 providers · 1334 tracked models

The registry snapshot and page stamp are shown so a stale deploy is visible at a glance. View live data status.

Source-linked scores by benchmark

Each row keeps the benchmark source, source type, raw metric, and percentile inside its fair comparison set. Capability summaries exclude archived categories, speed, and cost; those rows remain below.

Verified but agingThis model currently reads as verified but aging across the resolved source data.

Chat / text36 benchmarks55.8%

Intelligence Index

AA · Chat / text · Combined

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #227 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 14
Percentile: 59.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

59.3% percentile inside its fair comparison set

14Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #178 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 23.7%
Percentile: 60.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

60.9% percentile inside its fair comparison set

23.7%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #189 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 25.5%
Percentile: 58.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

58.5% percentile inside its fair comparison set

25.5%Raw benchmark value

IFBench

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #120 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.6%
Percentile: 65.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

65.8% percentile inside its fair comparison set

47.6%Raw benchmark value

Input price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #239 · Source label: Grok 4.3 (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.3 /1M input tokens
Percentile: 34.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

34.2% percentile inside its fair comparison set

$1.3 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #186 · Source label: Grok 4.3 (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $2.5 /1M output tokens
Percentile: 49.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

49.4% percentile inside its fair comparison set

$2.5 /1M output tokensRaw benchmark value

Output Speed

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #83 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 118.8 tokens/s
Percentile: 68.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

68.7% percentile inside its fair comparison set

118.8 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #215 · Source label: Grok 4.3 (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 22.53s
Percentile: 18.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

18.9% percentile inside its fair comparison set

22.53sRaw benchmark value

Time to first answer token

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #148 · Source label: Grok 4.3 (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 22.53s
Percentile: 43.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

43.9% percentile inside its fair comparison set

22.53sRaw benchmark value

Text Arena

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #86 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 77.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: overall. Source rank: #94. Votes: 71150. Organization: xai. License: Proprietary.

77.4% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,438 - 1,445

Text Arena · Creative Writing

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #72 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 81%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: creative_writing. Source rank: #80. Votes: 13173. Organization: xai. License: Proprietary.

81% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,416 - 1,429

Text Arena · English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #82 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 78.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: english. Source rank: #90. Votes: 32673. Organization: xai. License: Proprietary.

78.5% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,446 - 1,456

Text Arena · Exclude Ties

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #86 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 77.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: exclude_ties. Source rank: #94. Votes: 54660. Organization: xai. License: Proprietary.

77.4% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,435 - 1,445

Text Arena · Hard Prompts

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #96 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 74.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: hard_prompts. Source rank: #106. Votes: 47577. Organization: xai. License: Proprietary.

74.7% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,452 - 1,460

Text Arena · Hard Prompts English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #93 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 75.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: hard_prompts_english. Source rank: #102. Votes: 22373. Organization: xai. License: Proprietary.

75.4% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,457 - 1,468

Text Arena · Instruction Following

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #109 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 71.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: instruction_following. Source rank: #122. Votes: 25039. Organization: xai. License: Proprietary.

71.3% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,409 - 1,420

Text Arena · Longer Query

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #93 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 74.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: longer_query. Source rank: #102. Votes: 33150. Organization: xai. License: Proprietary.

74.1% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,438 - 1,448

Text Arena · Multi Turn

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #87 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 77%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: multi_turn. Source rank: #97. Votes: 12848. Organization: xai. License: Proprietary.

77% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,440 - 1,453

Text Arena · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #139 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 63.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: overall. Source rank: #154. Votes: 71150. Organization: xai. License: Proprietary.

63.3% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,393 - 1,400

Text Arena · Creative Writing · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #120 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,380
Percentile: 68.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: creative_writing. Source rank: #131. Votes: 13173. Organization: xai. License: Proprietary.

68.2% percentile inside its fair comparison set

1,380Raw benchmark valueCI 1,374 - 1,387

Text Arena · English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #142 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: english. Source rank: #158. Votes: 32673. Organization: xai. License: Proprietary.

62.5% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,400 - 1,409

Text Arena · Exclude Ties · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #138 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,377
Percentile: 63.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: exclude_ties. Source rank: #153. Votes: 54660. Organization: xai. License: Proprietary.

63.6% percentile inside its fair comparison set

1,377Raw benchmark valueCI 1,373 - 1,382

Text Arena · Hard Prompts · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #149 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 60.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: hard_prompts. Source rank: #166. Votes: 47577. Organization: xai. License: Proprietary.

60.6% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,392 - 1,401

Text Arena · Hard Prompts English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #148 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 60.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: hard_prompts_english. Source rank: #164. Votes: 22373. Organization: xai. License: Proprietary.

60.7% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,396 - 1,407

Text Arena · Instruction Following · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #152 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 59.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: instruction_following. Source rank: #170. Votes: 25039. Organization: xai. License: Proprietary.

59.8% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,360 - 1,371

Text Arena · Longer Query · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #138 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,393
Percentile: 61.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: longer_query. Source rank: #155. Votes: 33150. Organization: xai. License: Proprietary.

61.4% percentile inside its fair comparison set

1,393Raw benchmark valueCI 1,388 - 1,398

Text Arena · Multi Turn · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #128 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 66%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: multi_turn. Source rank: #141. Votes: 12848. Organization: xai. License: Proprietary.

66% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,399 - 1,412

Instruction following

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #52 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62.8%
Percentile: 21.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: IF. Tasks scored: 4.

21.5% percentile inside its fair comparison set

62.8%Raw benchmark value

Language

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #56 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.6%
Percentile: 15.4%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Language. Tasks scored: 3.

15.4% percentile inside its fair comparison set

73.6%Raw benchmark value

Paraphrase

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #42 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64.4%
Percentile: 36.9%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: paraphrase. Category: IF.

36.9% percentile inside its fair comparison set

64.4%Raw benchmark value

Simplify

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #52 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 57.6%
Percentile: 21.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: simplify. Category: IF.

21.5% percentile inside its fair comparison set

57.6%Raw benchmark value

Story generation

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #37 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70.6%
Percentile: 44.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: story_generation. Category: IF.

44.6% percentile inside its fair comparison set

70.6%Raw benchmark value

Summarize

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #59 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58.4%
Percentile: 10.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: summarize. Category: IF.

10.8% percentile inside its fair comparison set

58.4%Raw benchmark value

Connections

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #50 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94%
Percentile: 26.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: connections. Category: Language.

26.2% percentile inside its fair comparison set

94%Raw benchmark value

Plot unscrambling

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #60 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 48.7%
Percentile: 9.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: plot_unscrambling. Category: Language.

9.2% percentile inside its fair comparison set

48.7%Raw benchmark value

Typos

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #42 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78%
Percentile: 38.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typos. Category: Language.

38.5% percentile inside its fair comparison set

78%Raw benchmark value

Coding35 benchmarks45.1%

Terminal-Bench Hard

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #110 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18.9%
Percentile: 67.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

67.2% percentile inside its fair comparison set

18.9%Raw benchmark value

SciCode

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #146 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 39.4%
Percentile: 26.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

26.8% percentile inside its fair comparison set

39.4%Raw benchmark value

Text Arena · Coding

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #90 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 76%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: coding. Source rank: #99. Votes: 19889. Organization: xai. License: Proprietary.

76% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,482 - 1,493

Text Arena · Coding · No Style Control

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #137 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 63.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: coding. Source rank: #151. Votes: 19889. Organization: xai. License: Proprietary.

63.3% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,409 - 1,420

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #68 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 19.4%
Percentile: 28%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vibe-code; provider: SpaceXAI.

28% percentile inside its fair comparison set

19.4%Raw benchmark valueCI 11.1% - 27.7%

WebDev Arena

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #100 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,357
Percentile: 22%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: overall. Source rank: #105. Votes: 15057. Organization: xai. License: Proprietary.

22% percentile inside its fair comparison set

1,357Raw benchmark valueCI 1,350 - 1,363

Code Arena · Webdev Html

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #96 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,364
Percentile: 24%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: webdev-html. Source rank: #101. Votes: 1776. Organization: xai. License: Proprietary.

24% percentile inside its fair comparison set

1,364Raw benchmark valueCI 1,349 - 1,380

Code Arena · Webdev React

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #90 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,353
Percentile: 21.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: webdev-react. Source rank: #97. Votes: 11566. Organization: xai. License: Proprietary.

21.2% percentile inside its fair comparison set

1,353Raw benchmark valueCI 1,346 - 1,360

Code Migration

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #61 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 6.8%
Percentile: 11.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: code-migration; provider: SpaceXAI.

11.8% percentile inside its fair comparison set

6.8%Raw benchmark valueCI 4.5% - 9.1%

ProgramBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #54 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0%
Percentile: 51.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: programbench; provider: SpaceXAI.

51.7% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

Terminal-Bench 2.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #60 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 41.9%
Percentile: 11.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: SpaceXAI.

11.9% percentile inside its fair comparison set

41.9%Raw benchmark valueCI 36.8% - 47.1%

Code Arena · Image To Webdev

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #42 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,373
Percentile: 6.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: image_to_webdev. Source rank: #46. Votes: 5444. Organization: xai. License: Proprietary.

6.8% percentile inside its fair comparison set

1,373Raw benchmark valueCI 1,364 - 1,383

SWE-bench Verified

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #53 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71.4%
Percentile: 36.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: swebench; provider: SpaceXAI.

36.6% percentile inside its fair comparison set

71.4%Raw benchmark valueCI 67.4% - 75.4%

LiveCodeBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #37 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.5%
Percentile: 71.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: lcb; provider: SpaceXAI.

71.2% percentile inside its fair comparison set

84.5%Raw benchmark valueCI 82.5% - 86.5%

Agentic coding

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 18.5%
Percentile: 0%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Agentic Coding. Tasks scored: 3.

0% percentile inside its fair comparison set

18.5%Raw benchmark value

Coding

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #61 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 69.9%
Percentile: 7.7%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Coding. Tasks scored: 2.

7.7% percentile inside its fair comparison set

69.9%Raw benchmark value

JavaScript

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 27.3%
Percentile: 0%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: javascript. Category: Agentic Coding.

0% percentile inside its fair comparison set

27.3%Raw benchmark value

TypeScript

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 13.3%
Percentile: 0%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typescript. Category: Agentic Coding.

0% percentile inside its fair comparison set

13.3%Raw benchmark value

Python

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 15%
Percentile: 0%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: python. Category: Agentic Coding.

0% percentile inside its fair comparison set

15%Raw benchmark value

Coding generation

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #48 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74.6%
Percentile: 30.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_generation. Category: Coding.

30.8% percentile inside its fair comparison set

74.6%Raw benchmark value

Coding completion

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65.2%
Percentile: 1.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_completion. Category: Coding.

1.5% percentile inside its fair comparison set

65.2%Raw benchmark value

Debugging

BB · Coding · Rubric

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #6 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 86.1%
Percentile: 79.2%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-debugging.

79.2% percentile inside its fair comparison set

86.1%Raw benchmark value

Refactoring

BB · Coding · Rubric

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #7 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 69.1%
Percentile: 71.4%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-refactoring.

71.4% percentile inside its fair comparison set

69.1%Raw benchmark value

Security

BB · Coding · Rubric

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #7 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 81.9%
Percentile: 76%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-security.

76% percentile inside its fair comparison set

81.9%Raw benchmark value

UI bench

BB · Coding · Rubric

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #17 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 58.4%
Percentile: 27.3%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-ui.

27.3% percentile inside its fair comparison set

58.4%Raw benchmark value

Speed throughput

BB · Coding · Speed / cost

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #2 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 302.1 t/s
Percentile: 96%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-throughput.

96% percentile inside its fair comparison set

302.1 t/sRaw benchmark value

Speed TTFT

BB · Coding · Speed / cost

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #15 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 3131.00ms
Percentile: 44%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-ttft.

44% percentile inside its fair comparison set

3131.00msRaw benchmark value

Speed cost

BB · Coding · Speed / cost

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #14 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: $0.1 $
Percentile: 48%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-speed-cost.

48% percentile inside its fair comparison set

$0.1 $Raw benchmark value

Cost strict

BB · Coding · Speed / cost

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 100%
Percentile: 100%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-cost-strict.

100% percentile inside its fair comparison set

100%Raw benchmark value

Cost per win

BB · Coding · Speed / cost

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: $0 $
Percentile: 100%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-cost-per-win.

100% percentile inside its fair comparison set

$0 $Raw benchmark value

Score per dollar

BB · Coding · Speed / cost

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 33,515
Percentile: 100%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-score-per-dollar.

100% percentile inside its fair comparison set

33,515Raw benchmark value

Cost spend

BB · Coding · Speed / cost

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: $0.1 $
Percentile: 100%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-cost-spend.

100% percentile inside its fair comparison set

$0.1 $Raw benchmark value

Overall quality

BB · Coding · Combined

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #3 · Source label: Grok 4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 90.6%
Percentile: 90.9%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-overall-quality.

90.9% percentile inside its fair comparison set

90.6%Raw benchmark value

Overall vibe

BB · Coding · Combined

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: Grok 4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 90.3%
Percentile: 100%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-overall-vibe.

100% percentile inside its fair comparison set

90.3%Raw benchmark value

Overall coverage

BB · Coding · Combined

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: Grok 4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 100%
Percentile: 100%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-overall-coverage.

100% percentile inside its fair comparison set

100%Raw benchmark value

Reasoning / math / science18 benchmarks59.2%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #289 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 6.8%
Percentile: 45.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

45.6% percentile inside its fair comparison set

6.8%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #261 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 65.8%
Percentile: 47.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

47.3% percentile inside its fair comparison set

65.8%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #232 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 50.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

50.1% percentile inside its fair comparison set

0%Raw benchmark value

Text Arena · Math

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #112 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 69.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: math. Source rank: #125. Votes: 3402. Organization: xai. License: Proprietary.

69.1% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,408 - 1,430

Text Arena · Math · No Style Control

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #158 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,388
Percentile: 56.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: math. Source rank: #174. Votes: 3402. Organization: xai. License: Proprietary.

56.3% percentile inside its fair comparison set

1,388Raw benchmark valueCI 1,377 - 1,398

GPQA Diamond

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #22 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 91.4%
Percentile: 83.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: gpqa; provider: SpaceXAI.

83.1% percentile inside its fair comparison set

91.4%Raw benchmark valueCI 88.7% - 94.2%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #53 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.8%
Percentile: 58.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmlu_pro; provider: SpaceXAI.

58.4% percentile inside its fair comparison set

85.8%Raw benchmark valueCI 85.2% - 86.5%

Mathematics

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #54 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84.3%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Mathematics. Tasks scored: 4.

18.5% percentile inside its fair comparison set

84.3%Raw benchmark value

Reasoning

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #63 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70.8%
Percentile: 4.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Reasoning. Tasks scored: 4.

4.6% percentile inside its fair comparison set

70.8%Raw benchmark value

AMPS Hard

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #49 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 97%
Percentile: 32.3%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: AMPS_Hard. Category: Mathematics.

32.3% percentile inside its fair comparison set

97%Raw benchmark value

Integrals with game

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #51 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 63%
Percentile: 23.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: integrals_with_game. Category: Mathematics.

23.1% percentile inside its fair comparison set

63%Raw benchmark value

Math competition

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #41 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 95.1%
Percentile: 49.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: math_comp. Category: Mathematics.

49.2% percentile inside its fair comparison set

95.1%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #64 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.3%
Percentile: 3.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: olympiad. Category: Mathematics.

3.1% percentile inside its fair comparison set

82.3%Raw benchmark value

Theory of mind

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #63 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 61.5%
Percentile: 4.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: theory_of_mind. Category: Reasoning.

4.6% percentile inside its fair comparison set

61.5%Raw benchmark value

Zebra puzzle

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #63 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 57.8%
Percentile: 4.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: zebra_puzzle. Category: Reasoning.

4.6% percentile inside its fair comparison set

57.8%Raw benchmark value

Spatial

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #23 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 72.3%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: spatial. Category: Reasoning.

72.3% percentile inside its fair comparison set

98%Raw benchmark value

Logic with navigation

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #54 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 66%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: logic_with_navigation. Category: Reasoning.

18.5% percentile inside its fair comparison set

66%Raw benchmark value

Reasoning

BB · Reasoning / math / science · Rubric

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #2 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 40.9%
Percentile: 95.2%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-reasoning.

95.2% percentile inside its fair comparison set

40.9%Raw benchmark value

Professional reasoning37 benchmarks41.6%

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #21 · Source label: Grok 4.3 (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 17%
Percentile: 37.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

37.5% percentile inside its fair comparison set

17%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #99 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 70%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: expert. Source rank: #111. Votes: 7495. Organization: xai. License: Proprietary.

70% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,444 - 1,460

Text Arena · Industry Business And Management And Financial Operations

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #92 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 75.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_business_and_management_and_financial_operations. Source rank: #104. Votes: 14218. Organization: xai. License: Proprietary.

75.3% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,433 - 1,445

Text Arena · Industry Entertainment And Sports And Media

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #78 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 79.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_entertainment_and_sports_and_media. Source rank: #86. Votes: 17207. Organization: xai. License: Proprietary.

79.4% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,410 - 1,422

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #98 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 72.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_legal_and_government. Source rank: #111. Votes: 5778. Organization: xai. License: Proprietary.

72.2% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,430 - 1,448

Text Arena · Industry Life And Physical And Social Science

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #86 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 77.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_life_and_physical_and_social_science. Source rank: #94. Votes: 11780. Organization: xai. License: Proprietary.

77.3% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,451 - 1,464

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #108 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 69.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_mathematical. Source rank: #118. Votes: 3921. Organization: xai. License: Proprietary.

69.9% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,421 - 1,442

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #93 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 73.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_medicine_and_healthcare. Source rank: #106. Votes: 5340. Organization: xai. License: Proprietary.

73.4% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,442 - 1,460

Text Arena · Industry Software And It Services

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #85 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 77.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_software_and_it_services. Source rank: #93. Votes: 28457. Organization: xai. License: Proprietary.

77.7% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,474 - 1,484

Text Arena · Industry Writing And Literature And Language

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #78 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 79.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_writing_and_literature_and_language. Source rank: #87. Votes: 18603. Organization: xai. License: Proprietary.

79.5% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,418 - 1,430

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #149 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 54.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: expert. Source rank: #166. Votes: 7495. Organization: xai. License: Proprietary.

54.7% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,377 - 1,392

Text Arena · Industry Business And Management And Financial Operations · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #148 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,381
Percentile: 60.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_business_and_management_and_financial_operations. Source rank: #163. Votes: 14218. Organization: xai. License: Proprietary.

60.2% percentile inside its fair comparison set

1,381Raw benchmark valueCI 1,375 - 1,387

Text Arena · Industry Entertainment And Sports And Media · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #127 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,370
Percentile: 66.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_entertainment_and_sports_and_media. Source rank: #140. Votes: 17207. Organization: xai. License: Proprietary.

66.3% percentile inside its fair comparison set

1,370Raw benchmark valueCI 1,365 - 1,376

Text Arena · Industry Legal And Government · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #153 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 56.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_legal_and_government. Source rank: #170. Votes: 5778. Organization: xai. License: Proprietary.

56.4% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,377 - 1,394

Text Arena · Industry Life And Physical And Social Science · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #149 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 60.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_life_and_physical_and_social_science. Source rank: #165. Votes: 11780. Organization: xai. License: Proprietary.

60.4% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,392 - 1,405

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #148 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 58.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_mathematical. Source rank: #162. Votes: 3921. Organization: xai. License: Proprietary.

58.7% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,386 - 1,406

Text Arena · Industry Medicine And Healthcare · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #155 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,383
Percentile: 55.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_medicine_and_healthcare. Source rank: #173. Votes: 5340. Organization: xai. License: Proprietary.

55.5% percentile inside its fair comparison set

1,383Raw benchmark valueCI 1,374 - 1,393

Text Arena · Industry Software And It Services · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #141 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 62.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_software_and_it_services. Source rank: #155. Votes: 28457. Organization: xai. License: Proprietary.

62.8% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,411 - 1,421

Text Arena · Industry Writing And Literature And Language · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #125 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 66.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_writing_and_literature_and_language. Source rank: #138. Votes: 18603. Organization: xai. License: Proprietary.

66.9% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,379 - 1,391

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #54 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 15.4%
Percentile: 22.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_research; provider: SpaceXAI.

22.1% percentile inside its fair comparison set

15.4%Raw benchmark valueCI 10.5% - 20.3%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

Completing legal work with documents, spreadsheets, presentations, and file-system tools.

Rank #53 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0.4%
Percentile: 24.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: hlab; provider: SpaceXAI.

24.6% percentile inside its fair comparison set

0.4%Raw benchmark valueCI 0.4% - 0.4%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #31 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.5%
Percentile: 77.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_bench; provider: SpaceXAI.

77.8% percentile inside its fair comparison set

84.5%Raw benchmark valueCI 83.6% - 85.3%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #57 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 37.7%
Percentile: 18.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: fabv2; provider: SpaceXAI.

18.8% percentile inside its fair comparison set

37.7%Raw benchmark valueCI 37% - 38.5%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #69 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 38.1%
Percentile: 28.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medcode; provider: SpaceXAI.

28.4% percentile inside its fair comparison set

38.1%Raw benchmark valueCI 34% - 42.1%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #73 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74.4%
Percentile: 25%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medscribe; provider: SpaceXAI.

25% percentile inside its fair comparison set

74.4%Raw benchmark valueCI 70.4% - 78.4%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #82 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 19.7%
Percentile: 0%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: sage; provider: SpaceXAI.

0% percentile inside its fair comparison set

19.7%Raw benchmark valueCI 14.5% - 24.9%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #41 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 51.7%
Percentile: 11.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: public-benefits-bench; provider: SpaceXAI.

11.1% percentile inside its fair comparison set

51.7%Raw benchmark valueCI 49.1% - 54.2%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #28 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 40.6%
Percentile: 18.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: skillsbench; provider: SpaceXAI.

18.2% percentile inside its fair comparison set

40.6%Raw benchmark valueCI 31.6% - 49.7%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #83 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 70.8%
Percentile: 36.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: SpaceXAI.

36.4% percentile inside its fair comparison set

70.8%Raw benchmark valueCI 69.1% - 72.6%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #63 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 55.8%
Percentile: 4.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Data Analysis. Tasks scored: 3.

4.6% percentile inside its fair comparison set

55.8%Raw benchmark value

Overall

LB · Professional reasoning · Objective

Average objective performance across LiveBench's current public category mix.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62.2%
Percentile: 0%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category averages included: 7.

0% percentile inside its fair comparison set

62.2%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #63 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 28%
Percentile: 4.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: consecutive_events. Category: Data Analysis.

4.6% percentile inside its fair comparison set

28%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #64 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 41.3%
Percentile: 3.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablejoin. Category: Data Analysis.

3.1% percentile inside its fair comparison set

41.3%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #33 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 61.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablereformat. Category: Data Analysis.

61.5% percentile inside its fair comparison set

98%Raw benchmark value

Public Benefits Bench v1

VALS-AI · Professional reasoning · Objective

Answering public-benefits questions across the benefits lifecycle.

Rank #11 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 50.1%
Percentile: 16.7%
Last updated: stale
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: public-benefits-bench-v1; provider: SpaceXAI.

16.7% percentile inside its fair comparison set

50.1%Raw benchmark valueCI 47.5% - 52.6%

Hallucination

BB · Professional reasoning · Rubric

Accuracy and fabrication resistance under prompts that invite unsupported claims.

Rank #1 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 79.8%
Percentile: 100%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-hallucination.

100% percentile inside its fair comparison set

79.8%Raw benchmark value

BS pushback

BB · Professional reasoning · Rubric

Resistance to confidently accepting bogus assumptions in expert-style prompts.

Rank #5 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 91%
Percentile: 77.8%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-pushback.

77.8% percentile inside its fair comparison set

91%Raw benchmark value

Search / tool use3 benchmarks60.5%

Tau2-Bench Telecom

AA · Search / tool use · Objective

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #115 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 65.8%
Percentile: 66.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

66.4% percentile inside its fair comparison set

65.8%Raw benchmark value

Search Arena

AR · Search / tool use · Human

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #16 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,193
Percentile: 54.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: overall. Source rank: #17. Votes: 91483. Organization: xai. License: Proprietary.

54.5% percentile inside its fair comparison set

1,193Raw benchmark valueCI 1,188 - 1,199

Search Arena · No Style Control

AR · Search / tool use · Human

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #21 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,165
Percentile: 39.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: overall. Source rank: #23. Votes: 91483. Organization: xai. License: Proprietary.

39.4% percentile inside its fair comparison set

1,165Raw benchmark valueCI 1,160 - 1,170

Long context2 benchmarks65.4%

Long Context Reasoning

AA · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #289 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 32.3%
Percentile: 36.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

36.7% percentile inside its fair comparison set

32.3%Raw benchmark value

CorpFin v2

VALS-AI · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #8 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.5%
Percentile: 94%
Last updated: aging
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: corp_fin_v2; provider: SpaceXAI.

94% percentile inside its fair comparison set

68.5%Raw benchmark valueCI 66.7% - 70.3%

Vision understanding18 benchmarks55.7%

MMMU-Pro

AA · Vision understanding · Objective

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #120 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 64.8%
Percentile: 42.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

42.8% percentile inside its fair comparison set

64.8%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #51 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,243
Percentile: 64%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: overall. Source rank: #56. Votes: 26300. Organization: xai. License: Proprietary.

64% percentile inside its fair comparison set

1,243Raw benchmark valueCI 1,237 - 1,249

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #37 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,248
Percentile: 56.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: creative_writing_vision. Source rank: #42. Votes: 1865. Organization: xai. License: Proprietary.

56.1% percentile inside its fair comparison set

1,248Raw benchmark valueCI 1,233 - 1,263

Vision Arena · Diagram

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #53 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,265
Percentile: 47.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: diagram. Source rank: #59. Votes: 6970. Organization: xai. License: Proprietary.

47.5% percentile inside its fair comparison set

1,265Raw benchmark valueCI 1,256 - 1,274

Vision Arena · English

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #48 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,247
Percentile: 65.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: english. Source rank: #53. Votes: 10586. Organization: xai. License: Proprietary.

65.9% percentile inside its fair comparison set

1,247Raw benchmark valueCI 1,239 - 1,256

Vision Arena · Entity Recognition

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #17 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,220
Percentile: 60%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: entity_recognition. Source rank: #19. Votes: 132. Organization: xai. License: Proprietary.

60% percentile inside its fair comparison set

1,220Raw benchmark valueCI 1,175 - 1,266

Vision Arena · Homework

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #58 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,253
Percentile: 40.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: homework. Source rank: #67. Votes: 3329. Organization: xai. License: Proprietary.

40.6% percentile inside its fair comparison set

1,253Raw benchmark valueCI 1,242 - 1,264

Vision Arena · Humor

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #41 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,226
Percentile: 45.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: humor. Source rank: #46. Votes: 993. Organization: xai. License: Proprietary.

45.2% percentile inside its fair comparison set

1,226Raw benchmark valueCI 1,207 - 1,246

Vision Arena · Ocr

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #53 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,252
Percentile: 48%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: ocr. Source rank: #59. Votes: 18559. Organization: xai. License: Proprietary.

48% percentile inside its fair comparison set

1,252Raw benchmark valueCI 1,245 - 1,258

Vision Arena · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,229
Percentile: 53.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: overall. Source rank: #74. Votes: 26300. Organization: xai. License: Proprietary.

53.2% percentile inside its fair comparison set

1,229Raw benchmark valueCI 1,224 - 1,235

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #49 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,237
Percentile: 41.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: creative_writing_vision. Source rank: #56. Votes: 1865. Organization: xai. License: Proprietary.

41.5% percentile inside its fair comparison set

1,237Raw benchmark valueCI 1,222 - 1,251

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #68 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,239
Percentile: 32.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: diagram. Source rank: #77. Votes: 6970. Organization: xai. License: Proprietary.

32.3% percentile inside its fair comparison set

1,239Raw benchmark valueCI 1,231 - 1,248

Vision Arena · English · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,236
Percentile: 52.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: english. Source rank: #73. Votes: 10586. Organization: xai. License: Proprietary.

52.9% percentile inside its fair comparison set

1,236Raw benchmark valueCI 1,228 - 1,244

Vision Arena · Entity Recognition · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #23 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,227
Percentile: 45%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: entity_recognition. Source rank: #26. Votes: 132. Organization: xai. License: Proprietary.

45% percentile inside its fair comparison set

1,227Raw benchmark valueCI 1,181 - 1,273

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #67 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,240
Percentile: 31.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: homework. Source rank: #76. Votes: 3329. Organization: xai. License: Proprietary.

31.3% percentile inside its fair comparison set

1,240Raw benchmark valueCI 1,229 - 1,251

Vision Arena · Humor · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #52 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,219
Percentile: 30.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: humor. Source rank: #60. Votes: 993. Organization: xai. License: Proprietary.

30.1% percentile inside its fair comparison set

1,219Raw benchmark valueCI 1,200 - 1,239

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #68 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,235
Percentile: 33%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: ocr. Source rank: #76. Votes: 18559. Organization: xai. License: Proprietary.

33% percentile inside its fair comparison set

1,235Raw benchmark valueCI 1,229 - 1,241

MMMU Pro

VALS-AI · Vision understanding · Objective

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #34 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.1%
Percentile: 60.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmmu; provider: SpaceXAI.

60.2% percentile inside its fair comparison set

83.1%Raw benchmark valueCI 81.3% - 84.8%

Document understanding2 benchmarks12.1%

MortgageTax

VALS-AI · Document understanding · Objective

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #77 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 48.3%
Percentile: 11.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mortgage_tax; provider: SpaceXAI.

11.6% percentile inside its fair comparison set

48.3%Raw benchmark valueCI 46.3% - 50.2%

Vals Multimodal Index

VALS-AI · Document understanding · Combined

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #29 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 43
Percentile: 12.5%
Last updated: aging
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vals_multimodal_index; provider: SpaceXAI.

12.5% percentile inside its fair comparison set

43Raw benchmark valueCI 41 - 46

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #90 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 74.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: chinese. Source rank: #97. Votes: 4499. Organization: xai. License: Proprietary.

74.7% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,467 - 1,486

Text Arena · French

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #75 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 71.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: french. Source rank: #84. Votes: 2565. Organization: xai. License: Proprietary.

71.2% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,449 - 1,477

Text Arena · German

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #72 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 73.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: german. Source rank: #84. Votes: 1037. Organization: xai. License: Proprietary.

73.9% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,420 - 1,458

Text Arena · Japanese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #52 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,426
Percentile: 79%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: japanese. Source rank: #59. Votes: 849. Organization: xai. License: Proprietary.

79% percentile inside its fair comparison set

1,426Raw benchmark valueCI 1,404 - 1,448

Text Arena · Korean

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #61 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 75.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: korean. Source rank: #68. Votes: 1120. Organization: xai. License: Proprietary.

75.4% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,386 - 1,425

Text Arena · Non English

AR · Multilingual · Human

Observed user preference in Arena's Text Arena non_english leaderboard.

Rank #86 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 77.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: non_english. Source rank: #95. Votes: 38476. Organization: xai. License: Proprietary.

77.4% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,423 - 1,432

Text Arena · Polish

AR · Multilingual · Human

Observed user preference in Arena's Text Arena polish leaderboard.

Rank #61 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 69.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: polish. Source rank: #74. Votes: 1204. Organization: xai. License: Proprietary.

69.8% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,428 - 1,463

Text Arena · Russian

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #82 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 76.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: russian. Source rank: #91. Votes: 7498. Organization: xai. License: Proprietary.

76.2% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,432 - 1,447

Text Arena · Spanish

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #75 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 71.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: spanish. Source rank: #83. Votes: 1999. Organization: xai. License: Proprietary.

71.4% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,423 - 1,453

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #143 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 59.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: chinese. Source rank: #159. Votes: 4499. Organization: xai. License: Proprietary.

59.7% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,412 - 1,431

Text Arena · French · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #120 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 53.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: french. Source rank: #133. Votes: 2565. Organization: xai. License: Proprietary.

53.7% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,399 - 1,426

Text Arena · German · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #109 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,394
Percentile: 60.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: german. Source rank: #123. Votes: 1037. Organization: xai. License: Proprietary.

60.3% percentile inside its fair comparison set

1,394Raw benchmark valueCI 1,375 - 1,413

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #82 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,380
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: japanese. Source rank: #93. Votes: 849. Organization: xai. License: Proprietary.

66.7% percentile inside its fair comparison set

1,380Raw benchmark valueCI 1,357 - 1,402

Text Arena · Korean · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #111 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,356
Percentile: 54.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: korean. Source rank: #125. Votes: 1120. Organization: xai. License: Proprietary.

54.9% percentile inside its fair comparison set

1,356Raw benchmark valueCI 1,337 - 1,375

Text Arena · Non English · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena non_english leaderboard.

Rank #137 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 63.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: non_english. Source rank: #152. Votes: 38476. Organization: xai. License: Proprietary.

63.8% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,380 - 1,389

Text Arena · Polish · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena polish leaderboard.

Rank #105 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 47.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: polish. Source rank: #118. Votes: 1204. Organization: xai. License: Proprietary.

47.7% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,381 - 1,416

Text Arena · Russian · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #121 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 64.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: russian. Source rank: #135. Votes: 7498. Organization: xai. License: Proprietary.

64.8% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,391 - 1,406

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #130 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 50.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: spanish. Source rank: #144. Votes: 1999. Organization: xai. License: Proprietary.

50.2% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,383 - 1,413

Vision Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Vision Arena chinese leaderboard.

Rank #48 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,278
Percentile: 54.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: chinese. Source rank: #53. Votes: 1549. Organization: xai. License: Proprietary.

54.8% percentile inside its fair comparison set

1,278Raw benchmark valueCI 1,260 - 1,295

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Vision Arena chinese leaderboard.

Rank #59 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,257
Percentile: 44.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: chinese. Source rank: #68. Votes: 1549. Organization: xai. License: Proprietary.

44.2% percentile inside its fair comparison set

1,257Raw benchmark valueCI 1,239 - 1,274

Source links and registry checks

official

xAI models and pricing

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

official

LiveBench

Oct 3, 2026

source →

Model profile · xAI

Grok 4.3

Closed weightspremium · registry tag 2026 frontier revision

Verified but aging

Reads as verified but aging across the resolved source data. Capability fit excludes speed and cost.

Visible coverage: 63.7%
Verified coverage: 63.7%
Spread: 100%
Last verified: Oct 3, 2026

50%capability fit

textcodevisionsearchdocument11 aliases46 official source links

Open compare

Data version

Current snapshot.

Published Oct 3, 2026Model list checked4 stale sources105 claim warnings9 providers · 1334 tracked models

The registry snapshot and page stamp are shown so a stale deploy is visible at a glance. View live data status.

Source-linked scores by benchmark

Verified but agingThis model currently reads as verified but aging across the resolved source data.

Chat / text36 benchmarks55.8%

Intelligence Index

AA · Chat / text · Combined

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #227 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 14
Percentile: 59.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

59.3% percentile inside its fair comparison set

14Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #178 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 23.7%
Percentile: 60.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

60.9% percentile inside its fair comparison set

23.7%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #189 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 25.5%
Percentile: 58.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

58.5% percentile inside its fair comparison set

25.5%Raw benchmark value

IFBench

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #120 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.6%
Percentile: 65.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

65.8% percentile inside its fair comparison set

47.6%Raw benchmark value

Input price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #239 · Source label: Grok 4.3 (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.3 /1M input tokens
Percentile: 34.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

34.2% percentile inside its fair comparison set

$1.3 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #186 · Source label: Grok 4.3 (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $2.5 /1M output tokens
Percentile: 49.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

49.4% percentile inside its fair comparison set

$2.5 /1M output tokensRaw benchmark value

Output Speed

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #83 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 118.8 tokens/s
Percentile: 68.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

68.7% percentile inside its fair comparison set

118.8 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #215 · Source label: Grok 4.3 (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 22.53s
Percentile: 18.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

18.9% percentile inside its fair comparison set

22.53sRaw benchmark value

Time to first answer token

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #148 · Source label: Grok 4.3 (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 22.53s
Percentile: 43.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

43.9% percentile inside its fair comparison set

22.53sRaw benchmark value

Text Arena

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #86 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 77.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: overall. Source rank: #94. Votes: 71150. Organization: xai. License: Proprietary.

77.4% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,438 - 1,445

Text Arena · Creative Writing

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #72 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 81%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: creative_writing. Source rank: #80. Votes: 13173. Organization: xai. License: Proprietary.

81% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,416 - 1,429

Text Arena · English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #82 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 78.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: english. Source rank: #90. Votes: 32673. Organization: xai. License: Proprietary.

78.5% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,446 - 1,456

Text Arena · Exclude Ties

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #86 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 77.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: exclude_ties. Source rank: #94. Votes: 54660. Organization: xai. License: Proprietary.

77.4% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,435 - 1,445

Text Arena · Hard Prompts

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #96 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 74.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: hard_prompts. Source rank: #106. Votes: 47577. Organization: xai. License: Proprietary.

74.7% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,452 - 1,460

Text Arena · Hard Prompts English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #93 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 75.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: hard_prompts_english. Source rank: #102. Votes: 22373. Organization: xai. License: Proprietary.

75.4% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,457 - 1,468

Text Arena · Instruction Following

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #109 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 71.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: instruction_following. Source rank: #122. Votes: 25039. Organization: xai. License: Proprietary.

71.3% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,409 - 1,420

Text Arena · Longer Query

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #93 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 74.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: longer_query. Source rank: #102. Votes: 33150. Organization: xai. License: Proprietary.

74.1% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,438 - 1,448

Text Arena · Multi Turn

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #87 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 77%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: multi_turn. Source rank: #97. Votes: 12848. Organization: xai. License: Proprietary.

77% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,440 - 1,453

Text Arena · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #139 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 63.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: overall. Source rank: #154. Votes: 71150. Organization: xai. License: Proprietary.

63.3% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,393 - 1,400

Text Arena · Creative Writing · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #120 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,380
Percentile: 68.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: creative_writing. Source rank: #131. Votes: 13173. Organization: xai. License: Proprietary.

68.2% percentile inside its fair comparison set

1,380Raw benchmark valueCI 1,374 - 1,387

Text Arena · English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #142 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: english. Source rank: #158. Votes: 32673. Organization: xai. License: Proprietary.

62.5% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,400 - 1,409

Text Arena · Exclude Ties · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #138 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,377
Percentile: 63.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: exclude_ties. Source rank: #153. Votes: 54660. Organization: xai. License: Proprietary.

63.6% percentile inside its fair comparison set

1,377Raw benchmark valueCI 1,373 - 1,382

Text Arena · Hard Prompts · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #149 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 60.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: hard_prompts. Source rank: #166. Votes: 47577. Organization: xai. License: Proprietary.

60.6% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,392 - 1,401

Text Arena · Hard Prompts English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #148 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 60.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: hard_prompts_english. Source rank: #164. Votes: 22373. Organization: xai. License: Proprietary.

60.7% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,396 - 1,407

Text Arena · Instruction Following · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #152 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 59.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: instruction_following. Source rank: #170. Votes: 25039. Organization: xai. License: Proprietary.

59.8% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,360 - 1,371

Text Arena · Longer Query · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #138 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,393
Percentile: 61.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: longer_query. Source rank: #155. Votes: 33150. Organization: xai. License: Proprietary.

61.4% percentile inside its fair comparison set

1,393Raw benchmark valueCI 1,388 - 1,398

Text Arena · Multi Turn · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #128 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 66%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: multi_turn. Source rank: #141. Votes: 12848. Organization: xai. License: Proprietary.

66% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,399 - 1,412

Instruction following

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #52 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62.8%
Percentile: 21.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: IF. Tasks scored: 4.

21.5% percentile inside its fair comparison set

62.8%Raw benchmark value

Language

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #56 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.6%
Percentile: 15.4%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Language. Tasks scored: 3.

15.4% percentile inside its fair comparison set

73.6%Raw benchmark value

Paraphrase

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #42 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64.4%
Percentile: 36.9%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: paraphrase. Category: IF.

36.9% percentile inside its fair comparison set

64.4%Raw benchmark value

Simplify

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #52 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 57.6%
Percentile: 21.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: simplify. Category: IF.

21.5% percentile inside its fair comparison set

57.6%Raw benchmark value

Story generation

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #37 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70.6%
Percentile: 44.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: story_generation. Category: IF.

44.6% percentile inside its fair comparison set

70.6%Raw benchmark value

Summarize

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #59 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58.4%
Percentile: 10.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: summarize. Category: IF.

10.8% percentile inside its fair comparison set

58.4%Raw benchmark value

Connections

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #50 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94%
Percentile: 26.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: connections. Category: Language.

26.2% percentile inside its fair comparison set

94%Raw benchmark value

Plot unscrambling

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #60 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 48.7%
Percentile: 9.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: plot_unscrambling. Category: Language.

9.2% percentile inside its fair comparison set

48.7%Raw benchmark value

Typos

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #42 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78%
Percentile: 38.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typos. Category: Language.

38.5% percentile inside its fair comparison set

78%Raw benchmark value

Coding35 benchmarks45.1%

Terminal-Bench Hard

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #110 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18.9%
Percentile: 67.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

67.2% percentile inside its fair comparison set

18.9%Raw benchmark value

SciCode

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #146 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 39.4%
Percentile: 26.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

26.8% percentile inside its fair comparison set

39.4%Raw benchmark value

Text Arena · Coding

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #90 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 76%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: coding. Source rank: #99. Votes: 19889. Organization: xai. License: Proprietary.

76% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,482 - 1,493

Text Arena · Coding · No Style Control

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #137 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 63.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: coding. Source rank: #151. Votes: 19889. Organization: xai. License: Proprietary.

63.3% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,409 - 1,420

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #68 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 19.4%
Percentile: 28%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vibe-code; provider: SpaceXAI.

28% percentile inside its fair comparison set

19.4%Raw benchmark valueCI 11.1% - 27.7%

WebDev Arena

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #100 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,357
Percentile: 22%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: overall. Source rank: #105. Votes: 15057. Organization: xai. License: Proprietary.

22% percentile inside its fair comparison set

1,357Raw benchmark valueCI 1,350 - 1,363

Code Arena · Webdev Html

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #96 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,364
Percentile: 24%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: webdev-html. Source rank: #101. Votes: 1776. Organization: xai. License: Proprietary.

24% percentile inside its fair comparison set

1,364Raw benchmark valueCI 1,349 - 1,380

Code Arena · Webdev React

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #90 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,353
Percentile: 21.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: webdev-react. Source rank: #97. Votes: 11566. Organization: xai. License: Proprietary.

21.2% percentile inside its fair comparison set

1,353Raw benchmark valueCI 1,346 - 1,360

Code Migration

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #61 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 6.8%
Percentile: 11.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: code-migration; provider: SpaceXAI.

11.8% percentile inside its fair comparison set

6.8%Raw benchmark valueCI 4.5% - 9.1%

ProgramBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #54 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0%
Percentile: 51.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: programbench; provider: SpaceXAI.

51.7% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

Terminal-Bench 2.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #60 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 41.9%
Percentile: 11.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: SpaceXAI.

11.9% percentile inside its fair comparison set

41.9%Raw benchmark valueCI 36.8% - 47.1%

Code Arena · Image To Webdev

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #42 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,373
Percentile: 6.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: image_to_webdev. Source rank: #46. Votes: 5444. Organization: xai. License: Proprietary.

6.8% percentile inside its fair comparison set

1,373Raw benchmark valueCI 1,364 - 1,383

SWE-bench Verified

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #53 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71.4%
Percentile: 36.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: swebench; provider: SpaceXAI.

36.6% percentile inside its fair comparison set

71.4%Raw benchmark valueCI 67.4% - 75.4%

LiveCodeBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #37 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.5%
Percentile: 71.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: lcb; provider: SpaceXAI.

71.2% percentile inside its fair comparison set

84.5%Raw benchmark valueCI 82.5% - 86.5%

Agentic coding

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 18.5%
Percentile: 0%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Agentic Coding. Tasks scored: 3.

0% percentile inside its fair comparison set

18.5%Raw benchmark value

Coding

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #61 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 69.9%
Percentile: 7.7%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Coding. Tasks scored: 2.

7.7% percentile inside its fair comparison set

69.9%Raw benchmark value

JavaScript

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 27.3%
Percentile: 0%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: javascript. Category: Agentic Coding.

0% percentile inside its fair comparison set

27.3%Raw benchmark value

TypeScript

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 13.3%
Percentile: 0%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typescript. Category: Agentic Coding.

0% percentile inside its fair comparison set

13.3%Raw benchmark value

Python

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 15%
Percentile: 0%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: python. Category: Agentic Coding.

0% percentile inside its fair comparison set

15%Raw benchmark value

Coding generation

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #48 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74.6%
Percentile: 30.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_generation. Category: Coding.

30.8% percentile inside its fair comparison set

74.6%Raw benchmark value

Coding completion

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65.2%
Percentile: 1.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_completion. Category: Coding.

1.5% percentile inside its fair comparison set

65.2%Raw benchmark value

Debugging

BB · Coding · Rubric

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #6 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 86.1%
Percentile: 79.2%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-debugging.

79.2% percentile inside its fair comparison set

86.1%Raw benchmark value

Refactoring

BB · Coding · Rubric

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #7 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 69.1%
Percentile: 71.4%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-refactoring.

71.4% percentile inside its fair comparison set

69.1%Raw benchmark value

Security

BB · Coding · Rubric

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #7 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 81.9%
Percentile: 76%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-security.

76% percentile inside its fair comparison set

81.9%Raw benchmark value

UI bench

BB · Coding · Rubric

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #17 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 58.4%
Percentile: 27.3%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-ui.

27.3% percentile inside its fair comparison set

58.4%Raw benchmark value

Speed throughput

BB · Coding · Speed / cost

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #2 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 302.1 t/s
Percentile: 96%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-throughput.

96% percentile inside its fair comparison set

302.1 t/sRaw benchmark value

Speed TTFT

BB · Coding · Speed / cost

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #15 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 3131.00ms
Percentile: 44%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-ttft.

44% percentile inside its fair comparison set

3131.00msRaw benchmark value

Speed cost

BB · Coding · Speed / cost

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #14 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: $0.1 $
Percentile: 48%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-speed-cost.

48% percentile inside its fair comparison set

$0.1 $Raw benchmark value

Cost strict

BB · Coding · Speed / cost

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 100%
Percentile: 100%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-cost-strict.

100% percentile inside its fair comparison set

100%Raw benchmark value

Cost per win

BB · Coding · Speed / cost

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: $0 $
Percentile: 100%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-cost-per-win.

100% percentile inside its fair comparison set

$0 $Raw benchmark value

Score per dollar

BB · Coding · Speed / cost

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 33,515
Percentile: 100%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-score-per-dollar.

100% percentile inside its fair comparison set

33,515Raw benchmark value

Cost spend

BB · Coding · Speed / cost

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: $0.1 $
Percentile: 100%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-cost-spend.

100% percentile inside its fair comparison set

$0.1 $Raw benchmark value

Overall quality

BB · Coding · Combined

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #3 · Source label: Grok 4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 90.6%
Percentile: 90.9%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-overall-quality.

90.9% percentile inside its fair comparison set

90.6%Raw benchmark value

Overall vibe

BB · Coding · Combined

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: Grok 4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 90.3%
Percentile: 100%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-overall-vibe.

100% percentile inside its fair comparison set

90.3%Raw benchmark value

Overall coverage

BB · Coding · Combined

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: Grok 4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 100%
Percentile: 100%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-overall-coverage.

100% percentile inside its fair comparison set

100%Raw benchmark value

Reasoning / math / science18 benchmarks59.2%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #289 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 6.8%
Percentile: 45.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

45.6% percentile inside its fair comparison set

6.8%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #261 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 65.8%
Percentile: 47.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

47.3% percentile inside its fair comparison set

65.8%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #232 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 50.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

50.1% percentile inside its fair comparison set

0%Raw benchmark value

Text Arena · Math

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #112 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 69.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: math. Source rank: #125. Votes: 3402. Organization: xai. License: Proprietary.

69.1% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,408 - 1,430

Text Arena · Math · No Style Control

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #158 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,388
Percentile: 56.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: math. Source rank: #174. Votes: 3402. Organization: xai. License: Proprietary.

56.3% percentile inside its fair comparison set

1,388Raw benchmark valueCI 1,377 - 1,398

GPQA Diamond

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #22 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 91.4%
Percentile: 83.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: gpqa; provider: SpaceXAI.

83.1% percentile inside its fair comparison set

91.4%Raw benchmark valueCI 88.7% - 94.2%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #53 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.8%
Percentile: 58.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmlu_pro; provider: SpaceXAI.

58.4% percentile inside its fair comparison set

85.8%Raw benchmark valueCI 85.2% - 86.5%

Mathematics

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #54 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84.3%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Mathematics. Tasks scored: 4.

18.5% percentile inside its fair comparison set

84.3%Raw benchmark value

Reasoning

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #63 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70.8%
Percentile: 4.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Reasoning. Tasks scored: 4.

4.6% percentile inside its fair comparison set

70.8%Raw benchmark value

AMPS Hard

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #49 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 97%
Percentile: 32.3%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: AMPS_Hard. Category: Mathematics.

32.3% percentile inside its fair comparison set

97%Raw benchmark value

Integrals with game

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #51 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 63%
Percentile: 23.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: integrals_with_game. Category: Mathematics.

23.1% percentile inside its fair comparison set

63%Raw benchmark value

Math competition

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #41 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 95.1%
Percentile: 49.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: math_comp. Category: Mathematics.

49.2% percentile inside its fair comparison set

95.1%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #64 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.3%
Percentile: 3.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: olympiad. Category: Mathematics.

3.1% percentile inside its fair comparison set

82.3%Raw benchmark value

Theory of mind

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #63 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 61.5%
Percentile: 4.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: theory_of_mind. Category: Reasoning.

4.6% percentile inside its fair comparison set

61.5%Raw benchmark value

Zebra puzzle

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #63 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 57.8%
Percentile: 4.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: zebra_puzzle. Category: Reasoning.

4.6% percentile inside its fair comparison set

57.8%Raw benchmark value

Spatial

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #23 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 72.3%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: spatial. Category: Reasoning.

72.3% percentile inside its fair comparison set

98%Raw benchmark value

Logic with navigation

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #54 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 66%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: logic_with_navigation. Category: Reasoning.

18.5% percentile inside its fair comparison set

66%Raw benchmark value

Reasoning

BB · Reasoning / math / science · Rubric

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #2 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 40.9%
Percentile: 95.2%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-reasoning.

95.2% percentile inside its fair comparison set

40.9%Raw benchmark value

Professional reasoning37 benchmarks41.6%

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #21 · Source label: Grok 4.3 (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 17%
Percentile: 37.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

37.5% percentile inside its fair comparison set

17%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #99 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 70%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: expert. Source rank: #111. Votes: 7495. Organization: xai. License: Proprietary.

70% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,444 - 1,460

Text Arena · Industry Business And Management And Financial Operations

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #92 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 75.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_business_and_management_and_financial_operations. Source rank: #104. Votes: 14218. Organization: xai. License: Proprietary.

75.3% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,433 - 1,445

Text Arena · Industry Entertainment And Sports And Media

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #78 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 79.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_entertainment_and_sports_and_media. Source rank: #86. Votes: 17207. Organization: xai. License: Proprietary.

79.4% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,410 - 1,422

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #98 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 72.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_legal_and_government. Source rank: #111. Votes: 5778. Organization: xai. License: Proprietary.

72.2% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,430 - 1,448

Text Arena · Industry Life And Physical And Social Science

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #86 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 77.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_life_and_physical_and_social_science. Source rank: #94. Votes: 11780. Organization: xai. License: Proprietary.

77.3% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,451 - 1,464

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #108 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 69.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_mathematical. Source rank: #118. Votes: 3921. Organization: xai. License: Proprietary.

69.9% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,421 - 1,442

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #93 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 73.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_medicine_and_healthcare. Source rank: #106. Votes: 5340. Organization: xai. License: Proprietary.

73.4% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,442 - 1,460

Text Arena · Industry Software And It Services

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #85 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 77.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_software_and_it_services. Source rank: #93. Votes: 28457. Organization: xai. License: Proprietary.

77.7% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,474 - 1,484

Text Arena · Industry Writing And Literature And Language

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #78 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 79.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_writing_and_literature_and_language. Source rank: #87. Votes: 18603. Organization: xai. License: Proprietary.

79.5% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,418 - 1,430

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #149 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 54.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: expert. Source rank: #166. Votes: 7495. Organization: xai. License: Proprietary.

54.7% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,377 - 1,392

Text Arena · Industry Business And Management And Financial Operations · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #148 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,381
Percentile: 60.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_business_and_management_and_financial_operations. Source rank: #163. Votes: 14218. Organization: xai. License: Proprietary.

60.2% percentile inside its fair comparison set

1,381Raw benchmark valueCI 1,375 - 1,387

Text Arena · Industry Entertainment And Sports And Media · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #127 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,370
Percentile: 66.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_entertainment_and_sports_and_media. Source rank: #140. Votes: 17207. Organization: xai. License: Proprietary.

66.3% percentile inside its fair comparison set

1,370Raw benchmark valueCI 1,365 - 1,376

Text Arena · Industry Legal And Government · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #153 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 56.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_legal_and_government. Source rank: #170. Votes: 5778. Organization: xai. License: Proprietary.

56.4% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,377 - 1,394

Text Arena · Industry Life And Physical And Social Science · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #149 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 60.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_life_and_physical_and_social_science. Source rank: #165. Votes: 11780. Organization: xai. License: Proprietary.

60.4% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,392 - 1,405

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #148 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 58.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_mathematical. Source rank: #162. Votes: 3921. Organization: xai. License: Proprietary.

58.7% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,386 - 1,406

Text Arena · Industry Medicine And Healthcare · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #155 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,383
Percentile: 55.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_medicine_and_healthcare. Source rank: #173. Votes: 5340. Organization: xai. License: Proprietary.

55.5% percentile inside its fair comparison set

1,383Raw benchmark valueCI 1,374 - 1,393

Text Arena · Industry Software And It Services · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #141 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 62.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_software_and_it_services. Source rank: #155. Votes: 28457. Organization: xai. License: Proprietary.

62.8% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,411 - 1,421

Text Arena · Industry Writing And Literature And Language · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #125 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 66.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: industry_writing_and_literature_and_language. Source rank: #138. Votes: 18603. Organization: xai. License: Proprietary.

66.9% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,379 - 1,391

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #54 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 15.4%
Percentile: 22.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_research; provider: SpaceXAI.

22.1% percentile inside its fair comparison set

15.4%Raw benchmark valueCI 10.5% - 20.3%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

Completing legal work with documents, spreadsheets, presentations, and file-system tools.

Rank #53 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0.4%
Percentile: 24.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: hlab; provider: SpaceXAI.

24.6% percentile inside its fair comparison set

0.4%Raw benchmark valueCI 0.4% - 0.4%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #31 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.5%
Percentile: 77.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_bench; provider: SpaceXAI.

77.8% percentile inside its fair comparison set

84.5%Raw benchmark valueCI 83.6% - 85.3%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #57 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 37.7%
Percentile: 18.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: fabv2; provider: SpaceXAI.

18.8% percentile inside its fair comparison set

37.7%Raw benchmark valueCI 37% - 38.5%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #69 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 38.1%
Percentile: 28.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medcode; provider: SpaceXAI.

28.4% percentile inside its fair comparison set

38.1%Raw benchmark valueCI 34% - 42.1%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #73 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74.4%
Percentile: 25%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medscribe; provider: SpaceXAI.

25% percentile inside its fair comparison set

74.4%Raw benchmark valueCI 70.4% - 78.4%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #82 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 19.7%
Percentile: 0%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: sage; provider: SpaceXAI.

0% percentile inside its fair comparison set

19.7%Raw benchmark valueCI 14.5% - 24.9%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #41 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 51.7%
Percentile: 11.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: public-benefits-bench; provider: SpaceXAI.

11.1% percentile inside its fair comparison set

51.7%Raw benchmark valueCI 49.1% - 54.2%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #28 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 40.6%
Percentile: 18.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: skillsbench; provider: SpaceXAI.

18.2% percentile inside its fair comparison set

40.6%Raw benchmark valueCI 31.6% - 49.7%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #83 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 70.8%
Percentile: 36.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: SpaceXAI.

36.4% percentile inside its fair comparison set

70.8%Raw benchmark valueCI 69.1% - 72.6%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #63 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 55.8%
Percentile: 4.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Data Analysis. Tasks scored: 3.

4.6% percentile inside its fair comparison set

55.8%Raw benchmark value

Overall

LB · Professional reasoning · Objective

Average objective performance across LiveBench's current public category mix.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62.2%
Percentile: 0%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category averages included: 7.

0% percentile inside its fair comparison set

62.2%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #63 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 28%
Percentile: 4.6%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: consecutive_events. Category: Data Analysis.

4.6% percentile inside its fair comparison set

28%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #64 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 41.3%
Percentile: 3.1%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablejoin. Category: Data Analysis.

3.1% percentile inside its fair comparison set

41.3%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #33 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 61.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablereformat. Category: Data Analysis.

61.5% percentile inside its fair comparison set

98%Raw benchmark value

Public Benefits Bench v1

VALS-AI · Professional reasoning · Objective

Answering public-benefits questions across the benefits lifecycle.

Rank #11 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 50.1%
Percentile: 16.7%
Last updated: stale
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: public-benefits-bench-v1; provider: SpaceXAI.

16.7% percentile inside its fair comparison set

50.1%Raw benchmark valueCI 47.5% - 52.6%

Hallucination

BB · Professional reasoning · Rubric

Accuracy and fabrication resistance under prompts that invite unsupported claims.

Rank #1 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 79.8%
Percentile: 100%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-hallucination.

100% percentile inside its fair comparison set

79.8%Raw benchmark value

BS pushback

BB · Professional reasoning · Rubric

Resistance to confidently accepting bogus assumptions in expert-style prompts.

Rank #5 · Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: BridgeBench
Raw value: 91%
Percentile: 77.8%
Last updated: archived
Eligibility: headline eligible

Parsed from the BridgeBench page for bridgebench-pushback.

77.8% percentile inside its fair comparison set

91%Raw benchmark value

Search / tool use3 benchmarks60.5%

Tau2-Bench Telecom

AA · Search / tool use · Objective

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #115 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 65.8%
Percentile: 66.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

66.4% percentile inside its fair comparison set

65.8%Raw benchmark value

Search Arena

AR · Search / tool use · Human

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #16 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,193
Percentile: 54.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: overall. Source rank: #17. Votes: 91483. Organization: xai. License: Proprietary.

54.5% percentile inside its fair comparison set

1,193Raw benchmark valueCI 1,188 - 1,199

Search Arena · No Style Control

AR · Search / tool use · Human

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #21 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,165
Percentile: 39.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: overall. Source rank: #23. Votes: 91483. Organization: xai. License: Proprietary.

39.4% percentile inside its fair comparison set

1,165Raw benchmark valueCI 1,160 - 1,170

Long context2 benchmarks65.4%

Long Context Reasoning

AA · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #289 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 32.3%
Percentile: 36.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

36.7% percentile inside its fair comparison set

32.3%Raw benchmark value

CorpFin v2

VALS-AI · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #8 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.5%
Percentile: 94%
Last updated: aging
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: corp_fin_v2; provider: SpaceXAI.

94% percentile inside its fair comparison set

68.5%Raw benchmark valueCI 66.7% - 70.3%

Vision understanding18 benchmarks55.7%

MMMU-Pro

AA · Vision understanding · Objective

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #120 · Source label: Grok 4.3 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 64.8%
Percentile: 42.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

42.8% percentile inside its fair comparison set

64.8%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #51 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,243
Percentile: 64%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: overall. Source rank: #56. Votes: 26300. Organization: xai. License: Proprietary.

64% percentile inside its fair comparison set

1,243Raw benchmark valueCI 1,237 - 1,249

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #37 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,248
Percentile: 56.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: creative_writing_vision. Source rank: #42. Votes: 1865. Organization: xai. License: Proprietary.

56.1% percentile inside its fair comparison set

1,248Raw benchmark valueCI 1,233 - 1,263

Vision Arena · Diagram

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #53 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,265
Percentile: 47.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: diagram. Source rank: #59. Votes: 6970. Organization: xai. License: Proprietary.

47.5% percentile inside its fair comparison set

1,265Raw benchmark valueCI 1,256 - 1,274

Vision Arena · English

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #48 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,247
Percentile: 65.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: english. Source rank: #53. Votes: 10586. Organization: xai. License: Proprietary.

65.9% percentile inside its fair comparison set

1,247Raw benchmark valueCI 1,239 - 1,256

Vision Arena · Entity Recognition

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #17 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,220
Percentile: 60%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: entity_recognition. Source rank: #19. Votes: 132. Organization: xai. License: Proprietary.

60% percentile inside its fair comparison set

1,220Raw benchmark valueCI 1,175 - 1,266

Vision Arena · Homework

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #58 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,253
Percentile: 40.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: homework. Source rank: #67. Votes: 3329. Organization: xai. License: Proprietary.

40.6% percentile inside its fair comparison set

1,253Raw benchmark valueCI 1,242 - 1,264

Vision Arena · Humor

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #41 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,226
Percentile: 45.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: humor. Source rank: #46. Votes: 993. Organization: xai. License: Proprietary.

45.2% percentile inside its fair comparison set

1,226Raw benchmark valueCI 1,207 - 1,246

Vision Arena · Ocr

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #53 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,252
Percentile: 48%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: ocr. Source rank: #59. Votes: 18559. Organization: xai. License: Proprietary.

48% percentile inside its fair comparison set

1,252Raw benchmark valueCI 1,245 - 1,258

Vision Arena · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,229
Percentile: 53.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: overall. Source rank: #74. Votes: 26300. Organization: xai. License: Proprietary.

53.2% percentile inside its fair comparison set

1,229Raw benchmark valueCI 1,224 - 1,235

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #49 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,237
Percentile: 41.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: creative_writing_vision. Source rank: #56. Votes: 1865. Organization: xai. License: Proprietary.

41.5% percentile inside its fair comparison set

1,237Raw benchmark valueCI 1,222 - 1,251

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #68 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,239
Percentile: 32.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: diagram. Source rank: #77. Votes: 6970. Organization: xai. License: Proprietary.

32.3% percentile inside its fair comparison set

1,239Raw benchmark valueCI 1,231 - 1,248

Vision Arena · English · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #66 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,236
Percentile: 52.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: english. Source rank: #73. Votes: 10586. Organization: xai. License: Proprietary.

52.9% percentile inside its fair comparison set

1,236Raw benchmark valueCI 1,228 - 1,244

Vision Arena · Entity Recognition · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #23 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,227
Percentile: 45%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: entity_recognition. Source rank: #26. Votes: 132. Organization: xai. License: Proprietary.

45% percentile inside its fair comparison set

1,227Raw benchmark valueCI 1,181 - 1,273

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #67 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,240
Percentile: 31.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: homework. Source rank: #76. Votes: 3329. Organization: xai. License: Proprietary.

31.3% percentile inside its fair comparison set

1,240Raw benchmark valueCI 1,229 - 1,251

Vision Arena · Humor · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #52 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,219
Percentile: 30.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: humor. Source rank: #60. Votes: 993. Organization: xai. License: Proprietary.

30.1% percentile inside its fair comparison set

1,219Raw benchmark valueCI 1,200 - 1,239

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #68 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,235
Percentile: 33%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: ocr. Source rank: #76. Votes: 18559. Organization: xai. License: Proprietary.

33% percentile inside its fair comparison set

1,235Raw benchmark valueCI 1,229 - 1,241

MMMU Pro

VALS-AI · Vision understanding · Objective

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #34 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.1%
Percentile: 60.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmmu; provider: SpaceXAI.

60.2% percentile inside its fair comparison set

83.1%Raw benchmark valueCI 81.3% - 84.8%

Document understanding2 benchmarks12.1%

MortgageTax

VALS-AI · Document understanding · Objective

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #77 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 48.3%
Percentile: 11.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mortgage_tax; provider: SpaceXAI.

11.6% percentile inside its fair comparison set

48.3%Raw benchmark valueCI 46.3% - 50.2%

Vals Multimodal Index

VALS-AI · Document understanding · Combined

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #29 · Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 43
Percentile: 12.5%
Last updated: aging
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vals_multimodal_index; provider: SpaceXAI.

12.5% percentile inside its fair comparison set

43Raw benchmark valueCI 41 - 46

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #90 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 74.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: chinese. Source rank: #97. Votes: 4499. Organization: xai. License: Proprietary.

74.7% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,467 - 1,486

Text Arena · French

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #75 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 71.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: french. Source rank: #84. Votes: 2565. Organization: xai. License: Proprietary.

71.2% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,449 - 1,477

Text Arena · German

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #72 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 73.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: german. Source rank: #84. Votes: 1037. Organization: xai. License: Proprietary.

73.9% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,420 - 1,458

Text Arena · Japanese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #52 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,426
Percentile: 79%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: japanese. Source rank: #59. Votes: 849. Organization: xai. License: Proprietary.

79% percentile inside its fair comparison set

1,426Raw benchmark valueCI 1,404 - 1,448

Text Arena · Korean

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #61 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 75.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: korean. Source rank: #68. Votes: 1120. Organization: xai. License: Proprietary.

75.4% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,386 - 1,425

Text Arena · Non English

AR · Multilingual · Human

Observed user preference in Arena's Text Arena non_english leaderboard.

Rank #86 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 77.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: non_english. Source rank: #95. Votes: 38476. Organization: xai. License: Proprietary.

77.4% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,423 - 1,432

Text Arena · Polish

AR · Multilingual · Human

Observed user preference in Arena's Text Arena polish leaderboard.

Rank #61 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 69.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: polish. Source rank: #74. Votes: 1204. Organization: xai. License: Proprietary.

69.8% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,428 - 1,463

Text Arena · Russian

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #82 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 76.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: russian. Source rank: #91. Votes: 7498. Organization: xai. License: Proprietary.

76.2% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,432 - 1,447

Text Arena · Spanish

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #75 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 71.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: spanish. Source rank: #83. Votes: 1999. Organization: xai. License: Proprietary.

71.4% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,423 - 1,453

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #143 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 59.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: chinese. Source rank: #159. Votes: 4499. Organization: xai. License: Proprietary.

59.7% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,412 - 1,431

Text Arena · French · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #120 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 53.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: french. Source rank: #133. Votes: 2565. Organization: xai. License: Proprietary.

53.7% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,399 - 1,426

Text Arena · German · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #109 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,394
Percentile: 60.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: german. Source rank: #123. Votes: 1037. Organization: xai. License: Proprietary.

60.3% percentile inside its fair comparison set

1,394Raw benchmark valueCI 1,375 - 1,413

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #82 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,380
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: japanese. Source rank: #93. Votes: 849. Organization: xai. License: Proprietary.

66.7% percentile inside its fair comparison set

1,380Raw benchmark valueCI 1,357 - 1,402

Text Arena · Korean · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #111 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,356
Percentile: 54.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: korean. Source rank: #125. Votes: 1120. Organization: xai. License: Proprietary.

54.9% percentile inside its fair comparison set

1,356Raw benchmark valueCI 1,337 - 1,375

Text Arena · Non English · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena non_english leaderboard.

Rank #137 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 63.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: non_english. Source rank: #152. Votes: 38476. Organization: xai. License: Proprietary.

63.8% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,380 - 1,389

Text Arena · Polish · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena polish leaderboard.

Rank #105 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 47.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: polish. Source rank: #118. Votes: 1204. Organization: xai. License: Proprietary.

47.7% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,381 - 1,416

Text Arena · Russian · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #121 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 64.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: russian. Source rank: #135. Votes: 7498. Organization: xai. License: Proprietary.

64.8% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,391 - 1,406

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #130 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 50.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: spanish. Source rank: #144. Votes: 1999. Organization: xai. License: Proprietary.

50.2% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,383 - 1,413

Vision Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Vision Arena chinese leaderboard.

Rank #48 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,278
Percentile: 54.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: chinese. Source rank: #53. Votes: 1549. Organization: xai. License: Proprietary.

54.8% percentile inside its fair comparison set

1,278Raw benchmark valueCI 1,260 - 1,295

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Vision Arena chinese leaderboard.

Rank #59 · Source label: grok-4.3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,257
Percentile: 44.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `grok-4.3`. Category: chinese. Source rank: #68. Votes: 1549. Organization: xai. License: Proprietary.

44.2% percentile inside its fair comparison set

1,257Raw benchmark valueCI 1,239 - 1,274

Source links and registry checks

official

xAI models and pricing

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

official

LiveBench

Oct 3, 2026

source →

Grok 4.3

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

Grok 4.3

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks