Model profile · Google

Gemini 3.5 Flash

Closed weightsfrontier · registry tag 2026 current

Thin verified coverage

Reads as thin verified coverage across the resolved source data. Capability fit excludes speed and cost.

Visible coverage: 54.8%
Verified coverage: 54.8%
Spread: 90.8%
Last verified: Oct 3, 2026

59%capability fit

textcodevisiondocument11 aliases47 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.

Thin verified coverageThis model currently reads as thin verified coverage across the resolved source data.

Chat / text36 benchmarks80.7%

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 #129 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24
Percentile: 76.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

76.9% percentile inside its fair comparison set

24Raw 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 #73 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43%
Percentile: 84.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

84.1% percentile inside its fair comparison set

43%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 #186 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 25.7%
Percentile: 59.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

59.2% percentile inside its fair comparison set

25.7%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 #122 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.3%
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

65.2% percentile inside its fair comparison set

47.3%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 #254 · Source label: Gemini 3.5 Flash (Medium)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.5 /1M input tokens
Percentile: 28.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

28.5% percentile inside its fair comparison set

$1.5 /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 #270 · Source label: Gemini 3.5 Flash (Medium)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $9 /1M output tokens
Percentile: 24%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

24% percentile inside its fair comparison set

$9 /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 #29 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 197.9 tokens/s
Percentile: 89.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

89.3% percentile inside its fair comparison set

197.9 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 #202 · Source label: Gemini 3.5 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 16.19s
Percentile: 23.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

23.9% percentile inside its fair comparison set

16.19sRaw 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 #116 · Source label: Gemini 3.5 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 16.19s
Percentile: 56.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

56.1% percentile inside its fair comparison set

16.19sRaw 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 #28 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: overall. Source rank: #28. Votes: 48420. Organization: google. License: Proprietary.

92.8% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,473 - 1,481

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 #18 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 95.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: creative_writing. Source rank: #18. Votes: 9445. Organization: google. License: Proprietary.

95.5% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,461 - 1,476

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 #40 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 89.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: english. Source rank: #41. Votes: 20509. Organization: google. License: Proprietary.

89.6% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,473 - 1,484

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 #29 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: exclude_ties. Source rank: #29. Votes: 36505. Organization: google. License: Proprietary.

92.6% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,482 - 1,493

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 #41 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 89.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: hard_prompts. Source rank: #42. Votes: 32336. Organization: google. License: Proprietary.

89.4% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,490 - 1,500

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 #50 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 86.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: hard_prompts_english. Source rank: #51. Votes: 13297. Organization: google. License: Proprietary.

86.9% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,484 - 1,497

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 #40 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 89.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: instruction_following. Source rank: #41. Votes: 17011. Organization: google. License: Proprietary.

89.6% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,460 - 1,471

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 #39 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 89.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: longer_query. Source rank: #40. Votes: 22811. Organization: google. License: Proprietary.

89.3% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,476 - 1,487

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 #38 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 90.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: multi_turn. Source rank: #39. Votes: 8071. Organization: google. License: Proprietary.

90.1% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,473 - 1,488

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 #17 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: overall. Source rank: #17. Votes: 48420. Organization: google. License: Proprietary.

95.7% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,478 - 1,486

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 #16 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: creative_writing. Source rank: #16. Votes: 9445. Organization: google. License: Proprietary.

96% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,463 - 1,478

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 #22 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: english. Source rank: #22. Votes: 20509. Organization: google. License: Proprietary.

94.4% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,475 - 1,486

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 #18 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 95.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: exclude_ties. Source rank: #18. Votes: 36505. Organization: google. License: Proprietary.

95.5% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,485 - 1,496

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 #22 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: hard_prompts. Source rank: #22. Votes: 32336. Organization: google. License: Proprietary.

94.4% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,483 - 1,492

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 #31 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: hard_prompts_english. Source rank: #32. Votes: 13750. Organization: google. License: Proprietary.

92% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,476 - 1,488

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 #31 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: instruction_following. Source rank: #32. Votes: 17376. Organization: google. License: Proprietary.

92% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,461 - 1,472

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 #25 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 93.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: longer_query. Source rank: #25. Votes: 22811. Organization: google. License: Proprietary.

93.2% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,477 - 1,487

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 #23 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 94.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: multi_turn. Source rank: #23. Votes: 8071. Organization: google. License: Proprietary.

94.1% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,474 - 1,489

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 #7 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.6%
Percentile: 90.8%
Last updated: stale
Eligibility: headline eligible

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

90.8% percentile inside its fair comparison set

75.6%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 #16 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84.6%
Percentile: 76.9%
Last updated: stale
Eligibility: headline eligible

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

76.9% percentile inside its fair comparison set

84.6%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 #11 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.5%
Percentile: 84.6%
Last updated: stale
Eligibility: headline eligible

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

84.6% percentile inside its fair comparison set

75.5%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 #19 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 69.1%
Percentile: 72.3%
Last updated: stale
Eligibility: headline eligible

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

72.3% percentile inside its fair comparison set

69.1%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 #18 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.2%
Percentile: 73.8%
Last updated: stale
Eligibility: headline eligible

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

73.8% percentile inside its fair comparison set

75.2%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 #6 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.6%
Percentile: 92.3%
Last updated: stale
Eligibility: headline eligible

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

92.3% percentile inside its fair comparison set

82.6%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 #2 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 100%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

100%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 #20 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 67.8%
Percentile: 70.8%
Last updated: stale
Eligibility: headline eligible

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

70.8% percentile inside its fair comparison set

67.8%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 #8 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86%
Percentile: 89.2%
Last updated: stale
Eligibility: headline eligible

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

89.2% percentile inside its fair comparison set

86%Raw benchmark value

Coding22 benchmarks57%

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 #27 · Source label: Gemini 3.5 Flash (Medium)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 39.4%
Percentile: 92.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

92.2% percentile inside its fair comparison set

39.4%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 #56 · Source label: Gemini 3.5 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 53.9%
Percentile: 72.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

72.2% percentile inside its fair comparison set

53.9%Raw benchmark value

HiL-Bench

SL · Coding · Rubric

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

Rank #12 · Source label: Gemini 3.5 Flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 27.7%
Percentile: 31.3%
Last updated: recent
Eligibility: headline eligible

Parsed from the public Scale Labs page for scale-hil-bench. Reported model configuration: Gemini 3.5 Flash. Collapse policy: highest reported score per canonical model.

31.3% percentile inside its fair comparison set

27.7%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 #59 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,507
Percentile: 84.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: coding. Source rank: #63. Votes: 13817. Organization: google. License: Proprietary.

84.4% percentile inside its fair comparison set

1,507Raw benchmark valueCI 1,501 - 1,513

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 #32 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 91.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: coding. Source rank: #32. Votes: 13817. Organization: google. License: Proprietary.

91.6% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,486 - 1,498

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 #45 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 48.7%
Percentile: 52.7%
Last updated: recent
Eligibility: headline eligible

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

52.7% percentile inside its fair comparison set

48.7%Raw benchmark valueCI 39.4% - 57.9%

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 #53 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 59.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: overall. Source rank: #54. Votes: 9497. Organization: google. License: Proprietary.

59.1% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,492 - 1,506

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 #47 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,522
Percentile: 63.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: webdev-html. Source rank: #48. Votes: 1343. Organization: google. License: Proprietary.

63.2% percentile inside its fair comparison set

1,522Raw benchmark valueCI 1,505 - 1,539

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 #53 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 54%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: webdev-react. Source rank: #54. Votes: 6878. Organization: google. License: Proprietary.

54% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,486 - 1,503

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 #39 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 26.7%
Percentile: 44.1%
Last updated: recent
Eligibility: headline eligible

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

44.1% percentile inside its fair comparison set

26.7%Raw benchmark valueCI 18.7% - 34.8%

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 #42 · Source label: google/gemini-3.5-flash

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: Google.

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 #20 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74.2%
Percentile: 71.6%
Last updated: recent
Eligibility: headline eligible

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

71.6% percentile inside its fair comparison set

74.2%Raw benchmark valueCI 72% - 76.4%

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 #28 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 38.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: image_to_webdev. Source rank: #30. Votes: 2622. Organization: google. License: Proprietary.

38.6% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,488 - 1,512

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 #26 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 78.8%
Percentile: 69.5%
Last updated: recent
Eligibility: headline eligible

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

69.5% percentile inside its fair comparison set

78.8%Raw benchmark valueCI 75.2% - 82.4%

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 #12 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.6%
Percentile: 91.2%
Last updated: recent
Eligibility: headline eligible

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

91.2% percentile inside its fair comparison set

87.6%Raw benchmark valueCI 85.7% - 89.5%

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 #45 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 49%
Percentile: 33.8%
Last updated: stale
Eligibility: headline eligible

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

33.8% percentile inside its fair comparison set

49%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 #33 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.2%
Percentile: 52.3%
Last updated: stale
Eligibility: headline eligible

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

52.3% percentile inside its fair comparison set

78.2%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 #30 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 63.6%
Percentile: 58.5%
Last updated: stale
Eligibility: headline eligible

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

58.5% percentile inside its fair comparison set

63.6%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 #44 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 33.3%
Percentile: 35.4%
Last updated: stale
Eligibility: headline eligible

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

35.4% percentile inside its fair comparison set

33.3%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 #40 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 50%
Percentile: 46.2%
Last updated: stale
Eligibility: headline eligible

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

46.2% percentile inside its fair comparison set

50%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 #17 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.3%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

80.3%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 #41 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.1%
Percentile: 40%
Last updated: stale
Eligibility: headline eligible

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

40% percentile inside its fair comparison set

76.1%Raw benchmark value

Reasoning / math / science19 benchmarks55%

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 #126 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24.1%
Percentile: 76.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

76.4% percentile inside its fair comparison set

24.1%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 #109 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 82.8%
Percentile: 78.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

78.1% percentile inside its fair comparison set

82.8%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 #141 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1.4%
Percentile: 69.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

69.6% percentile inside its fair comparison set

1.4%Raw benchmark value

EnigmaEval

SL · Reasoning / math / science · Rubric

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

Rank #4 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 25.4%
Percentile: 25%
Last updated: recent
Eligibility: headline eligible

Parsed from the public Scale Labs page for scale-enigmaeval. Reported model configuration: gemini-3.5-flash-high. Collapse policy: highest reported score per canonical model.

25% percentile inside its fair comparison set

25.4%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 #19 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 95%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: math. Source rank: #19. Votes: 2361. Organization: google. License: Proprietary.

95% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,485 - 1,510

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 #12 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: math. Source rank: #12. Votes: 2361. Organization: google. License: Proprietary.

96.9% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,491 - 1,516

ProofBench

VALS-AI · Reasoning / math / science · Objective

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

Rank #30 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 31%
Percentile: 31%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: proof_bench; provider: Google.

31% percentile inside its fair comparison set

31%Raw benchmark valueCI 21.9% - 40.1%

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 #14 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 92.7%
Percentile: 89.5%
Last updated: recent
Eligibility: headline eligible

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

89.5% percentile inside its fair comparison set

92.7%Raw benchmark valueCI 89.8% - 95.5%

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 #10 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.5%
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

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

92.8% percentile inside its fair comparison set

89.5%Raw benchmark valueCI 88.9% - 90.1%

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #42 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 88.2%
Percentile: 36.9%
Last updated: stale
Eligibility: headline eligible

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

36.9% percentile inside its fair comparison set

88.2%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 #47 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82%
Percentile: 29.2%
Last updated: stale
Eligibility: headline eligible

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

29.2% percentile inside its fair comparison set

82%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 #17 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 83.1%
Last updated: stale
Eligibility: headline eligible

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

83.1% percentile inside its fair comparison set

98%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 #47 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68%
Percentile: 29.2%
Last updated: stale
Eligibility: headline eligible

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

29.2% percentile inside its fair comparison set

68%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 #37 · Source label: gemini-3.5-flash-high

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 #13 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 91.9%
Percentile: 81.5%
Last updated: stale
Eligibility: headline eligible

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

81.5% percentile inside its fair comparison set

91.9%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 #27 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.8%
Percentile: 66.2%
Last updated: stale
Eligibility: headline eligible

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

66.2% percentile inside its fair comparison set

80.8%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 #54 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 77.3%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

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

18.5% percentile inside its fair comparison set

77.3%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 #41 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96%
Percentile: 41.5%
Last updated: stale
Eligibility: headline eligible

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

41.5% percentile inside its fair comparison set

96%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 #28 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74%
Percentile: 58.5%
Last updated: stale
Eligibility: headline eligible

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

58.5% percentile inside its fair comparison set

74%Raw benchmark value

Professional reasoning36 benchmarks53.7%

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #1 · Source label: Gemini 3.5 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.1%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

100% percentile inside its fair comparison set

47.1%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #54 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 83.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: expert. Source rank: #55. Votes: 5554. Organization: google. License: Proprietary.

83.8% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,484 - 1,501

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 #39 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 89.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: industry_business_and_management_and_financial_operations. Source rank: #41. Votes: 9392. Organization: google. License: Proprietary.

89.7% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,461 - 1,475

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 #24 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 93.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: industry_entertainment_and_sports_and_media. Source rank: #24. Votes: 12051. Organization: google. License: Proprietary.

93.9% percentile inside its fair comparison set

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

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #30 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 91.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: industry_legal_and_government. Source rank: #31. Votes: 3837. Organization: google. License: Proprietary.

91.7% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,474 - 1,494

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 #27 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 93%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: industry_life_and_physical_and_social_science. Source rank: #28. Votes: 7797. Organization: google. License: Proprietary.

93% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,489 - 1,504

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #33 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 91%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: industry_mathematical. Source rank: #34. Votes: 2681. Organization: google. License: Proprietary.

91% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,476 - 1,501

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #38 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 89.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: industry_medicine_and_healthcare. Source rank: #38. Votes: 3438. Organization: google. License: Proprietary.

89.3% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,476 - 1,498

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 #52 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,501
Percentile: 86.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: industry_software_and_it_services. Source rank: #55. Votes: 19374. Organization: google. License: Proprietary.

86.4% percentile inside its fair comparison set

1,501Raw benchmark valueCI 1,496 - 1,507

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 #18 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 95.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: industry_writing_and_literature_and_language. Source rank: #18. Votes: 12663. Organization: google. License: Proprietary.

95.5% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,467 - 1,480

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #30 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 91.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: expert. Source rank: #31. Votes: 5554. Organization: google. License: Proprietary.

91.1% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,486 - 1,503

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 #22 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 94.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: industry_business_and_management_and_financial_operations. Source rank: #23. Votes: 9392. Organization: google. License: Proprietary.

94.3% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,461 - 1,474

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 #17 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,459
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: industry_entertainment_and_sports_and_media. Source rank: #17. Votes: 12051. Organization: google. License: Proprietary.

95.7% percentile inside its fair comparison set

1,459Raw benchmark valueCI 1,452 - 1,466

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 #20 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 94.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: industry_legal_and_government. Source rank: #20. Votes: 3837. Organization: google. License: Proprietary.

94.6% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,477 - 1,498

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 #21 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 94.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: industry_life_and_physical_and_social_science. Source rank: #21. Votes: 8006. Organization: google. License: Proprietary.

94.7% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,488 - 1,502

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #22 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,493
Percentile: 94.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: industry_mathematical. Source rank: #22. Votes: 2681. Organization: google. License: Proprietary.

94.1% percentile inside its fair comparison set

1,493Raw benchmark valueCI 1,481 - 1,505

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 #21 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 94.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: industry_medicine_and_healthcare. Source rank: #21. Votes: 3559. Organization: google. License: Proprietary.

94.2% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,472 - 1,493

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 #25 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 93.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: industry_software_and_it_services. Source rank: #25. Votes: 19374. Organization: google. License: Proprietary.

93.6% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,488 - 1,499

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 #15 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: industry_writing_and_literature_and_language. Source rank: #15. Votes: 12663. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,471 - 1,484

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #32 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 45
Percentile: 22.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vals_index; provider: Google.

22.5% percentile inside its fair comparison set

45Raw benchmark valueCI 43 - 47

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #37 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 30.8%
Percentile: 47.1%
Last updated: recent
Eligibility: headline eligible

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

47.1% percentile inside its fair comparison set

30.8%Raw benchmark valueCI 24.5% - 37.1%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #39 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 2.5%
Percentile: 44.9%
Last updated: recent
Eligibility: headline eligible

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

44.9% percentile inside its fair comparison set

2.5%Raw benchmark valueCI 0.9% - 4.1%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #51 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.6%
Percentile: 63%
Last updated: recent
Eligibility: headline eligible

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

63% percentile inside its fair comparison set

83.6%Raw benchmark valueCI 81.9% - 85.3%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #10 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 57.9%
Percentile: 87%
Last updated: recent
Eligibility: headline eligible

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

87% percentile inside its fair comparison set

57.9%Raw benchmark valueCI 57.4% - 58.3%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #6 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 55.8%
Percentile: 94.7%
Last updated: recent
Eligibility: headline eligible

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

94.7% percentile inside its fair comparison set

55.8%Raw benchmark valueCI 51.7% - 60%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #67 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 76.6%
Percentile: 31.3%
Last updated: recent
Eligibility: headline eligible

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

31.3% percentile inside its fair comparison set

76.6%Raw benchmark valueCI 72.8% - 80.3%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #18 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 49.9%
Percentile: 79%
Last updated: recent
Eligibility: headline eligible

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

79% percentile inside its fair comparison set

49.9%Raw benchmark valueCI 43.1% - 56.6%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #29 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 59.5%
Percentile: 37.8%
Last updated: recent
Eligibility: headline eligible

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

37.8% percentile inside its fair comparison set

59.5%Raw benchmark valueCI 57% - 62%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #17 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 52.7%
Percentile: 51.5%
Last updated: recent
Eligibility: headline eligible

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

51.5% percentile inside its fair comparison set

52.7%Raw benchmark valueCI 44% - 61.5%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #37 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74.4%
Percentile: 72.1%
Last updated: recent
Eligibility: headline eligible

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

72.1% percentile inside its fair comparison set

74.4%Raw benchmark valueCI 72.7% - 76%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #59 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64.9%
Percentile: 10.8%
Last updated: stale
Eligibility: headline eligible

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

10.8% percentile inside its fair comparison set

64.9%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #39 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74.6%
Percentile: 41.5%
Last updated: stale
Eligibility: headline eligible

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

41.5% percentile inside its fair comparison set

74.6%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #60 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 48%
Percentile: 9.2%
Last updated: stale
Eligibility: headline eligible

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

9.2% percentile inside its fair comparison set

48%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #19 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 50.5%
Percentile: 72.3%
Last updated: stale
Eligibility: headline eligible

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

72.3% percentile inside its fair comparison set

50.5%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #54 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.1%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

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

20% percentile inside its fair comparison set

96.1%Raw benchmark value

Public Benefits Bench v1

VALS-AI · Professional reasoning · Objective

Answering public-benefits questions across the benefits lifecycle.

Rank #5 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 58%
Percentile: 66.7%
Last updated: stale
Eligibility: headline eligible

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

66.7% percentile inside its fair comparison set

58%Raw benchmark valueCI 55.5% - 60.5%

Search / tool use1 benchmark62.8%

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 #127 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 58.8%
Percentile: 62.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

62.8% percentile inside its fair comparison set

58.8%Raw benchmark value

Long context2 benchmarks64.3%

Long Context Reasoning

AA · Long context · Objective

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

Rank #191 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61.3%
Percentile: 58.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

58.5% percentile inside its fair comparison set

61.3%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 #36 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 64.7%
Percentile: 70.1%
Last updated: aging
Eligibility: headline eligible

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

70.1% percentile inside its fair comparison set

64.7%Raw benchmark valueCI 62.8% - 66.5%

Vision understanding16 benchmarks86.5%

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 #41 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 80.1%
Percentile: 80.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

80.8% percentile inside its fair comparison set

80.1%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 #19 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,284
Percentile: 87.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: overall. Source rank: #19. Votes: 12467. Organization: google. License: Proprietary.

87.1% percentile inside its fair comparison set

1,284Raw benchmark valueCI 1,277 - 1,291

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 #14 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,287
Percentile: 84.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: creative_writing_vision. Source rank: #14. Votes: 982. Organization: google. License: Proprietary.

84.1% percentile inside its fair comparison set

1,287Raw benchmark valueCI 1,267 - 1,307

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 #17 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,315
Percentile: 83.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: diagram. Source rank: #17. Votes: 3210. Organization: google. License: Proprietary.

83.8% percentile inside its fair comparison set

1,315Raw benchmark valueCI 1,304 - 1,326

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 #22 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,278
Percentile: 84.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: english. Source rank: #23. Votes: 4488. Organization: google. License: Proprietary.

84.8% percentile inside its fair comparison set

1,278Raw benchmark valueCI 1,268 - 1,289

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 #19 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,317
Percentile: 81.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: homework. Source rank: #20. Votes: 1296. Organization: google. License: Proprietary.

81.3% percentile inside its fair comparison set

1,317Raw benchmark valueCI 1,300 - 1,334

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 #5 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,296
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: humor. Source rank: #5. Votes: 487. Organization: google. License: Proprietary.

94.5% percentile inside its fair comparison set

1,296Raw benchmark valueCI 1,268 - 1,324

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 #18 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,299
Percentile: 83%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: ocr. Source rank: #18. Votes: 8599. Organization: google. License: Proprietary.

83% percentile inside its fair comparison set

1,299Raw benchmark valueCI 1,291 - 1,306

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 #12 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,310
Percentile: 92.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: overall. Source rank: #12. Votes: 12336. Organization: google. License: Proprietary.

92.1% percentile inside its fair comparison set

1,310Raw benchmark valueCI 1,303 - 1,317

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 #13 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,310
Percentile: 85.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: creative_writing_vision. Source rank: #13. Votes: 982. Organization: google. License: Proprietary.

85.4% percentile inside its fair comparison set

1,310Raw benchmark valueCI 1,290 - 1,330

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 #13 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,326
Percentile: 87.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: diagram. Source rank: #13. Votes: 3210. Organization: google. License: Proprietary.

87.9% percentile inside its fair comparison set

1,326Raw benchmark valueCI 1,314 - 1,337

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 #10 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,305
Percentile: 93.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: english. Source rank: #10. Votes: 4488. Organization: google. License: Proprietary.

93.5% percentile inside its fair comparison set

1,305Raw benchmark valueCI 1,294 - 1,315

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 #15 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,331
Percentile: 85.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: homework. Source rank: #16. Votes: 1296. Organization: google. License: Proprietary.

85.4% percentile inside its fair comparison set

1,331Raw benchmark valueCI 1,314 - 1,347

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 #4 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,324
Percentile: 95.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: humor. Source rank: #4. Votes: 487. Organization: google. License: Proprietary.

95.9% percentile inside its fair comparison set

1,324Raw benchmark valueCI 1,296 - 1,352

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 #12 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,316
Percentile: 89%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: ocr. Source rank: #12. Votes: 8599. Organization: google. License: Proprietary.

89% percentile inside its fair comparison set

1,316Raw benchmark valueCI 1,309 - 1,324

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 #8 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.3%
Percentile: 91.6%
Last updated: recent
Eligibility: headline eligible

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

91.6% percentile inside its fair comparison set

88.3%Raw benchmark valueCI 86.7% - 89.8%

Document understanding4 benchmarks58.2%

Document Arena

AR · Document understanding · Human

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

Rank #24 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,461
Percentile: 42.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: overall. Source rank: #25. Votes: 6500. Organization: google. License: Proprietary.

42.5% percentile inside its fair comparison set

1,461Raw benchmark valueCI 1,453 - 1,468

Document Arena · No Style Control

AR · Document understanding · Human

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

Rank #19 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 55%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: overall. Source rank: #20. Votes: 6500. Organization: google. License: Proprietary.

55% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,455 - 1,471

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 #19 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.1%
Percentile: 79.1%
Last updated: recent
Eligibility: headline eligible

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

79.1% percentile inside its fair comparison set

68.1%Raw benchmark valueCI 66.3% - 69.9%

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 #16 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 63
Percentile: 53.1%
Last updated: aging
Eligibility: headline eligible

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

53.1% percentile inside its fair comparison set

63Raw benchmark valueCI 60 - 66

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #32 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 91.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: chinese. Source rank: #32. Votes: 3451. Organization: google. License: Proprietary.

91.2% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,507 - 1,528

Text Arena · French

AR · Multilingual · Human

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

Rank #32 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 87.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: french. Source rank: #35. Votes: 1511. Organization: google. License: Proprietary.

87.9% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,475 - 1,509

Text Arena · German

AR · Multilingual · Human

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

Rank #14 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 95.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: german. Source rank: #14. Votes: 741. Organization: google. License: Proprietary.

95.2% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,469 - 1,514

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #18 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 93%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: japanese. Source rank: #18. Votes: 672. Organization: google. License: Proprietary.

93% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,454 - 1,504

Text Arena · Korean

AR · Multilingual · Human

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

Rank #29 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 88.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: korean. Source rank: #29. Votes: 855. Organization: google. License: Proprietary.

88.5% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,422 - 1,465

Text Arena · Non English

AR · Multilingual · Human

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

Rank #28 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: non_english. Source rank: #28. Votes: 27909. Organization: google. License: Proprietary.

92.8% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,464 - 1,474

Text Arena · Polish

AR · Multilingual · Human

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

Rank #2 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,511
Percentile: 99.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: polish. Source rank: #2. Votes: 773. Organization: google. License: Proprietary.

99.5% percentile inside its fair comparison set

1,511Raw benchmark valueCI 1,489 - 1,533

Text Arena · Russian

AR · Multilingual · Human

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

Rank #22 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 93.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: russian. Source rank: #22. Votes: 5398. Organization: google. License: Proprietary.

93.8% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,482 - 1,500

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #27 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,471
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: spanish. Source rank: #27. Votes: 1410. Organization: google. License: Proprietary.

90% percentile inside its fair comparison set

1,471Raw benchmark valueCI 1,455 - 1,488

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #24 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,526
Percentile: 93.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: chinese. Source rank: #24. Votes: 3640. Organization: google. License: Proprietary.

93.5% percentile inside its fair comparison set

1,526Raw benchmark valueCI 1,516 - 1,537

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #22 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 91.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: french. Source rank: #22. Votes: 1511. Organization: google. License: Proprietary.

91.8% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,472 - 1,505

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #11 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: german. Source rank: #11. Votes: 741. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,471 - 1,517

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #14 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,486
Percentile: 94.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: japanese. Source rank: #14. Votes: 672. Organization: google. License: Proprietary.

94.7% percentile inside its fair comparison set

1,486Raw benchmark valueCI 1,461 - 1,511

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #18 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 93%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: korean. Source rank: #18. Votes: 855. Organization: google. License: Proprietary.

93% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,431 - 1,473

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #15 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: non_english. Source rank: #15. Votes: 27909. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,471 - 1,480

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #2 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,521
Percentile: 99.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: polish. Source rank: #2. Votes: 773. Organization: google. License: Proprietary.

99.5% percentile inside its fair comparison set

1,521Raw benchmark valueCI 1,499 - 1,543

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #15 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 95.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: russian. Source rank: #15. Votes: 5467. Organization: google. License: Proprietary.

95.9% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,484 - 1,501

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #13 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: spanish. Source rank: #13. Votes: 1410. Organization: google. License: Proprietary.

95.4% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,462 - 1,496

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #7 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,349
Percentile: 94.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: chinese. Source rank: #7. Votes: 781. Organization: google. License: Proprietary.

94.2% percentile inside its fair comparison set

1,349Raw benchmark valueCI 1,326 - 1,373

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #3 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: chinese. Source rank: #3. Votes: 781. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,356 - 1,402

Source links and registry checks

official

Vals AI

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 →

official

Scale Labs

Oct 3, 2026

source →

official

Scale Labs

Oct 3, 2026

source →

Model profile · Google

Gemini 3.5 Flash

Closed weightsfrontier · registry tag 2026 current

Thin verified coverage

Reads as thin verified coverage across the resolved source data. Capability fit excludes speed and cost.

Visible coverage: 54.8%
Verified coverage: 54.8%
Spread: 90.8%
Last verified: Oct 3, 2026

59%capability fit

textcodevisiondocument11 aliases47 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

Thin verified coverageThis model currently reads as thin verified coverage across the resolved source data.

Chat / text36 benchmarks80.7%

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 #129 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24
Percentile: 76.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

76.9% percentile inside its fair comparison set

24Raw 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 #73 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43%
Percentile: 84.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

84.1% percentile inside its fair comparison set

43%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 #186 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 25.7%
Percentile: 59.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

59.2% percentile inside its fair comparison set

25.7%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 #122 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.3%
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

65.2% percentile inside its fair comparison set

47.3%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 #254 · Source label: Gemini 3.5 Flash (Medium)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.5 /1M input tokens
Percentile: 28.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

28.5% percentile inside its fair comparison set

$1.5 /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 #270 · Source label: Gemini 3.5 Flash (Medium)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $9 /1M output tokens
Percentile: 24%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

24% percentile inside its fair comparison set

$9 /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 #29 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 197.9 tokens/s
Percentile: 89.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

89.3% percentile inside its fair comparison set

197.9 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 #202 · Source label: Gemini 3.5 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 16.19s
Percentile: 23.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

23.9% percentile inside its fair comparison set

16.19sRaw 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 #116 · Source label: Gemini 3.5 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 16.19s
Percentile: 56.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

56.1% percentile inside its fair comparison set

16.19sRaw 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 #28 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: overall. Source rank: #28. Votes: 48420. Organization: google. License: Proprietary.

92.8% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,473 - 1,481

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 #18 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 95.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: creative_writing. Source rank: #18. Votes: 9445. Organization: google. License: Proprietary.

95.5% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,461 - 1,476

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 #40 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 89.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: english. Source rank: #41. Votes: 20509. Organization: google. License: Proprietary.

89.6% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,473 - 1,484

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 #29 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: exclude_ties. Source rank: #29. Votes: 36505. Organization: google. License: Proprietary.

92.6% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,482 - 1,493

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 #41 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 89.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: hard_prompts. Source rank: #42. Votes: 32336. Organization: google. License: Proprietary.

89.4% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,490 - 1,500

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 #50 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 86.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: hard_prompts_english. Source rank: #51. Votes: 13297. Organization: google. License: Proprietary.

86.9% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,484 - 1,497

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 #40 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 89.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: instruction_following. Source rank: #41. Votes: 17011. Organization: google. License: Proprietary.

89.6% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,460 - 1,471

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 #39 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 89.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: longer_query. Source rank: #40. Votes: 22811. Organization: google. License: Proprietary.

89.3% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,476 - 1,487

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 #38 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 90.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: multi_turn. Source rank: #39. Votes: 8071. Organization: google. License: Proprietary.

90.1% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,473 - 1,488

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 #17 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: overall. Source rank: #17. Votes: 48420. Organization: google. License: Proprietary.

95.7% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,478 - 1,486

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 #16 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: creative_writing. Source rank: #16. Votes: 9445. Organization: google. License: Proprietary.

96% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,463 - 1,478

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 #22 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: english. Source rank: #22. Votes: 20509. Organization: google. License: Proprietary.

94.4% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,475 - 1,486

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 #18 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 95.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: exclude_ties. Source rank: #18. Votes: 36505. Organization: google. License: Proprietary.

95.5% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,485 - 1,496

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 #22 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: hard_prompts. Source rank: #22. Votes: 32336. Organization: google. License: Proprietary.

94.4% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,483 - 1,492

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 #31 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: hard_prompts_english. Source rank: #32. Votes: 13750. Organization: google. License: Proprietary.

92% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,476 - 1,488

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 #31 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: instruction_following. Source rank: #32. Votes: 17376. Organization: google. License: Proprietary.

92% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,461 - 1,472

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 #25 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 93.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: longer_query. Source rank: #25. Votes: 22811. Organization: google. License: Proprietary.

93.2% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,477 - 1,487

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 #23 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 94.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: multi_turn. Source rank: #23. Votes: 8071. Organization: google. License: Proprietary.

94.1% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,474 - 1,489

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 #7 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.6%
Percentile: 90.8%
Last updated: stale
Eligibility: headline eligible

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

90.8% percentile inside its fair comparison set

75.6%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 #16 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84.6%
Percentile: 76.9%
Last updated: stale
Eligibility: headline eligible

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

76.9% percentile inside its fair comparison set

84.6%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 #11 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.5%
Percentile: 84.6%
Last updated: stale
Eligibility: headline eligible

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

84.6% percentile inside its fair comparison set

75.5%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 #19 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 69.1%
Percentile: 72.3%
Last updated: stale
Eligibility: headline eligible

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

72.3% percentile inside its fair comparison set

69.1%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 #18 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.2%
Percentile: 73.8%
Last updated: stale
Eligibility: headline eligible

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

73.8% percentile inside its fair comparison set

75.2%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 #6 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.6%
Percentile: 92.3%
Last updated: stale
Eligibility: headline eligible

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

92.3% percentile inside its fair comparison set

82.6%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 #2 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 100%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

100%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 #20 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 67.8%
Percentile: 70.8%
Last updated: stale
Eligibility: headline eligible

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

70.8% percentile inside its fair comparison set

67.8%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 #8 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86%
Percentile: 89.2%
Last updated: stale
Eligibility: headline eligible

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

89.2% percentile inside its fair comparison set

86%Raw benchmark value

Coding22 benchmarks57%

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 #27 · Source label: Gemini 3.5 Flash (Medium)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 39.4%
Percentile: 92.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

92.2% percentile inside its fair comparison set

39.4%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 #56 · Source label: Gemini 3.5 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 53.9%
Percentile: 72.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

72.2% percentile inside its fair comparison set

53.9%Raw benchmark value

HiL-Bench

SL · Coding · Rubric

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

Rank #12 · Source label: Gemini 3.5 Flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 27.7%
Percentile: 31.3%
Last updated: recent
Eligibility: headline eligible

Parsed from the public Scale Labs page for scale-hil-bench. Reported model configuration: Gemini 3.5 Flash. Collapse policy: highest reported score per canonical model.

31.3% percentile inside its fair comparison set

27.7%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 #59 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,507
Percentile: 84.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: coding. Source rank: #63. Votes: 13817. Organization: google. License: Proprietary.

84.4% percentile inside its fair comparison set

1,507Raw benchmark valueCI 1,501 - 1,513

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 #32 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 91.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: coding. Source rank: #32. Votes: 13817. Organization: google. License: Proprietary.

91.6% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,486 - 1,498

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 #45 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 48.7%
Percentile: 52.7%
Last updated: recent
Eligibility: headline eligible

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

52.7% percentile inside its fair comparison set

48.7%Raw benchmark valueCI 39.4% - 57.9%

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 #53 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 59.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: overall. Source rank: #54. Votes: 9497. Organization: google. License: Proprietary.

59.1% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,492 - 1,506

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 #47 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,522
Percentile: 63.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: webdev-html. Source rank: #48. Votes: 1343. Organization: google. License: Proprietary.

63.2% percentile inside its fair comparison set

1,522Raw benchmark valueCI 1,505 - 1,539

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 #53 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 54%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: webdev-react. Source rank: #54. Votes: 6878. Organization: google. License: Proprietary.

54% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,486 - 1,503

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 #39 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 26.7%
Percentile: 44.1%
Last updated: recent
Eligibility: headline eligible

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

44.1% percentile inside its fair comparison set

26.7%Raw benchmark valueCI 18.7% - 34.8%

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 #42 · Source label: google/gemini-3.5-flash

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: Google.

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 #20 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74.2%
Percentile: 71.6%
Last updated: recent
Eligibility: headline eligible

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

71.6% percentile inside its fair comparison set

74.2%Raw benchmark valueCI 72% - 76.4%

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 #28 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 38.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: image_to_webdev. Source rank: #30. Votes: 2622. Organization: google. License: Proprietary.

38.6% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,488 - 1,512

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 #26 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 78.8%
Percentile: 69.5%
Last updated: recent
Eligibility: headline eligible

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

69.5% percentile inside its fair comparison set

78.8%Raw benchmark valueCI 75.2% - 82.4%

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 #12 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.6%
Percentile: 91.2%
Last updated: recent
Eligibility: headline eligible

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

91.2% percentile inside its fair comparison set

87.6%Raw benchmark valueCI 85.7% - 89.5%

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 #45 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 49%
Percentile: 33.8%
Last updated: stale
Eligibility: headline eligible

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

33.8% percentile inside its fair comparison set

49%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 #33 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.2%
Percentile: 52.3%
Last updated: stale
Eligibility: headline eligible

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

52.3% percentile inside its fair comparison set

78.2%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 #30 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 63.6%
Percentile: 58.5%
Last updated: stale
Eligibility: headline eligible

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

58.5% percentile inside its fair comparison set

63.6%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 #44 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 33.3%
Percentile: 35.4%
Last updated: stale
Eligibility: headline eligible

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

35.4% percentile inside its fair comparison set

33.3%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 #40 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 50%
Percentile: 46.2%
Last updated: stale
Eligibility: headline eligible

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

46.2% percentile inside its fair comparison set

50%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 #17 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.3%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

80.3%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 #41 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.1%
Percentile: 40%
Last updated: stale
Eligibility: headline eligible

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

40% percentile inside its fair comparison set

76.1%Raw benchmark value

Reasoning / math / science19 benchmarks55%

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 #126 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24.1%
Percentile: 76.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

76.4% percentile inside its fair comparison set

24.1%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 #109 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 82.8%
Percentile: 78.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

78.1% percentile inside its fair comparison set

82.8%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 #141 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1.4%
Percentile: 69.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

69.6% percentile inside its fair comparison set

1.4%Raw benchmark value

EnigmaEval

SL · Reasoning / math / science · Rubric

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

Rank #4 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 25.4%
Percentile: 25%
Last updated: recent
Eligibility: headline eligible

Parsed from the public Scale Labs page for scale-enigmaeval. Reported model configuration: gemini-3.5-flash-high. Collapse policy: highest reported score per canonical model.

25% percentile inside its fair comparison set

25.4%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 #19 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 95%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: math. Source rank: #19. Votes: 2361. Organization: google. License: Proprietary.

95% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,485 - 1,510

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 #12 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: math. Source rank: #12. Votes: 2361. Organization: google. License: Proprietary.

96.9% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,491 - 1,516

ProofBench

VALS-AI · Reasoning / math / science · Objective

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

Rank #30 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 31%
Percentile: 31%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: proof_bench; provider: Google.

31% percentile inside its fair comparison set

31%Raw benchmark valueCI 21.9% - 40.1%

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 #14 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 92.7%
Percentile: 89.5%
Last updated: recent
Eligibility: headline eligible

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

89.5% percentile inside its fair comparison set

92.7%Raw benchmark valueCI 89.8% - 95.5%

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 #10 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.5%
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

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

92.8% percentile inside its fair comparison set

89.5%Raw benchmark valueCI 88.9% - 90.1%

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #42 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 88.2%
Percentile: 36.9%
Last updated: stale
Eligibility: headline eligible

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

36.9% percentile inside its fair comparison set

88.2%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 #47 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82%
Percentile: 29.2%
Last updated: stale
Eligibility: headline eligible

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

29.2% percentile inside its fair comparison set

82%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 #17 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 83.1%
Last updated: stale
Eligibility: headline eligible

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

83.1% percentile inside its fair comparison set

98%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 #47 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68%
Percentile: 29.2%
Last updated: stale
Eligibility: headline eligible

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

29.2% percentile inside its fair comparison set

68%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 #37 · Source label: gemini-3.5-flash-high

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 #13 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 91.9%
Percentile: 81.5%
Last updated: stale
Eligibility: headline eligible

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

81.5% percentile inside its fair comparison set

91.9%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 #27 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.8%
Percentile: 66.2%
Last updated: stale
Eligibility: headline eligible

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

66.2% percentile inside its fair comparison set

80.8%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 #54 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 77.3%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

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

18.5% percentile inside its fair comparison set

77.3%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 #41 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96%
Percentile: 41.5%
Last updated: stale
Eligibility: headline eligible

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

41.5% percentile inside its fair comparison set

96%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 #28 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74%
Percentile: 58.5%
Last updated: stale
Eligibility: headline eligible

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

58.5% percentile inside its fair comparison set

74%Raw benchmark value

Professional reasoning36 benchmarks53.7%

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #1 · Source label: Gemini 3.5 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.1%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

100% percentile inside its fair comparison set

47.1%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #54 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 83.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: expert. Source rank: #55. Votes: 5554. Organization: google. License: Proprietary.

83.8% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,484 - 1,501

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 #39 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 89.7%
Last updated: recent
Eligibility: headline eligible

89.7% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,461 - 1,475

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 #24 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 93.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: industry_entertainment_and_sports_and_media. Source rank: #24. Votes: 12051. Organization: google. License: Proprietary.

93.9% percentile inside its fair comparison set

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

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #30 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 91.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: industry_legal_and_government. Source rank: #31. Votes: 3837. Organization: google. License: Proprietary.

91.7% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,474 - 1,494

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 #27 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 93%
Last updated: recent
Eligibility: headline eligible

93% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,489 - 1,504

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #33 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 91%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: industry_mathematical. Source rank: #34. Votes: 2681. Organization: google. License: Proprietary.

91% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,476 - 1,501

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #38 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 89.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: industry_medicine_and_healthcare. Source rank: #38. Votes: 3438. Organization: google. License: Proprietary.

89.3% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,476 - 1,498

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 #52 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,501
Percentile: 86.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: industry_software_and_it_services. Source rank: #55. Votes: 19374. Organization: google. License: Proprietary.

86.4% percentile inside its fair comparison set

1,501Raw benchmark valueCI 1,496 - 1,507

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 #18 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 95.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: industry_writing_and_literature_and_language. Source rank: #18. Votes: 12663. Organization: google. License: Proprietary.

95.5% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,467 - 1,480

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #30 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 91.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: expert. Source rank: #31. Votes: 5554. Organization: google. License: Proprietary.

91.1% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,486 - 1,503

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 #22 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 94.3%
Last updated: recent
Eligibility: headline eligible

94.3% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,461 - 1,474

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 #17 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,459
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: industry_entertainment_and_sports_and_media. Source rank: #17. Votes: 12051. Organization: google. License: Proprietary.

95.7% percentile inside its fair comparison set

1,459Raw benchmark valueCI 1,452 - 1,466

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 #20 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 94.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: industry_legal_and_government. Source rank: #20. Votes: 3837. Organization: google. License: Proprietary.

94.6% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,477 - 1,498

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 #21 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 94.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: industry_life_and_physical_and_social_science. Source rank: #21. Votes: 8006. Organization: google. License: Proprietary.

94.7% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,488 - 1,502

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #22 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,493
Percentile: 94.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: industry_mathematical. Source rank: #22. Votes: 2681. Organization: google. License: Proprietary.

94.1% percentile inside its fair comparison set

1,493Raw benchmark valueCI 1,481 - 1,505

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 #21 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 94.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: industry_medicine_and_healthcare. Source rank: #21. Votes: 3559. Organization: google. License: Proprietary.

94.2% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,472 - 1,493

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 #25 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 93.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: industry_software_and_it_services. Source rank: #25. Votes: 19374. Organization: google. License: Proprietary.

93.6% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,488 - 1,499

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 #15 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: industry_writing_and_literature_and_language. Source rank: #15. Votes: 12663. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,471 - 1,484

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #32 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 45
Percentile: 22.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vals_index; provider: Google.

22.5% percentile inside its fair comparison set

45Raw benchmark valueCI 43 - 47

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #37 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 30.8%
Percentile: 47.1%
Last updated: recent
Eligibility: headline eligible

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

47.1% percentile inside its fair comparison set

30.8%Raw benchmark valueCI 24.5% - 37.1%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #39 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 2.5%
Percentile: 44.9%
Last updated: recent
Eligibility: headline eligible

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

44.9% percentile inside its fair comparison set

2.5%Raw benchmark valueCI 0.9% - 4.1%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #51 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.6%
Percentile: 63%
Last updated: recent
Eligibility: headline eligible

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

63% percentile inside its fair comparison set

83.6%Raw benchmark valueCI 81.9% - 85.3%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #10 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 57.9%
Percentile: 87%
Last updated: recent
Eligibility: headline eligible

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

87% percentile inside its fair comparison set

57.9%Raw benchmark valueCI 57.4% - 58.3%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #6 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 55.8%
Percentile: 94.7%
Last updated: recent
Eligibility: headline eligible

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

94.7% percentile inside its fair comparison set

55.8%Raw benchmark valueCI 51.7% - 60%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #67 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 76.6%
Percentile: 31.3%
Last updated: recent
Eligibility: headline eligible

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

31.3% percentile inside its fair comparison set

76.6%Raw benchmark valueCI 72.8% - 80.3%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #18 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 49.9%
Percentile: 79%
Last updated: recent
Eligibility: headline eligible

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

79% percentile inside its fair comparison set

49.9%Raw benchmark valueCI 43.1% - 56.6%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #29 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 59.5%
Percentile: 37.8%
Last updated: recent
Eligibility: headline eligible

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

37.8% percentile inside its fair comparison set

59.5%Raw benchmark valueCI 57% - 62%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #17 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 52.7%
Percentile: 51.5%
Last updated: recent
Eligibility: headline eligible

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

51.5% percentile inside its fair comparison set

52.7%Raw benchmark valueCI 44% - 61.5%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #37 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74.4%
Percentile: 72.1%
Last updated: recent
Eligibility: headline eligible

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

72.1% percentile inside its fair comparison set

74.4%Raw benchmark valueCI 72.7% - 76%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #59 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64.9%
Percentile: 10.8%
Last updated: stale
Eligibility: headline eligible

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

10.8% percentile inside its fair comparison set

64.9%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #39 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74.6%
Percentile: 41.5%
Last updated: stale
Eligibility: headline eligible

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

41.5% percentile inside its fair comparison set

74.6%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #60 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 48%
Percentile: 9.2%
Last updated: stale
Eligibility: headline eligible

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

9.2% percentile inside its fair comparison set

48%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #19 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 50.5%
Percentile: 72.3%
Last updated: stale
Eligibility: headline eligible

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

72.3% percentile inside its fair comparison set

50.5%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #54 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.1%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

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

20% percentile inside its fair comparison set

96.1%Raw benchmark value

Public Benefits Bench v1

VALS-AI · Professional reasoning · Objective

Answering public-benefits questions across the benefits lifecycle.

Rank #5 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 58%
Percentile: 66.7%
Last updated: stale
Eligibility: headline eligible

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

66.7% percentile inside its fair comparison set

58%Raw benchmark valueCI 55.5% - 60.5%

Search / tool use1 benchmark62.8%

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 #127 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 58.8%
Percentile: 62.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

62.8% percentile inside its fair comparison set

58.8%Raw benchmark value

Long context2 benchmarks64.3%

Long Context Reasoning

AA · Long context · Objective

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

Rank #191 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61.3%
Percentile: 58.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

58.5% percentile inside its fair comparison set

61.3%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 #36 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 64.7%
Percentile: 70.1%
Last updated: aging
Eligibility: headline eligible

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

70.1% percentile inside its fair comparison set

64.7%Raw benchmark valueCI 62.8% - 66.5%

Vision understanding16 benchmarks86.5%

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 #41 · Source label: Gemini 3.5 Flash (Minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 80.1%
Percentile: 80.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

80.8% percentile inside its fair comparison set

80.1%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 #19 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,284
Percentile: 87.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: overall. Source rank: #19. Votes: 12467. Organization: google. License: Proprietary.

87.1% percentile inside its fair comparison set

1,284Raw benchmark valueCI 1,277 - 1,291

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 #14 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,287
Percentile: 84.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: creative_writing_vision. Source rank: #14. Votes: 982. Organization: google. License: Proprietary.

84.1% percentile inside its fair comparison set

1,287Raw benchmark valueCI 1,267 - 1,307

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 #17 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,315
Percentile: 83.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: diagram. Source rank: #17. Votes: 3210. Organization: google. License: Proprietary.

83.8% percentile inside its fair comparison set

1,315Raw benchmark valueCI 1,304 - 1,326

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 #22 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,278
Percentile: 84.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: english. Source rank: #23. Votes: 4488. Organization: google. License: Proprietary.

84.8% percentile inside its fair comparison set

1,278Raw benchmark valueCI 1,268 - 1,289

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 #19 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,317
Percentile: 81.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: homework. Source rank: #20. Votes: 1296. Organization: google. License: Proprietary.

81.3% percentile inside its fair comparison set

1,317Raw benchmark valueCI 1,300 - 1,334

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 #5 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,296
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: humor. Source rank: #5. Votes: 487. Organization: google. License: Proprietary.

94.5% percentile inside its fair comparison set

1,296Raw benchmark valueCI 1,268 - 1,324

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 #18 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,299
Percentile: 83%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: ocr. Source rank: #18. Votes: 8599. Organization: google. License: Proprietary.

83% percentile inside its fair comparison set

1,299Raw benchmark valueCI 1,291 - 1,306

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 #12 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,310
Percentile: 92.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: overall. Source rank: #12. Votes: 12336. Organization: google. License: Proprietary.

92.1% percentile inside its fair comparison set

1,310Raw benchmark valueCI 1,303 - 1,317

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 #13 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,310
Percentile: 85.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: creative_writing_vision. Source rank: #13. Votes: 982. Organization: google. License: Proprietary.

85.4% percentile inside its fair comparison set

1,310Raw benchmark valueCI 1,290 - 1,330

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 #13 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,326
Percentile: 87.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: diagram. Source rank: #13. Votes: 3210. Organization: google. License: Proprietary.

87.9% percentile inside its fair comparison set

1,326Raw benchmark valueCI 1,314 - 1,337

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 #10 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,305
Percentile: 93.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: english. Source rank: #10. Votes: 4488. Organization: google. License: Proprietary.

93.5% percentile inside its fair comparison set

1,305Raw benchmark valueCI 1,294 - 1,315

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 #15 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,331
Percentile: 85.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: homework. Source rank: #16. Votes: 1296. Organization: google. License: Proprietary.

85.4% percentile inside its fair comparison set

1,331Raw benchmark valueCI 1,314 - 1,347

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 #4 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,324
Percentile: 95.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: humor. Source rank: #4. Votes: 487. Organization: google. License: Proprietary.

95.9% percentile inside its fair comparison set

1,324Raw benchmark valueCI 1,296 - 1,352

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 #12 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,316
Percentile: 89%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: ocr. Source rank: #12. Votes: 8599. Organization: google. License: Proprietary.

89% percentile inside its fair comparison set

1,316Raw benchmark valueCI 1,309 - 1,324

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 #8 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.3%
Percentile: 91.6%
Last updated: recent
Eligibility: headline eligible

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

91.6% percentile inside its fair comparison set

88.3%Raw benchmark valueCI 86.7% - 89.8%

Document understanding4 benchmarks58.2%

Document Arena

AR · Document understanding · Human

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

Rank #24 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,461
Percentile: 42.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: overall. Source rank: #25. Votes: 6500. Organization: google. License: Proprietary.

42.5% percentile inside its fair comparison set

1,461Raw benchmark valueCI 1,453 - 1,468

Document Arena · No Style Control

AR · Document understanding · Human

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

Rank #19 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 55%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: overall. Source rank: #20. Votes: 6500. Organization: google. License: Proprietary.

55% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,455 - 1,471

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 #19 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.1%
Percentile: 79.1%
Last updated: recent
Eligibility: headline eligible

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

79.1% percentile inside its fair comparison set

68.1%Raw benchmark valueCI 66.3% - 69.9%

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 #16 · Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 63
Percentile: 53.1%
Last updated: aging
Eligibility: headline eligible

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

53.1% percentile inside its fair comparison set

63Raw benchmark valueCI 60 - 66

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #32 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 91.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: chinese. Source rank: #32. Votes: 3451. Organization: google. License: Proprietary.

91.2% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,507 - 1,528

Text Arena · French

AR · Multilingual · Human

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

Rank #32 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 87.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: french. Source rank: #35. Votes: 1511. Organization: google. License: Proprietary.

87.9% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,475 - 1,509

Text Arena · German

AR · Multilingual · Human

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

Rank #14 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 95.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: german. Source rank: #14. Votes: 741. Organization: google. License: Proprietary.

95.2% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,469 - 1,514

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #18 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 93%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: japanese. Source rank: #18. Votes: 672. Organization: google. License: Proprietary.

93% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,454 - 1,504

Text Arena · Korean

AR · Multilingual · Human

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

Rank #29 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 88.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: korean. Source rank: #29. Votes: 855. Organization: google. License: Proprietary.

88.5% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,422 - 1,465

Text Arena · Non English

AR · Multilingual · Human

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

Rank #28 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: non_english. Source rank: #28. Votes: 27909. Organization: google. License: Proprietary.

92.8% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,464 - 1,474

Text Arena · Polish

AR · Multilingual · Human

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

Rank #2 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,511
Percentile: 99.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: polish. Source rank: #2. Votes: 773. Organization: google. License: Proprietary.

99.5% percentile inside its fair comparison set

1,511Raw benchmark valueCI 1,489 - 1,533

Text Arena · Russian

AR · Multilingual · Human

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

Rank #22 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 93.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: russian. Source rank: #22. Votes: 5398. Organization: google. License: Proprietary.

93.8% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,482 - 1,500

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #27 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,471
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: spanish. Source rank: #27. Votes: 1410. Organization: google. License: Proprietary.

90% percentile inside its fair comparison set

1,471Raw benchmark valueCI 1,455 - 1,488

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #24 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,526
Percentile: 93.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: chinese. Source rank: #24. Votes: 3640. Organization: google. License: Proprietary.

93.5% percentile inside its fair comparison set

1,526Raw benchmark valueCI 1,516 - 1,537

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #22 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 91.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: french. Source rank: #22. Votes: 1511. Organization: google. License: Proprietary.

91.8% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,472 - 1,505

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #11 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: german. Source rank: #11. Votes: 741. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,471 - 1,517

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #14 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,486
Percentile: 94.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: japanese. Source rank: #14. Votes: 672. Organization: google. License: Proprietary.

94.7% percentile inside its fair comparison set

1,486Raw benchmark valueCI 1,461 - 1,511

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #18 · Source label: gemini-3.5-flash-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 93%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-medium`. Category: korean. Source rank: #18. Votes: 855. Organization: google. License: Proprietary.

93% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,431 - 1,473

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #15 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: non_english. Source rank: #15. Votes: 27909. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,471 - 1,480

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #2 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,521
Percentile: 99.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: polish. Source rank: #2. Votes: 773. Organization: google. License: Proprietary.

99.5% percentile inside its fair comparison set

1,521Raw benchmark valueCI 1,499 - 1,543

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #15 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 95.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: russian. Source rank: #15. Votes: 5467. Organization: google. License: Proprietary.

95.9% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,484 - 1,501

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #13 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: spanish. Source rank: #13. Votes: 1410. Organization: google. License: Proprietary.

95.4% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,462 - 1,496

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #7 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,349
Percentile: 94.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: chinese. Source rank: #7. Votes: 781. Organization: google. License: Proprietary.

94.2% percentile inside its fair comparison set

1,349Raw benchmark valueCI 1,326 - 1,373

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #3 · Source label: gemini-3.5-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.5-flash-high`. Category: chinese. Source rank: #3. Votes: 781. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,356 - 1,402

Source links and registry checks

official

Vals AI

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 →

official

Scale Labs

Oct 3, 2026

source →

official

Scale Labs

Oct 3, 2026

source →

Gemini 3.5 Flash

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

Gemini 3.5 Flash

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks