Model profile · OpenAI

gpt-6-astra-max

Closed weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

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

Visible coverage: 43.8%
Verified coverage: 43.8%
Spread: 43.2%
Last verified: Oct 3, 2026

88%capability fit

textcodevisiondocument5 aliases42 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 / text35 benchmarks91.6%

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 #7 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 53
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

98.9% percentile inside its fair comparison set

53Raw 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 #11 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 62.6%
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

97.8% percentile inside its fair comparison set

62.6%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 #95 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 48.7%
Percentile: 79.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

79.2% percentile inside its fair comparison set

48.7%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 #336 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $10 /1M input tokens
Percentile: 5.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

5.9% percentile inside its fair comparison set

$10 /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 #337 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $50 /1M output tokens
Percentile: 5.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

5.6% percentile inside its fair comparison set

$50 /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 #213 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 53.7 tokens/s
Percentile: 19.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

19.1% percentile inside its fair comparison set

53.7 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 #263 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 341.88s
Percentile: 0.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

0.8% percentile inside its fair comparison set

341.88sRaw 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 #261 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 341.88s
Percentile: 0.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

0.8% percentile inside its fair comparison set

341.88sRaw 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 #29 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: overall. Source rank: #29. Votes: 9156. Organization: openai. License: Proprietary.

92.6% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,470 - 1,484

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 #38 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,449
Percentile: 90.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: creative_writing. Source rank: #39. Votes: 2029. Organization: openai. License: Proprietary.

90.1% percentile inside its fair comparison set

1,449Raw benchmark valueCI 1,435 - 1,463

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 #26 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: english. Source rank: #26. Votes: 3692. Organization: openai. License: Proprietary.

93.4% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,478 - 1,498

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 #27 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 93.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: exclude_ties. Source rank: #27. Votes: 6832. Organization: openai. License: Proprietary.

93.1% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,480 - 1,498

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 #30 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 92.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: hard_prompts. Source rank: #30. Votes: 5598. Organization: openai. License: Proprietary.

92.3% percentile inside its fair comparison set

1,502Raw benchmark valueCI 1,493 - 1,510

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 #22 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,508
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: hard_prompts_english. Source rank: #22. Votes: 2264. Organization: openai. License: Proprietary.

94.4% percentile inside its fair comparison set

1,508Raw benchmark valueCI 1,496 - 1,521

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 #29 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: instruction_following. Source rank: #30. Votes: 2905. Organization: openai. License: Proprietary.

92.6% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,463 - 1,485

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 #32 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 91.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: longer_query. Source rank: #32. Votes: 3877. Organization: openai. License: Proprietary.

91.3% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,477 - 1,497

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 #23 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 94.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: multi_turn. Source rank: #23. Votes: 1248. Organization: openai. License: Proprietary.

94.1% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,471 - 1,505

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 #66 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 82.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: overall. Source rank: #71. Votes: 9156. Organization: openai. License: Proprietary.

82.7% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,435 - 1,449

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 #64 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 83.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: creative_writing. Source rank: #70. Votes: 2029. Organization: openai. License: Proprietary.

83.2% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,406 - 1,433

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 #71 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 81.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: english. Source rank: #76. Votes: 3692. Organization: openai. License: Proprietary.

81.4% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,438 - 1,458

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 #66 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 82.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: exclude_ties. Source rank: #72. Votes: 6832. Organization: openai. License: Proprietary.

82.7% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,429 - 1,447

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 #48 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 87.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: hard_prompts. Source rank: #51. Votes: 5598. Organization: openai. License: Proprietary.

87.5% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,455 - 1,472

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 #50 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 86.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: hard_prompts_english. Source rank: #52. Votes: 2264. Organization: openai. License: Proprietary.

86.9% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,453 - 1,478

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 #44 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: instruction_following. Source rank: #46. Votes: 2905. Organization: openai. License: Proprietary.

88.6% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,444 - 1,466

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 #49 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 86.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: longer_query. Source rank: #52. Votes: 3877. Organization: openai. License: Proprietary.

86.5% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,448 - 1,468

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 #62 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 83.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: multi_turn. Source rank: #67. Votes: 1248. Organization: openai. License: Proprietary.

83.7% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,435 - 1,469

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 #8 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.6%
Percentile: 89.2%
Last updated: stale
Eligibility: headline eligible

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

89.2% 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 #4 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 89.4%
Percentile: 95.4%
Last updated: stale
Eligibility: headline eligible

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

95.4% percentile inside its fair comparison set

89.4%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 #5 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.3%
Percentile: 93.8%
Last updated: stale
Eligibility: headline eligible

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

93.8% percentile inside its fair comparison set

78.3%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 #10 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70.5%
Percentile: 86.2%
Last updated: stale
Eligibility: headline eligible

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

86.2% percentile inside its fair comparison set

70.5%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 #23 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74%
Percentile: 66.2%
Last updated: stale
Eligibility: headline eligible

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

66.2% percentile inside its fair comparison set

74%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 #10 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 79.6%
Percentile: 86.2%
Last updated: stale
Eligibility: headline eligible

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

86.2% percentile inside its fair comparison set

79.6%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 #14 · Source label: gpt-6-astra-max

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 #1 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86.3%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

86.3%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 #33 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82%
Percentile: 61.5%
Last updated: stale
Eligibility: headline eligible

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

61.5% percentile inside its fair comparison set

82%Raw benchmark value

Coding20 benchmarks90.9%

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 #28 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 56.5%
Percentile: 86.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

86.4% percentile inside its fair comparison set

56.5%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 #7 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,543
Percentile: 98.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: coding. Source rank: #7. Votes: 2135. Organization: openai. License: Proprietary.

98.4% percentile inside its fair comparison set

1,543Raw benchmark valueCI 1,530 - 1,556

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 #35 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 90.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: coding. Source rank: #35. Votes: 2135. Organization: openai. License: Proprietary.

90.8% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,476 - 1,502

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 #6 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.6%
Percentile: 94.6%
Last updated: recent
Eligibility: headline eligible

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

94.6% percentile inside its fair comparison set

89.6%Raw benchmark valueCI 85.3% - 93.9%

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 #2 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,788
Percentile: 99.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: overall. Source rank: #2. Votes: 6123. Organization: openai. License: Proprietary.

99.2% percentile inside its fair comparison set

1,788Raw benchmark valueCI 1,777 - 1,798

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 #2 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,781
Percentile: 99.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: webdev-html. Source rank: #2. Votes: 977. Organization: openai. License: Proprietary.

99.2% percentile inside its fair comparison set

1,781Raw benchmark valueCI 1,756 - 1,805

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 #3 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,810
Percentile: 98.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: webdev-react. Source rank: #3. Votes: 4213. Organization: openai. License: Proprietary.

98.2% percentile inside its fair comparison set

1,810Raw benchmark valueCI 1,798 - 1,822

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 #3 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67.7%
Percentile: 97.1%
Last updated: recent
Eligibility: headline eligible

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

97.1% percentile inside its fair comparison set

67.7%Raw benchmark valueCI 59.5% - 76%

IOI

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 #2 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 100%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: ioi; provider: OpenAI.

100% percentile inside its fair comparison set

100%Raw benchmark valueCI 100% - 100%

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 #4 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 5.5%
Percentile: 94.8%
Last updated: recent
Eligibility: headline eligible

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

94.8% percentile inside its fair comparison set

5.5%Raw benchmark valueCI 2.3% - 8.7%

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 #2 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.3%
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

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

98.5% percentile inside its fair comparison set

87.3%Raw benchmark valueCI 86.5% - 88%

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 #1 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,733
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: image_to_webdev. Source rank: #1. Votes: 1085. Organization: openai. License: Proprietary.

100% percentile inside its fair comparison set

1,733Raw benchmark valueCI 1,712 - 1,754

Terminal-Bench 4.0

TERMINAL-BENCH · Coding · Objective

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

Rank #1 · Source label: GPT-6 Astra (max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 58.2%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from the public Terminal-Bench 4.0 official published leaderboard (status: display). Collapse policy: highest verified score per canonical model. Selected agent: Codex. Display model: GPT-6 Astra. Agent URL: https://openai.com/codex/. Reported stderr: 1.423 percentage points.

100% percentile inside its fair comparison set

58.2%Raw benchmark valueCI 55.4% - 61%

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 #21 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 57.3%
Percentile: 69.2%
Last updated: stale
Eligibility: headline eligible

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

69.2% percentile inside its fair comparison set

57.3%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 #20 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.4%
Percentile: 70.8%
Last updated: stale
Eligibility: headline eligible

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

70.8% percentile inside its fair comparison set

80.4%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 #42 · Source label: gpt-6-astra-max

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 #33 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 43.3%
Percentile: 61.5%
Last updated: stale
Eligibility: headline eligible

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

61.5% percentile inside its fair comparison set

43.3%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 #12 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65%
Percentile: 86.2%
Last updated: stale
Eligibility: headline eligible

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

86.2% percentile inside its fair comparison set

65%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 #22 · Source label: gpt-6-astra-max

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 #26 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.4%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

80.4%Raw benchmark value

Reasoning / math / science16 benchmarks94.8%

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 #12 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 54.7%
Percentile: 97.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

97.9% percentile inside its fair comparison set

54.7%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 #2 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 96.1%
Percentile: 99.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

99.8% percentile inside its fair comparison set

96.1%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 #2 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 31.7%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

100% percentile inside its fair comparison set

31.7%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 #26 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 93%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: math. Source rank: #27. Votes: 458. Organization: openai. License: Proprietary.

93% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,463 - 1,517

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 #42 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: math. Source rank: #44. Votes: 458. Organization: openai. License: Proprietary.

88.6% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,442 - 1,496

ProofBench

VALS-AI · Reasoning / math / science · Objective

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

Rank #5 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 99%
Percentile: 92.9%
Last updated: recent
Eligibility: headline eligible

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

92.9% percentile inside its fair comparison set

99%Raw benchmark valueCI 97% - 101%

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #4 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.8%
Percentile: 95.4%
Last updated: stale
Eligibility: headline eligible

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

95.4% percentile inside its fair comparison set

96.8%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 #1 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 92.7%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

92.7%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 #35 · Source label: gpt-6-astra-max

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 #2 · Source label: gpt-6-astra-max

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: integrals_with_game. Category: Mathematics.

100% percentile inside its fair comparison set

100%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 #13 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 97.1%
Percentile: 96.9%
Last updated: stale
Eligibility: headline eligible

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

96.9% percentile inside its fair comparison set

97.1%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 #9 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 92.2%
Percentile: 87.7%
Last updated: stale
Eligibility: headline eligible

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

87.7% percentile inside its fair comparison set

92.2%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 #14 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84.6%
Percentile: 87.7%
Last updated: stale
Eligibility: headline eligible

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

87.7% percentile inside its fair comparison set

84.6%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 #11 · Source label: gpt-6-astra-max

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: zebra_puzzle. Category: Reasoning.

100% percentile inside its fair comparison set

100%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 #30 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

72.3% percentile inside its fair comparison set

98%Raw benchmark value

Logic with navigation

LB · Reasoning / math / science · Objective

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

Rank #2 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 88%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

88%Raw benchmark value

Professional reasoning31 benchmarks79.7%

PRBench Legal

SL · Professional reasoning · Rubric

Applied legal reasoning on professional-domain tasks.

Rank #15 · Source label: GPT 6 Astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 48.4%
Percentile: 65.9%
Last updated: recent
Eligibility: headline eligible

Parsed from the public Scale Labs page for scale-prbench-legal. Reported model configuration: GPT 6 Astra. Collapse policy: highest reported score per canonical model.

65.9% percentile inside its fair comparison set

48.4%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #20 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 94.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: expert. Source rank: #20. Votes: 900. Organization: openai. License: Proprietary.

94.2% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,497 - 1,537

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 #33 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 91.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_business_and_management_and_financial_operations. Source rank: #35. Votes: 1640. Organization: openai. License: Proprietary.

91.3% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,458 - 1,488

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 #22 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_entertainment_and_sports_and_media. Source rank: #22. Votes: 2320. Organization: openai. License: Proprietary.

94.4% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,445 - 1,471

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #29 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_legal_and_government. Source rank: #30. Votes: 785. Organization: openai. License: Proprietary.

92% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,463 - 1,506

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 #31 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,493
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_life_and_physical_and_social_science. Source rank: #32. Votes: 1538. Organization: openai. License: Proprietary.

92% percentile inside its fair comparison set

1,493Raw benchmark valueCI 1,478 - 1,508

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #21 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_mathematical. Source rank: #22. Votes: 511. Organization: openai. License: Proprietary.

94.4% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,472 - 1,525

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #75 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 78.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_medicine_and_healthcare. Source rank: #82. Votes: 672. Organization: openai. License: Proprietary.

78.6% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,444 - 1,490

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 #17 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,523
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_software_and_it_services. Source rank: #17. Votes: 3336. Organization: openai. License: Proprietary.

95.7% percentile inside its fair comparison set

1,523Raw benchmark valueCI 1,513 - 1,533

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 #29 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 92.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_writing_and_literature_and_language. Source rank: #31. Votes: 2559. Organization: openai. License: Proprietary.

92.5% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,453 - 1,478

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #32 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 90.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: expert. Source rank: #33. Votes: 900. Organization: openai. License: Proprietary.

90.5% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,473 - 1,512

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 #56 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 85.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_business_and_management_and_financial_operations. Source rank: #59. Votes: 1640. Organization: openai. License: Proprietary.

85.1% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,422 - 1,452

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 #48 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 87.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_entertainment_and_sports_and_media. Source rank: #50. Votes: 2320. Organization: openai. License: Proprietary.

87.4% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,415 - 1,441

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 #56 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 84.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_legal_and_government. Source rank: #59. Votes: 785. Organization: openai. License: Proprietary.

84.2% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,433 - 1,476

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 #75 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 80.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_life_and_physical_and_social_science. Source rank: #80. Votes: 1538. Organization: openai. License: Proprietary.

80.2% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,435 - 1,466

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #39 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 89.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_mathematical. Source rank: #41. Votes: 511. Organization: openai. License: Proprietary.

89.3% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,451 - 1,503

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 #119 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 65.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_medicine_and_healthcare. Source rank: #130. Votes: 672. Organization: openai. License: Proprietary.

65.9% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,396 - 1,441

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 #49 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 87.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_software_and_it_services. Source rank: #51. Votes: 3336. Organization: openai. License: Proprietary.

87.2% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,465 - 1,485

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 #50 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 86.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_writing_and_literature_and_language. Source rank: #53. Votes: 2559. Organization: openai. License: Proprietary.

86.9% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,427 - 1,451

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #6 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 63
Percentile: 87.5%
Last updated: recent
Eligibility: headline eligible

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

87.5% percentile inside its fair comparison set

63Raw benchmark valueCI 61 - 65

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #25 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 39.4%
Percentile: 64.7%
Last updated: recent
Eligibility: headline eligible

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

64.7% percentile inside its fair comparison set

39.4%Raw benchmark valueCI 32.8% - 46.1%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #28 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 5.4%
Percentile: 60.9%
Last updated: recent
Eligibility: headline eligible

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

60.9% percentile inside its fair comparison set

5.4%Raw benchmark valueCI 3.1% - 7.7%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #25 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 53.5%
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

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

65.2% percentile inside its fair comparison set

53.5%Raw benchmark valueCI 49.5% - 57.6%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #28 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 48.5%
Percentile: 71.6%
Last updated: recent
Eligibility: headline eligible

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

71.6% percentile inside its fair comparison set

48.5%Raw benchmark valueCI 44.3% - 52.7%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #14 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.9%
Percentile: 86.5%
Last updated: recent
Eligibility: headline eligible

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

86.5% percentile inside its fair comparison set

87.9%Raw benchmark valueCI 84.1% - 91.7%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #36 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 46.4%
Percentile: 56.8%
Last updated: recent
Eligibility: headline eligible

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

56.8% percentile inside its fair comparison set

46.4%Raw benchmark valueCI 39.6% - 53.1%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #1 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 83%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

83%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #4 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.2%
Percentile: 95.4%
Last updated: stale
Eligibility: headline eligible

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

95.4% percentile inside its fair comparison set

82.2%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #6 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 90.6%
Percentile: 93.8%
Last updated: stale
Eligibility: headline eligible

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

93.8% percentile inside its fair comparison set

90.6%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #1 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58.4%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

58.4%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #19 · Source label: gpt-6-astra-max

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: tablereformat. Category: Data Analysis.

100% percentile inside its fair comparison set

100%Raw benchmark value

Long context1 benchmark90.8%

Long Context Reasoning

AA · Long context · Objective

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

Rank #43 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 80.7%
Percentile: 90.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

90.8% percentile inside its fair comparison set

80.7%Raw benchmark value

Vision understanding13 benchmarks92.9%

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 #2 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 86.9%
Percentile: 99.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

99.5% percentile inside its fair comparison set

86.9%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 #20 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,284
Percentile: 86.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: overall. Source rank: #20. Votes: 3175. Organization: openai. License: Proprietary.

86.3% percentile inside its fair comparison set

1,284Raw benchmark valueCI 1,273 - 1,296

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 #15 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,285
Percentile: 82.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: creative_writing_vision. Source rank: #15. Votes: 340. Organization: openai. License: Proprietary.

82.9% percentile inside its fair comparison set

1,285Raw benchmark valueCI 1,251 - 1,319

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 #20 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,311
Percentile: 80.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: diagram. Source rank: #22. Votes: 752. Organization: openai. License: Proprietary.

80.8% percentile inside its fair comparison set

1,311Raw benchmark valueCI 1,289 - 1,333

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 #10 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,289
Percentile: 93.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: english. Source rank: #10. Votes: 1055. Organization: openai. License: Proprietary.

93.5% percentile inside its fair comparison set

1,289Raw benchmark valueCI 1,270 - 1,308

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 #3 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,342
Percentile: 97.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: homework. Source rank: #3. Votes: 411. Organization: openai. License: Proprietary.

97.9% percentile inside its fair comparison set

1,342Raw benchmark valueCI 1,314 - 1,371

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 #16 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,299
Percentile: 85%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: ocr. Source rank: #16. Votes: 2145. Organization: openai. License: Proprietary.

85% percentile inside its fair comparison set

1,299Raw benchmark valueCI 1,286 - 1,312

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 #31 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,280
Percentile: 78.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: overall. Source rank: #34. Votes: 3175. Organization: openai. License: Proprietary.

78.4% percentile inside its fair comparison set

1,280Raw benchmark valueCI 1,268 - 1,291

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 #26 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,275
Percentile: 69.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: creative_writing_vision. Source rank: #30. Votes: 340. Organization: openai. License: Proprietary.

69.5% percentile inside its fair comparison set

1,275Raw benchmark valueCI 1,241 - 1,308

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 #28 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,299
Percentile: 72.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: diagram. Source rank: #31. Votes: 752. Organization: openai. License: Proprietary.

72.7% percentile inside its fair comparison set

1,299Raw benchmark valueCI 1,277 - 1,321

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 #30 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,282
Percentile: 79%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: english. Source rank: #33. Votes: 1055. Organization: openai. License: Proprietary.

79% percentile inside its fair comparison set

1,282Raw benchmark valueCI 1,263 - 1,301

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 #8 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,338
Percentile: 92.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: homework. Source rank: #8. Votes: 411. Organization: openai. License: Proprietary.

92.7% percentile inside its fair comparison set

1,338Raw benchmark valueCI 1,310 - 1,366

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 #27 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,292
Percentile: 74%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: ocr. Source rank: #30. Votes: 2145. Organization: openai. License: Proprietary.

74% percentile inside its fair comparison set

1,292Raw benchmark valueCI 1,279 - 1,305

Document understanding2 benchmarks62.5%

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 #16 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: overall. Source rank: #17. Votes: 1621. Organization: openai. License: Proprietary.

62.5% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,458 - 1,487

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 #15 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 65%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: overall. Source rank: #16. Votes: 1621. Organization: openai. License: Proprietary.

65% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,453 - 1,482

Multilingual14 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #41 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,510
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: chinese. Source rank: #43. Votes: 674. Organization: openai. License: Proprietary.

88.6% percentile inside its fair comparison set

1,510Raw benchmark valueCI 1,488 - 1,532

Text Arena · French

AR · Multilingual · Human

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

Rank #26 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 90.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: french. Source rank: #26. Votes: 216. Organization: openai. License: Proprietary.

90.3% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,456 - 1,537

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #59 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 76.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: japanese. Source rank: #68. Votes: 174. Organization: openai. License: Proprietary.

76.1% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,370 - 1,467

Text Arena · Non English

AR · Multilingual · Human

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

Rank #36 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 90.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: non_english. Source rank: #38. Votes: 5457. Organization: openai. License: Proprietary.

90.7% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,454 - 1,471

Text Arena · Russian

AR · Multilingual · Human

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

Rank #39 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 88.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: russian. Source rank: #43. Votes: 1191. Organization: openai. License: Proprietary.

88.9% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,453 - 1,487

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #77 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 70.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: spanish. Source rank: #86. Votes: 269. Organization: openai. License: Proprietary.

70.7% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,401 - 1,473

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #64 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 82.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: chinese. Source rank: #67. Votes: 674. Organization: openai. License: Proprietary.

82.1% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,465 - 1,509

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #67 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 74.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: french. Source rank: #72. Votes: 216. Organization: openai. License: Proprietary.

74.3% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,413 - 1,494

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #81 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 67.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: japanese. Source rank: #92. Votes: 174. Organization: openai. License: Proprietary.

67.1% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,333 - 1,430

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #60 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 84.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: non_english. Source rank: #66. Votes: 5457. Organization: openai. License: Proprietary.

84.3% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,423 - 1,440

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #60 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 82.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: russian. Source rank: #66. Votes: 1191. Organization: openai. License: Proprietary.

82.7% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,422 - 1,457

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #114 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 56.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: spanish. Source rank: #125. Votes: 269. Organization: openai. License: Proprietary.

56.4% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,373 - 1,445

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #3 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,358
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: chinese. Source rank: #3. Votes: 201. Organization: openai. License: Proprietary.

98.1% percentile inside its fair comparison set

1,358Raw benchmark valueCI 1,316 - 1,400

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #11 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 90.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: chinese. Source rank: #12. Votes: 201. Organization: openai. License: Proprietary.

90.4% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,323 - 1,407

Source links and registry checks

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

Terminal-Bench

Oct 3, 2026

source →

Model profile · OpenAI

gpt-6-astra-max

Closed weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

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

Visible coverage: 43.8%
Verified coverage: 43.8%
Spread: 43.2%
Last verified: Oct 3, 2026

88%capability fit

textcodevisiondocument5 aliases42 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 / text35 benchmarks91.6%

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 #7 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 53
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

98.9% percentile inside its fair comparison set

53Raw 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 #11 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 62.6%
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

97.8% percentile inside its fair comparison set

62.6%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 #95 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 48.7%
Percentile: 79.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

79.2% percentile inside its fair comparison set

48.7%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 #336 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $10 /1M input tokens
Percentile: 5.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

5.9% percentile inside its fair comparison set

$10 /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 #337 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $50 /1M output tokens
Percentile: 5.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

5.6% percentile inside its fair comparison set

$50 /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 #213 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 53.7 tokens/s
Percentile: 19.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

19.1% percentile inside its fair comparison set

53.7 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 #263 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 341.88s
Percentile: 0.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

0.8% percentile inside its fair comparison set

341.88sRaw 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 #261 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 341.88s
Percentile: 0.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

0.8% percentile inside its fair comparison set

341.88sRaw 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 #29 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: overall. Source rank: #29. Votes: 9156. Organization: openai. License: Proprietary.

92.6% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,470 - 1,484

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 #38 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,449
Percentile: 90.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: creative_writing. Source rank: #39. Votes: 2029. Organization: openai. License: Proprietary.

90.1% percentile inside its fair comparison set

1,449Raw benchmark valueCI 1,435 - 1,463

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 #26 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: english. Source rank: #26. Votes: 3692. Organization: openai. License: Proprietary.

93.4% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,478 - 1,498

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 #27 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 93.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: exclude_ties. Source rank: #27. Votes: 6832. Organization: openai. License: Proprietary.

93.1% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,480 - 1,498

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 #30 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 92.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: hard_prompts. Source rank: #30. Votes: 5598. Organization: openai. License: Proprietary.

92.3% percentile inside its fair comparison set

1,502Raw benchmark valueCI 1,493 - 1,510

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 #22 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,508
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: hard_prompts_english. Source rank: #22. Votes: 2264. Organization: openai. License: Proprietary.

94.4% percentile inside its fair comparison set

1,508Raw benchmark valueCI 1,496 - 1,521

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 #29 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: instruction_following. Source rank: #30. Votes: 2905. Organization: openai. License: Proprietary.

92.6% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,463 - 1,485

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 #32 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 91.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: longer_query. Source rank: #32. Votes: 3877. Organization: openai. License: Proprietary.

91.3% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,477 - 1,497

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 #23 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 94.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: multi_turn. Source rank: #23. Votes: 1248. Organization: openai. License: Proprietary.

94.1% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,471 - 1,505

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 #66 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 82.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: overall. Source rank: #71. Votes: 9156. Organization: openai. License: Proprietary.

82.7% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,435 - 1,449

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 #64 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 83.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: creative_writing. Source rank: #70. Votes: 2029. Organization: openai. License: Proprietary.

83.2% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,406 - 1,433

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 #71 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 81.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: english. Source rank: #76. Votes: 3692. Organization: openai. License: Proprietary.

81.4% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,438 - 1,458

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 #66 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 82.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: exclude_ties. Source rank: #72. Votes: 6832. Organization: openai. License: Proprietary.

82.7% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,429 - 1,447

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 #48 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 87.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: hard_prompts. Source rank: #51. Votes: 5598. Organization: openai. License: Proprietary.

87.5% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,455 - 1,472

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 #50 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 86.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: hard_prompts_english. Source rank: #52. Votes: 2264. Organization: openai. License: Proprietary.

86.9% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,453 - 1,478

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 #44 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: instruction_following. Source rank: #46. Votes: 2905. Organization: openai. License: Proprietary.

88.6% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,444 - 1,466

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 #49 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 86.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: longer_query. Source rank: #52. Votes: 3877. Organization: openai. License: Proprietary.

86.5% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,448 - 1,468

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 #62 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 83.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: multi_turn. Source rank: #67. Votes: 1248. Organization: openai. License: Proprietary.

83.7% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,435 - 1,469

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 #8 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.6%
Percentile: 89.2%
Last updated: stale
Eligibility: headline eligible

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

89.2% 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 #4 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 89.4%
Percentile: 95.4%
Last updated: stale
Eligibility: headline eligible

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

95.4% percentile inside its fair comparison set

89.4%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 #5 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.3%
Percentile: 93.8%
Last updated: stale
Eligibility: headline eligible

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

93.8% percentile inside its fair comparison set

78.3%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 #10 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70.5%
Percentile: 86.2%
Last updated: stale
Eligibility: headline eligible

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

86.2% percentile inside its fair comparison set

70.5%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 #23 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74%
Percentile: 66.2%
Last updated: stale
Eligibility: headline eligible

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

66.2% percentile inside its fair comparison set

74%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 #10 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 79.6%
Percentile: 86.2%
Last updated: stale
Eligibility: headline eligible

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

86.2% percentile inside its fair comparison set

79.6%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 #14 · Source label: gpt-6-astra-max

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 #1 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86.3%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

86.3%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 #33 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82%
Percentile: 61.5%
Last updated: stale
Eligibility: headline eligible

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

61.5% percentile inside its fair comparison set

82%Raw benchmark value

Coding20 benchmarks90.9%

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 #28 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 56.5%
Percentile: 86.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

86.4% percentile inside its fair comparison set

56.5%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 #7 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,543
Percentile: 98.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: coding. Source rank: #7. Votes: 2135. Organization: openai. License: Proprietary.

98.4% percentile inside its fair comparison set

1,543Raw benchmark valueCI 1,530 - 1,556

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 #35 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 90.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: coding. Source rank: #35. Votes: 2135. Organization: openai. License: Proprietary.

90.8% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,476 - 1,502

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 #6 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.6%
Percentile: 94.6%
Last updated: recent
Eligibility: headline eligible

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

94.6% percentile inside its fair comparison set

89.6%Raw benchmark valueCI 85.3% - 93.9%

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 #2 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,788
Percentile: 99.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: overall. Source rank: #2. Votes: 6123. Organization: openai. License: Proprietary.

99.2% percentile inside its fair comparison set

1,788Raw benchmark valueCI 1,777 - 1,798

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 #2 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,781
Percentile: 99.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: webdev-html. Source rank: #2. Votes: 977. Organization: openai. License: Proprietary.

99.2% percentile inside its fair comparison set

1,781Raw benchmark valueCI 1,756 - 1,805

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 #3 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,810
Percentile: 98.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: webdev-react. Source rank: #3. Votes: 4213. Organization: openai. License: Proprietary.

98.2% percentile inside its fair comparison set

1,810Raw benchmark valueCI 1,798 - 1,822

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 #3 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67.7%
Percentile: 97.1%
Last updated: recent
Eligibility: headline eligible

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

97.1% percentile inside its fair comparison set

67.7%Raw benchmark valueCI 59.5% - 76%

IOI

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 #2 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 100%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: ioi; provider: OpenAI.

100% percentile inside its fair comparison set

100%Raw benchmark valueCI 100% - 100%

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 #4 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 5.5%
Percentile: 94.8%
Last updated: recent
Eligibility: headline eligible

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

94.8% percentile inside its fair comparison set

5.5%Raw benchmark valueCI 2.3% - 8.7%

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 #2 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.3%
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

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

98.5% percentile inside its fair comparison set

87.3%Raw benchmark valueCI 86.5% - 88%

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 #1 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,733
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: image_to_webdev. Source rank: #1. Votes: 1085. Organization: openai. License: Proprietary.

100% percentile inside its fair comparison set

1,733Raw benchmark valueCI 1,712 - 1,754

Terminal-Bench 4.0

TERMINAL-BENCH · Coding · Objective

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

Rank #1 · Source label: GPT-6 Astra (max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 58.2%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

100% percentile inside its fair comparison set

58.2%Raw benchmark valueCI 55.4% - 61%

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 #21 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 57.3%
Percentile: 69.2%
Last updated: stale
Eligibility: headline eligible

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

69.2% percentile inside its fair comparison set

57.3%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 #20 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.4%
Percentile: 70.8%
Last updated: stale
Eligibility: headline eligible

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

70.8% percentile inside its fair comparison set

80.4%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 #42 · Source label: gpt-6-astra-max

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 #33 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 43.3%
Percentile: 61.5%
Last updated: stale
Eligibility: headline eligible

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

61.5% percentile inside its fair comparison set

43.3%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 #12 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65%
Percentile: 86.2%
Last updated: stale
Eligibility: headline eligible

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

86.2% percentile inside its fair comparison set

65%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 #22 · Source label: gpt-6-astra-max

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 #26 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.4%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

80.4%Raw benchmark value

Reasoning / math / science16 benchmarks94.8%

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 #12 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 54.7%
Percentile: 97.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

97.9% percentile inside its fair comparison set

54.7%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 #2 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 96.1%
Percentile: 99.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

99.8% percentile inside its fair comparison set

96.1%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 #2 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 31.7%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

100% percentile inside its fair comparison set

31.7%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 #26 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 93%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: math. Source rank: #27. Votes: 458. Organization: openai. License: Proprietary.

93% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,463 - 1,517

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 #42 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: math. Source rank: #44. Votes: 458. Organization: openai. License: Proprietary.

88.6% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,442 - 1,496

ProofBench

VALS-AI · Reasoning / math / science · Objective

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

Rank #5 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 99%
Percentile: 92.9%
Last updated: recent
Eligibility: headline eligible

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

92.9% percentile inside its fair comparison set

99%Raw benchmark valueCI 97% - 101%

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #4 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.8%
Percentile: 95.4%
Last updated: stale
Eligibility: headline eligible

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

95.4% percentile inside its fair comparison set

96.8%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 #1 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 92.7%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

92.7%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 #35 · Source label: gpt-6-astra-max

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 #2 · Source label: gpt-6-astra-max

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: integrals_with_game. Category: Mathematics.

100% percentile inside its fair comparison set

100%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 #13 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 97.1%
Percentile: 96.9%
Last updated: stale
Eligibility: headline eligible

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

96.9% percentile inside its fair comparison set

97.1%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 #9 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 92.2%
Percentile: 87.7%
Last updated: stale
Eligibility: headline eligible

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

87.7% percentile inside its fair comparison set

92.2%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 #14 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84.6%
Percentile: 87.7%
Last updated: stale
Eligibility: headline eligible

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

87.7% percentile inside its fair comparison set

84.6%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 #11 · Source label: gpt-6-astra-max

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: zebra_puzzle. Category: Reasoning.

100% percentile inside its fair comparison set

100%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 #30 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

72.3% percentile inside its fair comparison set

98%Raw benchmark value

Logic with navigation

LB · Reasoning / math / science · Objective

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

Rank #2 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 88%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

88%Raw benchmark value

Professional reasoning31 benchmarks79.7%

PRBench Legal

SL · Professional reasoning · Rubric

Applied legal reasoning on professional-domain tasks.

Rank #15 · Source label: GPT 6 Astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 48.4%
Percentile: 65.9%
Last updated: recent
Eligibility: headline eligible

Parsed from the public Scale Labs page for scale-prbench-legal. Reported model configuration: GPT 6 Astra. Collapse policy: highest reported score per canonical model.

65.9% percentile inside its fair comparison set

48.4%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #20 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 94.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: expert. Source rank: #20. Votes: 900. Organization: openai. License: Proprietary.

94.2% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,497 - 1,537

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 #33 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 91.3%
Last updated: recent
Eligibility: headline eligible

91.3% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,458 - 1,488

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 #22 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_entertainment_and_sports_and_media. Source rank: #22. Votes: 2320. Organization: openai. License: Proprietary.

94.4% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,445 - 1,471

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #29 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_legal_and_government. Source rank: #30. Votes: 785. Organization: openai. License: Proprietary.

92% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,463 - 1,506

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 #31 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,493
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_life_and_physical_and_social_science. Source rank: #32. Votes: 1538. Organization: openai. License: Proprietary.

92% percentile inside its fair comparison set

1,493Raw benchmark valueCI 1,478 - 1,508

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #21 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_mathematical. Source rank: #22. Votes: 511. Organization: openai. License: Proprietary.

94.4% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,472 - 1,525

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #75 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 78.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_medicine_and_healthcare. Source rank: #82. Votes: 672. Organization: openai. License: Proprietary.

78.6% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,444 - 1,490

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 #17 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,523
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_software_and_it_services. Source rank: #17. Votes: 3336. Organization: openai. License: Proprietary.

95.7% percentile inside its fair comparison set

1,523Raw benchmark valueCI 1,513 - 1,533

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 #29 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 92.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_writing_and_literature_and_language. Source rank: #31. Votes: 2559. Organization: openai. License: Proprietary.

92.5% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,453 - 1,478

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #32 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 90.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: expert. Source rank: #33. Votes: 900. Organization: openai. License: Proprietary.

90.5% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,473 - 1,512

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 #56 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 85.1%
Last updated: recent
Eligibility: headline eligible

85.1% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,422 - 1,452

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 #48 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 87.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_entertainment_and_sports_and_media. Source rank: #50. Votes: 2320. Organization: openai. License: Proprietary.

87.4% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,415 - 1,441

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 #56 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 84.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_legal_and_government. Source rank: #59. Votes: 785. Organization: openai. License: Proprietary.

84.2% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,433 - 1,476

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 #75 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 80.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_life_and_physical_and_social_science. Source rank: #80. Votes: 1538. Organization: openai. License: Proprietary.

80.2% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,435 - 1,466

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #39 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 89.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_mathematical. Source rank: #41. Votes: 511. Organization: openai. License: Proprietary.

89.3% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,451 - 1,503

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 #119 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 65.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_medicine_and_healthcare. Source rank: #130. Votes: 672. Organization: openai. License: Proprietary.

65.9% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,396 - 1,441

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 #49 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 87.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_software_and_it_services. Source rank: #51. Votes: 3336. Organization: openai. License: Proprietary.

87.2% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,465 - 1,485

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 #50 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 86.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: industry_writing_and_literature_and_language. Source rank: #53. Votes: 2559. Organization: openai. License: Proprietary.

86.9% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,427 - 1,451

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #6 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 63
Percentile: 87.5%
Last updated: recent
Eligibility: headline eligible

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

87.5% percentile inside its fair comparison set

63Raw benchmark valueCI 61 - 65

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #25 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 39.4%
Percentile: 64.7%
Last updated: recent
Eligibility: headline eligible

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

64.7% percentile inside its fair comparison set

39.4%Raw benchmark valueCI 32.8% - 46.1%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #28 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 5.4%
Percentile: 60.9%
Last updated: recent
Eligibility: headline eligible

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

60.9% percentile inside its fair comparison set

5.4%Raw benchmark valueCI 3.1% - 7.7%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #25 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 53.5%
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

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

65.2% percentile inside its fair comparison set

53.5%Raw benchmark valueCI 49.5% - 57.6%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #28 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 48.5%
Percentile: 71.6%
Last updated: recent
Eligibility: headline eligible

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

71.6% percentile inside its fair comparison set

48.5%Raw benchmark valueCI 44.3% - 52.7%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #14 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.9%
Percentile: 86.5%
Last updated: recent
Eligibility: headline eligible

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

86.5% percentile inside its fair comparison set

87.9%Raw benchmark valueCI 84.1% - 91.7%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #36 · Source label: openai/gpt-6-astra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 46.4%
Percentile: 56.8%
Last updated: recent
Eligibility: headline eligible

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

56.8% percentile inside its fair comparison set

46.4%Raw benchmark valueCI 39.6% - 53.1%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #1 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 83%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

83%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #4 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.2%
Percentile: 95.4%
Last updated: stale
Eligibility: headline eligible

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

95.4% percentile inside its fair comparison set

82.2%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #6 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 90.6%
Percentile: 93.8%
Last updated: stale
Eligibility: headline eligible

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

93.8% percentile inside its fair comparison set

90.6%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #1 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58.4%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

58.4%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #19 · Source label: gpt-6-astra-max

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: tablereformat. Category: Data Analysis.

100% percentile inside its fair comparison set

100%Raw benchmark value

Long context1 benchmark90.8%

Long Context Reasoning

AA · Long context · Objective

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

Rank #43 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 80.7%
Percentile: 90.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

90.8% percentile inside its fair comparison set

80.7%Raw benchmark value

Vision understanding13 benchmarks92.9%

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 #2 · Source label: GPT-6 Astra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 86.9%
Percentile: 99.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

99.5% percentile inside its fair comparison set

86.9%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 #20 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,284
Percentile: 86.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: overall. Source rank: #20. Votes: 3175. Organization: openai. License: Proprietary.

86.3% percentile inside its fair comparison set

1,284Raw benchmark valueCI 1,273 - 1,296

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 #15 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,285
Percentile: 82.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: creative_writing_vision. Source rank: #15. Votes: 340. Organization: openai. License: Proprietary.

82.9% percentile inside its fair comparison set

1,285Raw benchmark valueCI 1,251 - 1,319

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 #20 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,311
Percentile: 80.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: diagram. Source rank: #22. Votes: 752. Organization: openai. License: Proprietary.

80.8% percentile inside its fair comparison set

1,311Raw benchmark valueCI 1,289 - 1,333

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 #10 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,289
Percentile: 93.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: english. Source rank: #10. Votes: 1055. Organization: openai. License: Proprietary.

93.5% percentile inside its fair comparison set

1,289Raw benchmark valueCI 1,270 - 1,308

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 #3 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,342
Percentile: 97.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: homework. Source rank: #3. Votes: 411. Organization: openai. License: Proprietary.

97.9% percentile inside its fair comparison set

1,342Raw benchmark valueCI 1,314 - 1,371

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 #16 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,299
Percentile: 85%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: ocr. Source rank: #16. Votes: 2145. Organization: openai. License: Proprietary.

85% percentile inside its fair comparison set

1,299Raw benchmark valueCI 1,286 - 1,312

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 #31 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,280
Percentile: 78.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: overall. Source rank: #34. Votes: 3175. Organization: openai. License: Proprietary.

78.4% percentile inside its fair comparison set

1,280Raw benchmark valueCI 1,268 - 1,291

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 #26 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,275
Percentile: 69.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: creative_writing_vision. Source rank: #30. Votes: 340. Organization: openai. License: Proprietary.

69.5% percentile inside its fair comparison set

1,275Raw benchmark valueCI 1,241 - 1,308

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 #28 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,299
Percentile: 72.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: diagram. Source rank: #31. Votes: 752. Organization: openai. License: Proprietary.

72.7% percentile inside its fair comparison set

1,299Raw benchmark valueCI 1,277 - 1,321

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 #30 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,282
Percentile: 79%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: english. Source rank: #33. Votes: 1055. Organization: openai. License: Proprietary.

79% percentile inside its fair comparison set

1,282Raw benchmark valueCI 1,263 - 1,301

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 #8 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,338
Percentile: 92.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: homework. Source rank: #8. Votes: 411. Organization: openai. License: Proprietary.

92.7% percentile inside its fair comparison set

1,338Raw benchmark valueCI 1,310 - 1,366

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 #27 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,292
Percentile: 74%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: ocr. Source rank: #30. Votes: 2145. Organization: openai. License: Proprietary.

74% percentile inside its fair comparison set

1,292Raw benchmark valueCI 1,279 - 1,305

Document understanding2 benchmarks62.5%

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 #16 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: overall. Source rank: #17. Votes: 1621. Organization: openai. License: Proprietary.

62.5% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,458 - 1,487

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 #15 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 65%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: overall. Source rank: #16. Votes: 1621. Organization: openai. License: Proprietary.

65% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,453 - 1,482

Multilingual14 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #41 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,510
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: chinese. Source rank: #43. Votes: 674. Organization: openai. License: Proprietary.

88.6% percentile inside its fair comparison set

1,510Raw benchmark valueCI 1,488 - 1,532

Text Arena · French

AR · Multilingual · Human

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

Rank #26 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 90.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: french. Source rank: #26. Votes: 216. Organization: openai. License: Proprietary.

90.3% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,456 - 1,537

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #59 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 76.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: japanese. Source rank: #68. Votes: 174. Organization: openai. License: Proprietary.

76.1% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,370 - 1,467

Text Arena · Non English

AR · Multilingual · Human

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

Rank #36 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 90.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: non_english. Source rank: #38. Votes: 5457. Organization: openai. License: Proprietary.

90.7% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,454 - 1,471

Text Arena · Russian

AR · Multilingual · Human

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

Rank #39 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 88.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: russian. Source rank: #43. Votes: 1191. Organization: openai. License: Proprietary.

88.9% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,453 - 1,487

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #77 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 70.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: spanish. Source rank: #86. Votes: 269. Organization: openai. License: Proprietary.

70.7% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,401 - 1,473

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #64 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 82.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: chinese. Source rank: #67. Votes: 674. Organization: openai. License: Proprietary.

82.1% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,465 - 1,509

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #67 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 74.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: french. Source rank: #72. Votes: 216. Organization: openai. License: Proprietary.

74.3% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,413 - 1,494

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #81 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 67.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: japanese. Source rank: #92. Votes: 174. Organization: openai. License: Proprietary.

67.1% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,333 - 1,430

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #60 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 84.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: non_english. Source rank: #66. Votes: 5457. Organization: openai. License: Proprietary.

84.3% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,423 - 1,440

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #60 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 82.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: russian. Source rank: #66. Votes: 1191. Organization: openai. License: Proprietary.

82.7% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,422 - 1,457

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #114 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 56.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: spanish. Source rank: #125. Votes: 269. Organization: openai. License: Proprietary.

56.4% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,373 - 1,445

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #3 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,358
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: chinese. Source rank: #3. Votes: 201. Organization: openai. License: Proprietary.

98.1% percentile inside its fair comparison set

1,358Raw benchmark valueCI 1,316 - 1,400

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #11 · Source label: gpt-6-astra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 90.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-6-astra-max`. Category: chinese. Source rank: #12. Votes: 201. Organization: openai. License: Proprietary.

90.4% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,323 - 1,407

Source links and registry checks

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

Terminal-Bench

Oct 3, 2026

source →

gpt-6-astra-max

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

gpt-6-astra-max

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks