Model profile · OpenAI

GPT-5.5

Closed weightsfrontier · registry tag 2026 frontier revision

Visible tradeoffs

Reads as visible tradeoffs across the resolved source data.

Visible coverage: 61.6%
Verified coverage: 61.6%
Spread: 100%
Last verified: Jun 20, 2026

77%bench fit

textcodevisiondocumentsearch19 aliases46 official source links

Open compare

Data version

Current snapshot.

Data version Jun 20, 2026Model list checked9 providers · 1081 tracked modelsPage refreshed Jul 5, 2026

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

Source-linked scores by benchmark

Each row keeps the benchmark source, source type, raw metric, and percentile inside its fair comparison set.

Visible tradeoffsThis model currently reads as visible tradeoffs across the resolved source data.

Chat / text37 benchmarks77.8%

Intelligence Index

AA · Chat / text · Combined

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

Rank #27 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 35
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

93.4% percentile inside its fair comparison set

35Raw 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 #9 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 45.1%
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

97.3% percentile inside its fair comparison set

45.1%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 #233 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 8.8%
Percentile: 22.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

22.1% percentile inside its fair comparison set

8.8%Raw benchmark value

IFBench

AA · Chat / text · Objective

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

Rank #111 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 46.1%
Percentile: 65.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

65.1% percentile inside its fair comparison set

46.1%Raw benchmark value

Blended 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 #265 · Source label: GPT-5.5 (xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $11.3 /1M tokens
Percentile: 4.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

4.7% percentile inside its fair comparison set

$11.3 /1M tokensRaw 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 #261 · Source label: GPT-5.5 (xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $5 /1M input tokens
Percentile: 6.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

6.9% percentile inside its fair comparison set

$5 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

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

Rank #265 · Source label: GPT-5.5 (xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $30 /1M output tokens
Percentile: 4.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

4.7% percentile inside its fair comparison set

$30 /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 #146 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61 tokens/s
Percentile: 31%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

31% percentile inside its fair comparison set

61 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 #208 · Source label: GPT-5.5 (xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 107.59s
Percentile: 1.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

1.4% percentile inside its fair comparison set

107.59sRaw 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 #207 · Source label: GPT-5.5 (xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 107.59s
Percentile: 1.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

1.9% percentile inside its fair comparison set

107.59sRaw 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 #8 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: overall. Source rank: #10. Votes: 28268. Organization: openai. License: Proprietary.

97.8% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,476 - 1,486

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 #16 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: creative_writing. Source rank: #19. Votes: 4904. Organization: openai. License: Proprietary.

95.4% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,441 - 1,460

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 #12 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: english. Source rank: #14. Votes: 13577. Organization: openai. License: Proprietary.

96.6% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,477 - 1,490

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 #8 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: exclude_ties. Source rank: #10. Votes: 21714. Organization: openai. License: Proprietary.

97.8% percentile inside its fair comparison set

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

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 #11 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: hard_prompts. Source rank: #13. Votes: 18193. Organization: openai. License: Proprietary.

96.9% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,494 - 1,505

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 #14 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: hard_prompts_english. Source rank: #16. Votes: 9194. Organization: openai. License: Proprietary.

96% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,492 - 1,507

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 #9 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: instruction_following. Source rank: #11. Votes: 9331. Organization: openai. License: Proprietary.

97.5% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,471 - 1,486

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 #12 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,486
Percentile: 96.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: longer_query. Source rank: #16. Votes: 12143. Organization: openai. License: Proprietary.

96.4% percentile inside its fair comparison set

1,486Raw benchmark valueCI 1,479 - 1,493

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 #16 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: multi_turn. Source rank: #19. Votes: 4810. Organization: openai. License: Proprietary.

95.4% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,474 - 1,493

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 #11 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: overall. Source rank: #14. Votes: 28268. Organization: openai. License: Proprietary.

96.9% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,463 - 1,473

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 #14 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: creative_writing. Source rank: #16. Votes: 4977. Organization: openai. License: Proprietary.

96% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,442 - 1,461

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 #15 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: english. Source rank: #18. Votes: 13577. Organization: openai. License: Proprietary.

95.7% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,461 - 1,473

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 #13 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,471
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: exclude_ties. Source rank: #16. Votes: 21714. Organization: openai. License: Proprietary.

96.3% percentile inside its fair comparison set

1,471Raw benchmark valueCI 1,465 - 1,477

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 #7 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 98.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: hard_prompts. Source rank: #9. Votes: 18193. Organization: openai. License: Proprietary.

98.2% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,480 - 1,491

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 #11 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: hard_prompts_english. Source rank: #13. Votes: 9194. Organization: openai. License: Proprietary.

96.9% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,474 - 1,489

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 #8 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: instruction_following. Source rank: #10. Votes: 9331. Organization: openai. License: Proprietary.

97.8% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,469 - 1,484

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 #9 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 97.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: longer_query. Source rank: #12. Votes: 12143. Organization: openai. License: Proprietary.

97.4% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,474 - 1,488

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 #15 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,471
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: multi_turn. Source rank: #18. Votes: 4810. Organization: openai. License: Proprietary.

95.7% percentile inside its fair comparison set

1,471Raw benchmark valueCI 1,462 - 1,481

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 #13 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65.7%
Percentile: 88.9%
Last updated: archived
Eligibility: headline eligible

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

88.9% percentile inside its fair comparison set

65.7%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 #3 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 85.6%
Percentile: 98.1%
Last updated: archived
Eligibility: headline eligible

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

98.1% percentile inside its fair comparison set

85.6%Raw benchmark value

Paraphrase

LB · Chat / text · Objective

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

Rank #16 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 63.6%
Percentile: 86.1%
Last updated: archived
Eligibility: headline eligible

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

86.1% percentile inside its fair comparison set

63.6%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 #28 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58.7%
Percentile: 75%
Last updated: archived
Eligibility: headline eligible

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

75% percentile inside its fair comparison set

58.7%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 #26 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 67.2%
Percentile: 76.9%
Last updated: archived
Eligibility: headline eligible

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

76.9% percentile inside its fair comparison set

67.2%Raw benchmark value

Summarize

LB · Chat / text · Objective

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

Rank #10 · Source label: gpt-5.5-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 71.9%
Percentile: 91.7%
Last updated: archived
Eligibility: headline eligible

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

91.7% percentile inside its fair comparison set

71.9%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 #8 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 100%
Percentile: 100%
Last updated: archived
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 #4 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70.7%
Percentile: 97.2%
Last updated: archived
Eligibility: headline eligible

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

97.2% percentile inside its fair comparison set

70.7%Raw benchmark value

Typos

LB · Chat / text · Objective

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

Rank #4 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86%
Percentile: 97.2%
Last updated: archived
Eligibility: headline eligible

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

97.2% percentile inside its fair comparison set

86%Raw benchmark value

Coding27 benchmarks76.2%

Terminal-Bench Hard

AA · Coding · Objective

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

Rank #7 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 49.2%
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

98% percentile inside its fair comparison set

49.2%Raw benchmark value

SciCode

AA · Coding · Objective

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

Rank #14 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.3%
Percentile: 96.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

96.5% percentile inside its fair comparison set

47.3%Raw benchmark value

Coding Index

AA · Coding · Combined

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

Rank #15 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 56
Percentile: 81.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `codingIndex`.

81.3% percentile inside its fair comparison set

56Raw benchmark value

Agentic Index

AA · Coding · Combined

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

Rank #23 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 26
Percentile: 52.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `agenticIndex`.

52.2% percentile inside its fair comparison set

26Raw benchmark value

Code 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 #14 · Source label: gpt-5.5-high (codex-harness)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 82.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high (codex-harness)`. Category: overall. Source rank: #18. Votes: 6726. Organization: openai. License: Proprietary.

82.2% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,475 - 1,492

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 #14 · Source label: gpt-5.5-high (codex-harness)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 82.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high (codex-harness)`. Category: webdev. Source rank: #18. Votes: 6726. Organization: openai. License: Proprietary.

82.2% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,475 - 1,492

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 #10 · Source label: gpt-5.5-high (codex-harness)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 87.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high (codex-harness)`. Category: webdev-html. Source rank: #13. Votes: 847. Organization: openai. License: Proprietary.

87.7% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,491 - 1,533

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 #16 · Source label: gpt-5.5-high (codex-harness)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 74.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high (codex-harness)`. Category: webdev-react. Source rank: #20. Votes: 5865. Organization: openai. License: Proprietary.

74.6% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,465 - 1,483

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-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 45.2%
Percentile: 90.9%
Last updated: recent
Eligibility: headline eligible

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

90.9% percentile inside its fair comparison set

45.2%Raw benchmark valueCI 37% - 53.3%

LiveCodeBench

VALS-AI · Coding · Objective

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

Rank #18 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.3%
Percentile: 81.1%
Last updated: recent
Eligibility: headline eligible

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

81.1% percentile inside its fair comparison set

85.3%Raw benchmark valueCI 83.3% - 87.3%

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 #3 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0.5%
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

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

90% percentile inside its fair comparison set

0.5%Raw benchmark valueCI 0% - 1.5%

SWE-bench Verified

VALS-AI · Coding · Objective

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

Rank #4 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82.6%
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

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

94.4% percentile inside its fair comparison set

82.6%Raw benchmark valueCI 79.3% - 85.9%

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-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 76.4%
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

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

96.3% percentile inside its fair comparison set

76.4%Raw benchmark valueCI 75.1% - 77.7%

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 #4 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69.8%
Percentile: 93.9%
Last updated: recent
Eligibility: headline eligible

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

93.9% percentile inside its fair comparison set

69.8%Raw benchmark valueCI 61% - 78.7%

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 #15 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,519
Percentile: 95.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: coding. Source rank: #19. Votes: 7700. Organization: openai. License: Proprietary.

95.6% percentile inside its fair comparison set

1,519Raw benchmark valueCI 1,511 - 1,527

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 #12 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: coding. Source rank: #16. Votes: 7700. Organization: openai. License: Proprietary.

96.6% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,486 - 1,502

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 #6 · Source label: gpt-5.5-high (codex-harness)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,519
Percentile: 70.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high (codex-harness)`. Category: image_to_webdev. Source rank: #8. Votes: 1965. Organization: openai. License: Proprietary.

70.6% percentile inside its fair comparison set

1,519Raw benchmark valueCI 1,504 - 1,534

HiL-Bench

SL · Coding · Rubric

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

Rank #1 · Source label: GPT-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 29.1%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

100% percentile inside its fair comparison set

29.1%Raw benchmark value

Terminal-Bench 2.0

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-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 82.2%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from the public Terminal-Bench 2.0 verified leaderboard. Collapse policy: highest verified score per canonical model. Selected agent: Codex CLI (0.121.0). Display model: GPT-5.5. Integration method: API. Agent URL: https://developers.openai.com/codex/cli. Reported stderr: 1.135 percentage points.

100% percentile inside its fair comparison set

82.2%Raw benchmark value

Terminal-Bench 2.0

OFF · Coding · Objective

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

Rank #1

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 82.7%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Verified against OpenAI's GPT-5.5 launch page dated April 23, 2026. Uses the published Terminal-Bench 2.0 figure. Checked 2026-04-29. Verification: manual_public_page_verification.

100% percentile inside its fair comparison set

82.7%Raw benchmark value

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 #93 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 16.7%
Percentile: 14.8%
Last updated: archived
Eligibility: headline eligible

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

14.8% percentile inside its fair comparison set

16.7%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 #15 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.6%
Percentile: 87%
Last updated: archived
Eligibility: headline eligible

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

87% percentile inside its fair comparison set

78.6%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 #98 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 5%
Percentile: 10.2%
Last updated: archived
Eligibility: headline eligible

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

10.2% percentile inside its fair comparison set

5%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 #90 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 10%
Percentile: 16.8%
Last updated: archived
Eligibility: headline eligible

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

16.8% percentile inside its fair comparison set

10%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 #92 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 25%
Percentile: 15.7%
Last updated: archived
Eligibility: headline eligible

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

15.7% percentile inside its fair comparison set

25%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 #52 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74.6%
Percentile: 52.8%
Last updated: archived
Eligibility: headline eligible

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

52.8% percentile inside its fair comparison set

74.6%Raw benchmark value

Coding completion

LB · Coding · Objective

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

Rank #4 · Source label: gpt-5.5-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.4%
Percentile: 97.2%
Last updated: archived
Eligibility: headline eligible

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

97.2% percentile inside its fair comparison set

80.4%Raw benchmark value

Reasoning / math / science19 benchmarks81.7%

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 #73 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 12.6%
Percentile: 80.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

80.5% percentile inside its fair comparison set

12.6%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 #88 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 76.8%
Percentile: 76.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

76.7% percentile inside its fair comparison set

76.8%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

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

Rank #37 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1.4%
Percentile: 88.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

88.1% percentile inside its fair comparison set

1.4%Raw benchmark value

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-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 50%
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

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

88.6% percentile inside its fair comparison set

50%Raw benchmark valueCI 40.2% - 59.8%

GPQA Diamond

VALS-AI · Reasoning / math / science · Objective

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

Rank #3 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 93.2%
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

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

98.9% percentile inside its fair comparison set

93.2%Raw benchmark valueCI 90.7% - 95.7%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

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

Rank #10 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.1%
Percentile: 89.9%
Last updated: recent
Eligibility: headline eligible

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

89.9% percentile inside its fair comparison set

88.1%Raw benchmark valueCI 87.5% - 88.8%

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 #9 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: math. Source rank: #11. Votes: 1569. Organization: openai. License: Proprietary.

97.5% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,478 - 1,509

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 #13 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 96.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: math. Source rank: #16. Votes: 1569. Organization: openai. License: Proprietary.

96.2% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,461 - 1,491

Humanity's Last Exam

OFF · Reasoning / math / science · Objective

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

Rank #3

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 41.4%
Percentile: 71.4%
Last updated: recent
Eligibility: headline eligible

Verified against OpenAI's GPT-5.5 launch page dated April 23, 2026. Uses the published no-tools Humanity's Last Exam figure. Checked 2026-04-29. Verification: manual_public_page_verification.

71.4% percentile inside its fair comparison set

41.4%Raw benchmark value

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #72 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 69.8%
Percentile: 34.3%
Last updated: archived
Eligibility: headline eligible

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

34.3% percentile inside its fair comparison set

69.8%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 #8 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86.2%
Percentile: 93.5%
Last updated: archived
Eligibility: headline eligible

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

93.5% percentile inside its fair comparison set

86.2%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 #23 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 94.4%
Last updated: archived
Eligibility: headline eligible

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

94.4% 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 #7 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 85%
Percentile: 94.4%
Last updated: archived
Eligibility: headline eligible

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

94.4% percentile inside its fair comparison set

85%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 #12 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 95.1%
Percentile: 89.8%
Last updated: archived
Eligibility: headline eligible

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

89.8% percentile inside its fair comparison set

95.1%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

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

Rank #109 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

0% percentile inside its fair comparison set

0%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 #20 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.8%
Percentile: 88%
Last updated: archived
Eligibility: headline eligible

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

88% percentile inside its fair comparison set

78.8%Raw benchmark value

Zebra puzzle

LB · Reasoning / math / science · Objective

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

Rank #9 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96%
Percentile: 92.5%
Last updated: archived
Eligibility: headline eligible

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

92.5% percentile inside its fair comparison set

96%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 #25 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 88.9%
Last updated: archived
Eligibility: headline eligible

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

88.9% 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 #14 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72%
Percentile: 88%
Last updated: archived
Eligibility: headline eligible

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

88% percentile inside its fair comparison set

72%Raw benchmark value

Professional reasoning37 benchmarks88.5%

GDPval-AA

AA · Professional reasoning · Rubric

Agentic performance on economically valuable work tasks.

Rank #22 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1,123
Percentile: 54.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gdpvalBreakdown.elo`.

54.3% percentile inside its fair comparison set

1,123Raw benchmark value

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #2 · Source label: GPT-5.5 (xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 37.7%
Percentile: 95.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

95.8% percentile inside its fair comparison set

37.7%Raw benchmark value

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #2 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 40.4%
Percentile: 91.7%
Last updated: recent
Eligibility: headline eligible

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

91.7% percentile inside its fair comparison set

40.4%Raw benchmark valueCI 33.7% - 47.1%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #1 · Source label: openai/gpt-5.5-codex

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 62.6%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

62.6%Raw benchmark valueCI 53.9% - 71.2%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #6 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 60.9%
Percentile: 54.5%
Last updated: recent
Eligibility: headline eligible

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

54.5% percentile inside its fair comparison set

60.9%Raw benchmark valueCI 58.4% - 63.4%

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #3 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68
Percentile: 92.3%
Last updated: recent
Eligibility: headline eligible

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

92.3% percentile inside its fair comparison set

68Raw benchmark valueCI 65 - 71

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #7 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 3.8%
Percentile: 61.5%
Last updated: recent
Eligibility: headline eligible

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

61.5% percentile inside its fair comparison set

3.8%Raw benchmark valueCI 1.4% - 6.1%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #5 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.5%
Percentile: 95.6%
Last updated: recent
Eligibility: headline eligible

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

95.6% percentile inside its fair comparison set

86.5%Raw benchmark valueCI 85.7% - 87.3%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #4 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 51.8%
Percentile: 88%
Last updated: recent
Eligibility: headline eligible

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

88% percentile inside its fair comparison set

51.8%Raw benchmark valueCI 50.7% - 52.8%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #13 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 75%
Percentile: 86.8%
Last updated: recent
Eligibility: headline eligible

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

86.8% percentile inside its fair comparison set

75%Raw benchmark valueCI 73.3% - 76.7%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #15 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 49.1%
Percentile: 72.5%
Last updated: recent
Eligibility: headline eligible

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

72.5% percentile inside its fair comparison set

49.1%Raw benchmark valueCI 44.8% - 53.4%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #4 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.9%
Percentile: 94%
Last updated: recent
Eligibility: headline eligible

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

94% percentile inside its fair comparison set

86.9%Raw benchmark valueCI 83.1% - 90.7%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #6 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,523
Percentile: 98.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: expert. Source rank: #8. Votes: 2590. Organization: openai. License: Proprietary.

98.2% percentile inside its fair comparison set

1,523Raw benchmark valueCI 1,510 - 1,535

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 #7 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: industry_business_and_management_and_financial_operations. Source rank: #9. Votes: 5645. Organization: openai. License: Proprietary.

98.1% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,478 - 1,496

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 #16 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #19. Votes: 6255. Organization: openai. License: Proprietary.

95.4% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,438 - 1,455

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #12 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_legal_and_government. Source rank: #14. Votes: 2182. Organization: openai. License: Proprietary.

96.3% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,472 - 1,499

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 #12 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: industry_life_and_physical_and_social_science. Source rank: #14. Votes: 4805. Organization: openai. License: Proprietary.

96.6% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,487 - 1,505

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #9 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 97.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_mathematical. Source rank: #11. Votes: 1633. Organization: openai. License: Proprietary.

97.4% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,484 - 1,514

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #31 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 89.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: industry_medicine_and_healthcare. Source rank: #39. Votes: 2187. Organization: openai. License: Proprietary.

89.8% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,463 - 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 #14 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_software_and_it_services. Source rank: #17. Votes: 11038. Organization: openai. License: Proprietary.

96% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,502 - 1,516

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 #7 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_writing_and_literature_and_language. Source rank: #9. Votes: 7044. Organization: openai. License: Proprietary.

98.1% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,466 - 1,482

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #4 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: expert. Source rank: #5. Votes: 2590. Organization: openai. License: Proprietary.

98.9% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,500 - 1,525

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 #5 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: industry_business_and_management_and_financial_operations. Source rank: #7. Votes: 5645. Organization: openai. License: Proprietary.

98.7% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,466 - 1,484

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 #12 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #15. Votes: 6255. Organization: openai. License: Proprietary.

96.6% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,436 - 1,453

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 #11 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_legal_and_government. Source rank: #13. Votes: 2182. Organization: openai. License: Proprietary.

96.6% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,466 - 1,494

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 #11 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: industry_life_and_physical_and_social_science. Source rank: #13. Votes: 4805. Organization: openai. License: Proprietary.

96.9% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,473 - 1,491

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #12 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 96.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_mathematical. Source rank: #14. Votes: 1633. Organization: openai. License: Proprietary.

96.4% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,468 - 1,498

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 #42 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 86.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: industry_medicine_and_healthcare. Source rank: #46. Votes: 2187. Organization: openai. License: Proprietary.

86.1% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,439 - 1,466

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 #10 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 97.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_software_and_it_services. Source rank: #13. Votes: 11038. Organization: openai. License: Proprietary.

97.2% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,483 - 1,496

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 #6 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_writing_and_literature_and_language. Source rank: #8. Votes: 7044. Organization: openai. License: Proprietary.

98.5% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,460 - 1,476

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #8 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 51.5%
Percentile: 84.4%
Last updated: recent
Eligibility: headline eligible

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

84.4% percentile inside its fair comparison set

51.5%Raw benchmark valueCI 43.8% - 59.3%

Public Benefits Bench v1

VALS-AI · Professional reasoning · Objective

Answering public-benefits questions across the benefits lifecycle.

Rank #8 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 57.2%
Percentile: 41.7%
Last updated: recent
Eligibility: headline eligible

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

41.7% percentile inside its fair comparison set

57.2%Raw benchmark valueCI 54.7% - 59.8%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #13 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 77%
Percentile: 88.9%
Last updated: archived
Eligibility: headline eligible

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

88.9% percentile inside its fair comparison set

77%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #42 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68.7%
Percentile: 62%
Last updated: archived
Eligibility: headline eligible

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

62% percentile inside its fair comparison set

68.7%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #21 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.2%
Percentile: 81.5%
Last updated: archived
Eligibility: headline eligible

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

81.5% percentile inside its fair comparison set

78.2%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #3 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 52.4%
Percentile: 98.1%
Last updated: archived
Eligibility: headline eligible

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

98.1% percentile inside its fair comparison set

52.4%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #22 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 100%
Percentile: 100%
Last updated: archived
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

Search / tool use4 benchmarks86.3%

Tau2-Bench Telecom

AA · Search / tool use · Objective

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

Rank #98 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 69.3%
Percentile: 68.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

68.6% percentile inside its fair comparison set

69.3%Raw benchmark value

Search Arena

AR · Search / tool use · Human

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

Rank #2 · Source label: gpt-5.5-search

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,225
Percentile: 96.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-search`. Category: overall. Source rank: #2. Votes: 37025. Organization: openai. License: Proprietary.

96.7% percentile inside its fair comparison set

1,225Raw benchmark valueCI 1,219 - 1,231

Search Arena · No Style Control

AR · Search / tool use · Human

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

Rank #2 · Source label: gpt-5.5-search

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,240
Percentile: 96.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-search`. Category: overall. Source rank: #2. Votes: 37025. Organization: openai. License: Proprietary.

96.7% percentile inside its fair comparison set

1,240Raw benchmark valueCI 1,235 - 1,246

BrowseComp

OFF · Search / tool use · Objective

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

Rank #2

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 84.4%
Percentile: 83.3%
Last updated: recent
Eligibility: headline eligible

Verified against OpenAI's GPT-5.5 launch page dated April 23, 2026. Uses the published BrowseComp figure. Checked 2026-04-29. Verification: manual_public_page_verification.

83.3% percentile inside its fair comparison set

84.4%Raw benchmark value

Long context2 benchmarks88.9%

Long Context Reasoning

AA · Long context · Objective

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

Rank #64 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 56.3%
Percentile: 80%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

80% percentile inside its fair comparison set

56.3%Raw benchmark value

CorpFin v2

VALS-AI · Long context · Objective

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

Rank #3 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.4%
Percentile: 97.7%
Last updated: recent
Eligibility: headline eligible

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

97.7% percentile inside its fair comparison set

68.4%Raw benchmark valueCI 66.6% - 70.2%

Vision understanding17 benchmarks92.4%

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 #24 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 71.4%
Percentile: 83%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

83% percentile inside its fair comparison set

71.4%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 #7 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,284
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: overall. Source rank: #9. Votes: 10106. Organization: openai. License: Proprietary.

94.5% percentile inside its fair comparison set

1,284Raw benchmark valueCI 1,275 - 1,292

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 #8 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,277
Percentile: 87.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: creative_writing_vision. Source rank: #11. Votes: 563. Organization: openai. License: Proprietary.

87.3% percentile inside its fair comparison set

1,277Raw benchmark valueCI 1,251 - 1,304

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 #4 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,325
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: diagram. Source rank: #5. Votes: 3025. Organization: openai. License: Proprietary.

95.7% percentile inside its fair comparison set

1,325Raw benchmark valueCI 1,313 - 1,338

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 #7 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,281
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: english. Source rank: #9. Votes: 4748. Organization: openai. License: Proprietary.

94.5% percentile inside its fair comparison set

1,281Raw benchmark valueCI 1,270 - 1,293

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 #1 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,341
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: homework. Source rank: #1. Votes: 1617. Organization: openai. License: Proprietary.

100% percentile inside its fair comparison set

1,341Raw benchmark valueCI 1,325 - 1,357

Vision Arena · Humor

AR · Vision understanding · Human

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

Rank #7 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,277
Percentile: 87.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: humor. Source rank: #9. Votes: 334. Organization: openai. License: Proprietary.

87.8% percentile inside its fair comparison set

1,277Raw benchmark valueCI 1,244 - 1,309

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 #8 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,297
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: ocr. Source rank: #10. Votes: 7300. Organization: openai. License: Proprietary.

90% percentile inside its fair comparison set

1,297Raw benchmark valueCI 1,289 - 1,306

Vision Arena · No Style Control

AR · Vision understanding · Human

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

Rank #9 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,294
Percentile: 92.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: overall. Source rank: #11. Votes: 10106. Organization: openai. License: Proprietary.

92.7% percentile inside its fair comparison set

1,294Raw benchmark valueCI 1,286 - 1,302

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 #7 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,297
Percentile: 89.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: creative_writing_vision. Source rank: #9. Votes: 563. Organization: openai. License: Proprietary.

89.1% percentile inside its fair comparison set

1,297Raw benchmark valueCI 1,271 - 1,323

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 #4 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,326
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: diagram. Source rank: #6. Votes: 3025. Organization: openai. License: Proprietary.

95.7% percentile inside its fair comparison set

1,326Raw benchmark valueCI 1,314 - 1,339

Vision Arena · English · No Style Control

AR · Vision understanding · Human

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

Rank #10 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,292
Percentile: 91.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: english. Source rank: #12. Votes: 4748. Organization: openai. License: Proprietary.

91.7% percentile inside its fair comparison set

1,292Raw benchmark valueCI 1,280 - 1,303

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 #3 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,338
Percentile: 97.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: homework. Source rank: #3. Votes: 1617. Organization: openai. License: Proprietary.

97.1% percentile inside its fair comparison set

1,338Raw benchmark valueCI 1,322 - 1,353

Vision Arena · Humor · No Style Control

AR · Vision understanding · Human

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

Rank #8 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,286
Percentile: 85.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: humor. Source rank: #10. Votes: 334. Organization: openai. License: Proprietary.

85.7% percentile inside its fair comparison set

1,286Raw benchmark valueCI 1,254 - 1,319

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 #9 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,305
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: ocr. Source rank: #11. Votes: 7300. Organization: openai. License: Proprietary.

88.6% percentile inside its fair comparison set

1,305Raw benchmark valueCI 1,297 - 1,314

MMMU Pro

VALS-AI · Vision understanding · Objective

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

Rank #3 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.3%
Percentile: 98.3%
Last updated: recent
Eligibility: headline eligible

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

98.3% percentile inside its fair comparison set

88.3%Raw benchmark valueCI 86.7% - 89.8%

MMMU-Pro

OFF · Vision understanding · Objective

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

Rank #1

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 81.2%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Verified against OpenAI's GPT-5.5 launch page dated April 23, 2026. Uses the published no-tools MMMU Pro figure. Checked 2026-04-29. Verification: manual_public_page_verification.

100% percentile inside its fair comparison set

81.2%Raw benchmark value

Document understanding4 benchmarks84.5%

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 #7 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 75%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: overall. Source rank: #9. Votes: 11789. Organization: openai. License: Proprietary.

75% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,470 - 1,485

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 #5 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 83.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: overall. Source rank: #7. Votes: 11789. Organization: openai. License: Proprietary.

83.3% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,478 - 1,493

Vals Multimodal Index

VALS-AI · Document understanding · Combined

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

Rank #3 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68
Percentile: 89.5%
Last updated: recent
Eligibility: headline eligible

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

89.5% percentile inside its fair comparison set

68Raw benchmark valueCI 65 - 71

MortgageTax

VALS-AI · Document understanding · Objective

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

Rank #7 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.8%
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

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

90% percentile inside its fair comparison set

68.8%Raw benchmark valueCI 67% - 70.5%

Multilingual16 benchmarks96.1%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #3 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,537
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: chinese. Source rank: #5. Votes: 1395. Organization: openai. License: Proprietary.

99.3% percentile inside its fair comparison set

1,537Raw benchmark valueCI 1,520 - 1,555

Text Arena · French

AR · Multilingual · Human

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

Rank #5 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,511
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: french. Source rank: #6. Votes: 1062. Organization: openai. License: Proprietary.

98.1% percentile inside its fair comparison set

1,511Raw benchmark valueCI 1,490 - 1,532

Text Arena · German

AR · Multilingual · Human

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

Rank #8 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 97%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: german. Source rank: #10. Votes: 417. Organization: openai. License: Proprietary.

97% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,454 - 1,515

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #1 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,536
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: japanese. Source rank: #1. Votes: 256. Organization: openai. License: Proprietary.

100% percentile inside its fair comparison set

1,536Raw benchmark valueCI 1,495 - 1,578

Text Arena · Korean

AR · Multilingual · Human

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

Rank #6 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: korean. Source rank: #6. Votes: 392. Organization: openai. License: Proprietary.

97.6% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,433 - 1,496

Text Arena · Russian

AR · Multilingual · Human

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

Rank #11 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 96.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: russian. Source rank: #14. Votes: 3017. Organization: openai. License: Proprietary.

96.5% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,474 - 1,497

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #22 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 90.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: spanish. Source rank: #27. Votes: 868. Organization: openai. License: Proprietary.

90.2% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,440 - 1,483

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #2 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,544
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: chinese. Source rank: #3. Votes: 1395. Organization: openai. License: Proprietary.

99.7% percentile inside its fair comparison set

1,544Raw benchmark valueCI 1,526 - 1,561

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #7 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 97.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: french. Source rank: #9. Votes: 1062. Organization: openai. License: Proprietary.

97.2% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,476 - 1,517

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #10 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 96.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: german. Source rank: #12. Votes: 417. Organization: openai. License: Proprietary.

96.2% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,443 - 1,504

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #1 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,527
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: japanese. Source rank: #1. Votes: 256. Organization: openai. License: Proprietary.

100% percentile inside its fair comparison set

1,527Raw benchmark valueCI 1,486 - 1,569

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #2 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 99.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: korean. Source rank: #2. Votes: 392. Organization: openai. License: Proprietary.

99.5% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,446 - 1,509

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #11 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 96.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: russian. Source rank: #14. Votes: 3017. Organization: openai. License: Proprietary.

96.5% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,464 - 1,487

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #20 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 91.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: spanish. Source rank: #22. Votes: 868. Organization: openai. License: Proprietary.

91.1% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,437 - 1,479

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #11 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,315
Percentile: 87%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: chinese. Source rank: #14. Votes: 682. Organization: openai. License: Proprietary.

87% percentile inside its fair comparison set

1,315Raw benchmark valueCI 1,287 - 1,342

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #7 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,349
Percentile: 92.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: chinese. Source rank: #9. Votes: 682. Organization: openai. License: Proprietary.

92.2% percentile inside its fair comparison set

1,349Raw benchmark valueCI 1,321 - 1,376

Source links and registry checks

official

OpenAI models docs

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Artificial Analysis

Jun 20, 2026

source →

official

LiveBench

Jun 20, 2026

source →

official

Terminal-Bench

Jun 20, 2026

source →

Model profile · OpenAI

GPT-5.5

Closed weightsfrontier · registry tag 2026 frontier revision

Visible tradeoffs

Reads as visible tradeoffs across the resolved source data.

Visible coverage: 61.6%
Verified coverage: 61.6%
Spread: 100%
Last verified: Jun 20, 2026

77%bench fit

textcodevisiondocumentsearch19 aliases46 official source links

Open compare

Data version

Current snapshot.

Data version Jun 20, 2026Model list checked9 providers · 1081 tracked modelsPage refreshed Jul 5, 2026

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

Source-linked scores by benchmark

Each row keeps the benchmark source, source type, raw metric, and percentile inside its fair comparison set.

Visible tradeoffsThis model currently reads as visible tradeoffs across the resolved source data.

Chat / text37 benchmarks77.8%

Intelligence Index

AA · Chat / text · Combined

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

Rank #27 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 35
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

93.4% percentile inside its fair comparison set

35Raw 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 #9 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 45.1%
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

97.3% percentile inside its fair comparison set

45.1%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 #233 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 8.8%
Percentile: 22.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

22.1% percentile inside its fair comparison set

8.8%Raw benchmark value

IFBench

AA · Chat / text · Objective

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

Rank #111 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 46.1%
Percentile: 65.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

65.1% percentile inside its fair comparison set

46.1%Raw benchmark value

Blended 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 #265 · Source label: GPT-5.5 (xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $11.3 /1M tokens
Percentile: 4.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

4.7% percentile inside its fair comparison set

$11.3 /1M tokensRaw 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 #261 · Source label: GPT-5.5 (xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $5 /1M input tokens
Percentile: 6.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

6.9% percentile inside its fair comparison set

$5 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

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

Rank #265 · Source label: GPT-5.5 (xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $30 /1M output tokens
Percentile: 4.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

4.7% percentile inside its fair comparison set

$30 /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 #146 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61 tokens/s
Percentile: 31%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

31% percentile inside its fair comparison set

61 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 #208 · Source label: GPT-5.5 (xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 107.59s
Percentile: 1.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

1.4% percentile inside its fair comparison set

107.59sRaw 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 #207 · Source label: GPT-5.5 (xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 107.59s
Percentile: 1.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

1.9% percentile inside its fair comparison set

107.59sRaw 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 #8 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: overall. Source rank: #10. Votes: 28268. Organization: openai. License: Proprietary.

97.8% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,476 - 1,486

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 #16 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: creative_writing. Source rank: #19. Votes: 4904. Organization: openai. License: Proprietary.

95.4% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,441 - 1,460

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 #12 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: english. Source rank: #14. Votes: 13577. Organization: openai. License: Proprietary.

96.6% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,477 - 1,490

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 #8 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: exclude_ties. Source rank: #10. Votes: 21714. Organization: openai. License: Proprietary.

97.8% percentile inside its fair comparison set

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

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 #11 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: hard_prompts. Source rank: #13. Votes: 18193. Organization: openai. License: Proprietary.

96.9% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,494 - 1,505

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 #14 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: hard_prompts_english. Source rank: #16. Votes: 9194. Organization: openai. License: Proprietary.

96% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,492 - 1,507

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 #9 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: instruction_following. Source rank: #11. Votes: 9331. Organization: openai. License: Proprietary.

97.5% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,471 - 1,486

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 #12 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,486
Percentile: 96.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: longer_query. Source rank: #16. Votes: 12143. Organization: openai. License: Proprietary.

96.4% percentile inside its fair comparison set

1,486Raw benchmark valueCI 1,479 - 1,493

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 #16 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: multi_turn. Source rank: #19. Votes: 4810. Organization: openai. License: Proprietary.

95.4% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,474 - 1,493

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 #11 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: overall. Source rank: #14. Votes: 28268. Organization: openai. License: Proprietary.

96.9% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,463 - 1,473

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 #14 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: creative_writing. Source rank: #16. Votes: 4977. Organization: openai. License: Proprietary.

96% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,442 - 1,461

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 #15 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: english. Source rank: #18. Votes: 13577. Organization: openai. License: Proprietary.

95.7% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,461 - 1,473

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 #13 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,471
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: exclude_ties. Source rank: #16. Votes: 21714. Organization: openai. License: Proprietary.

96.3% percentile inside its fair comparison set

1,471Raw benchmark valueCI 1,465 - 1,477

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 #7 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 98.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: hard_prompts. Source rank: #9. Votes: 18193. Organization: openai. License: Proprietary.

98.2% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,480 - 1,491

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 #11 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: hard_prompts_english. Source rank: #13. Votes: 9194. Organization: openai. License: Proprietary.

96.9% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,474 - 1,489

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 #8 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: instruction_following. Source rank: #10. Votes: 9331. Organization: openai. License: Proprietary.

97.8% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,469 - 1,484

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 #9 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 97.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: longer_query. Source rank: #12. Votes: 12143. Organization: openai. License: Proprietary.

97.4% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,474 - 1,488

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 #15 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,471
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: multi_turn. Source rank: #18. Votes: 4810. Organization: openai. License: Proprietary.

95.7% percentile inside its fair comparison set

1,471Raw benchmark valueCI 1,462 - 1,481

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 #13 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65.7%
Percentile: 88.9%
Last updated: archived
Eligibility: headline eligible

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

88.9% percentile inside its fair comparison set

65.7%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 #3 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 85.6%
Percentile: 98.1%
Last updated: archived
Eligibility: headline eligible

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

98.1% percentile inside its fair comparison set

85.6%Raw benchmark value

Paraphrase

LB · Chat / text · Objective

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

Rank #16 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 63.6%
Percentile: 86.1%
Last updated: archived
Eligibility: headline eligible

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

86.1% percentile inside its fair comparison set

63.6%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 #28 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58.7%
Percentile: 75%
Last updated: archived
Eligibility: headline eligible

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

75% percentile inside its fair comparison set

58.7%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 #26 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 67.2%
Percentile: 76.9%
Last updated: archived
Eligibility: headline eligible

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

76.9% percentile inside its fair comparison set

67.2%Raw benchmark value

Summarize

LB · Chat / text · Objective

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

Rank #10 · Source label: gpt-5.5-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 71.9%
Percentile: 91.7%
Last updated: archived
Eligibility: headline eligible

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

91.7% percentile inside its fair comparison set

71.9%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 #8 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 100%
Percentile: 100%
Last updated: archived
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 #4 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70.7%
Percentile: 97.2%
Last updated: archived
Eligibility: headline eligible

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

97.2% percentile inside its fair comparison set

70.7%Raw benchmark value

Typos

LB · Chat / text · Objective

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

Rank #4 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86%
Percentile: 97.2%
Last updated: archived
Eligibility: headline eligible

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

97.2% percentile inside its fair comparison set

86%Raw benchmark value

Coding27 benchmarks76.2%

Terminal-Bench Hard

AA · Coding · Objective

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

Rank #7 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 49.2%
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

98% percentile inside its fair comparison set

49.2%Raw benchmark value

SciCode

AA · Coding · Objective

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

Rank #14 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.3%
Percentile: 96.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

96.5% percentile inside its fair comparison set

47.3%Raw benchmark value

Coding Index

AA · Coding · Combined

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

Rank #15 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 56
Percentile: 81.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `codingIndex`.

81.3% percentile inside its fair comparison set

56Raw benchmark value

Agentic Index

AA · Coding · Combined

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

Rank #23 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 26
Percentile: 52.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `agenticIndex`.

52.2% percentile inside its fair comparison set

26Raw benchmark value

Code 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 #14 · Source label: gpt-5.5-high (codex-harness)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 82.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high (codex-harness)`. Category: overall. Source rank: #18. Votes: 6726. Organization: openai. License: Proprietary.

82.2% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,475 - 1,492

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 #14 · Source label: gpt-5.5-high (codex-harness)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 82.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high (codex-harness)`. Category: webdev. Source rank: #18. Votes: 6726. Organization: openai. License: Proprietary.

82.2% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,475 - 1,492

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 #10 · Source label: gpt-5.5-high (codex-harness)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 87.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high (codex-harness)`. Category: webdev-html. Source rank: #13. Votes: 847. Organization: openai. License: Proprietary.

87.7% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,491 - 1,533

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 #16 · Source label: gpt-5.5-high (codex-harness)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 74.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high (codex-harness)`. Category: webdev-react. Source rank: #20. Votes: 5865. Organization: openai. License: Proprietary.

74.6% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,465 - 1,483

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-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 45.2%
Percentile: 90.9%
Last updated: recent
Eligibility: headline eligible

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

90.9% percentile inside its fair comparison set

45.2%Raw benchmark valueCI 37% - 53.3%

LiveCodeBench

VALS-AI · Coding · Objective

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

Rank #18 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.3%
Percentile: 81.1%
Last updated: recent
Eligibility: headline eligible

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

81.1% percentile inside its fair comparison set

85.3%Raw benchmark valueCI 83.3% - 87.3%

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 #3 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0.5%
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

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

90% percentile inside its fair comparison set

0.5%Raw benchmark valueCI 0% - 1.5%

SWE-bench Verified

VALS-AI · Coding · Objective

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

Rank #4 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82.6%
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

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

94.4% percentile inside its fair comparison set

82.6%Raw benchmark valueCI 79.3% - 85.9%

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-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 76.4%
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

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

96.3% percentile inside its fair comparison set

76.4%Raw benchmark valueCI 75.1% - 77.7%

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 #4 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69.8%
Percentile: 93.9%
Last updated: recent
Eligibility: headline eligible

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

93.9% percentile inside its fair comparison set

69.8%Raw benchmark valueCI 61% - 78.7%

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 #15 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,519
Percentile: 95.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: coding. Source rank: #19. Votes: 7700. Organization: openai. License: Proprietary.

95.6% percentile inside its fair comparison set

1,519Raw benchmark valueCI 1,511 - 1,527

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 #12 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: coding. Source rank: #16. Votes: 7700. Organization: openai. License: Proprietary.

96.6% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,486 - 1,502

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 #6 · Source label: gpt-5.5-high (codex-harness)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,519
Percentile: 70.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high (codex-harness)`. Category: image_to_webdev. Source rank: #8. Votes: 1965. Organization: openai. License: Proprietary.

70.6% percentile inside its fair comparison set

1,519Raw benchmark valueCI 1,504 - 1,534

HiL-Bench

SL · Coding · Rubric

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

Rank #1 · Source label: GPT-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 29.1%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

100% percentile inside its fair comparison set

29.1%Raw benchmark value

Terminal-Bench 2.0

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-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 82.2%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

100% percentile inside its fair comparison set

82.2%Raw benchmark value

Terminal-Bench 2.0

OFF · Coding · Objective

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

Rank #1

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 82.7%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Verified against OpenAI's GPT-5.5 launch page dated April 23, 2026. Uses the published Terminal-Bench 2.0 figure. Checked 2026-04-29. Verification: manual_public_page_verification.

100% percentile inside its fair comparison set

82.7%Raw benchmark value

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 #93 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 16.7%
Percentile: 14.8%
Last updated: archived
Eligibility: headline eligible

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

14.8% percentile inside its fair comparison set

16.7%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 #15 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.6%
Percentile: 87%
Last updated: archived
Eligibility: headline eligible

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

87% percentile inside its fair comparison set

78.6%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 #98 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 5%
Percentile: 10.2%
Last updated: archived
Eligibility: headline eligible

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

10.2% percentile inside its fair comparison set

5%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 #90 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 10%
Percentile: 16.8%
Last updated: archived
Eligibility: headline eligible

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

16.8% percentile inside its fair comparison set

10%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 #92 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 25%
Percentile: 15.7%
Last updated: archived
Eligibility: headline eligible

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

15.7% percentile inside its fair comparison set

25%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 #52 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74.6%
Percentile: 52.8%
Last updated: archived
Eligibility: headline eligible

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

52.8% percentile inside its fair comparison set

74.6%Raw benchmark value

Coding completion

LB · Coding · Objective

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

Rank #4 · Source label: gpt-5.5-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.4%
Percentile: 97.2%
Last updated: archived
Eligibility: headline eligible

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

97.2% percentile inside its fair comparison set

80.4%Raw benchmark value

Reasoning / math / science19 benchmarks81.7%

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 #73 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 12.6%
Percentile: 80.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

80.5% percentile inside its fair comparison set

12.6%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 #88 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 76.8%
Percentile: 76.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

76.7% percentile inside its fair comparison set

76.8%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

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

Rank #37 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1.4%
Percentile: 88.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

88.1% percentile inside its fair comparison set

1.4%Raw benchmark value

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-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 50%
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

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

88.6% percentile inside its fair comparison set

50%Raw benchmark valueCI 40.2% - 59.8%

GPQA Diamond

VALS-AI · Reasoning / math / science · Objective

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

Rank #3 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 93.2%
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

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

98.9% percentile inside its fair comparison set

93.2%Raw benchmark valueCI 90.7% - 95.7%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

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

Rank #10 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.1%
Percentile: 89.9%
Last updated: recent
Eligibility: headline eligible

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

89.9% percentile inside its fair comparison set

88.1%Raw benchmark valueCI 87.5% - 88.8%

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 #9 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: math. Source rank: #11. Votes: 1569. Organization: openai. License: Proprietary.

97.5% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,478 - 1,509

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 #13 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 96.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: math. Source rank: #16. Votes: 1569. Organization: openai. License: Proprietary.

96.2% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,461 - 1,491

Humanity's Last Exam

OFF · Reasoning / math / science · Objective

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

Rank #3

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 41.4%
Percentile: 71.4%
Last updated: recent
Eligibility: headline eligible

Verified against OpenAI's GPT-5.5 launch page dated April 23, 2026. Uses the published no-tools Humanity's Last Exam figure. Checked 2026-04-29. Verification: manual_public_page_verification.

71.4% percentile inside its fair comparison set

41.4%Raw benchmark value

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #72 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 69.8%
Percentile: 34.3%
Last updated: archived
Eligibility: headline eligible

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

34.3% percentile inside its fair comparison set

69.8%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 #8 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86.2%
Percentile: 93.5%
Last updated: archived
Eligibility: headline eligible

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

93.5% percentile inside its fair comparison set

86.2%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 #23 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 94.4%
Last updated: archived
Eligibility: headline eligible

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

94.4% 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 #7 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 85%
Percentile: 94.4%
Last updated: archived
Eligibility: headline eligible

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

94.4% percentile inside its fair comparison set

85%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 #12 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 95.1%
Percentile: 89.8%
Last updated: archived
Eligibility: headline eligible

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

89.8% percentile inside its fair comparison set

95.1%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

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

Rank #109 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

0% percentile inside its fair comparison set

0%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 #20 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.8%
Percentile: 88%
Last updated: archived
Eligibility: headline eligible

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

88% percentile inside its fair comparison set

78.8%Raw benchmark value

Zebra puzzle

LB · Reasoning / math / science · Objective

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

Rank #9 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96%
Percentile: 92.5%
Last updated: archived
Eligibility: headline eligible

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

92.5% percentile inside its fair comparison set

96%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 #25 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 88.9%
Last updated: archived
Eligibility: headline eligible

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

88.9% 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 #14 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72%
Percentile: 88%
Last updated: archived
Eligibility: headline eligible

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

88% percentile inside its fair comparison set

72%Raw benchmark value

Professional reasoning37 benchmarks88.5%

GDPval-AA

AA · Professional reasoning · Rubric

Agentic performance on economically valuable work tasks.

Rank #22 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1,123
Percentile: 54.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gdpvalBreakdown.elo`.

54.3% percentile inside its fair comparison set

1,123Raw benchmark value

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #2 · Source label: GPT-5.5 (xhigh)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 37.7%
Percentile: 95.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

95.8% percentile inside its fair comparison set

37.7%Raw benchmark value

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #2 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 40.4%
Percentile: 91.7%
Last updated: recent
Eligibility: headline eligible

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

91.7% percentile inside its fair comparison set

40.4%Raw benchmark valueCI 33.7% - 47.1%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #1 · Source label: openai/gpt-5.5-codex

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 62.6%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

62.6%Raw benchmark valueCI 53.9% - 71.2%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #6 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 60.9%
Percentile: 54.5%
Last updated: recent
Eligibility: headline eligible

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

54.5% percentile inside its fair comparison set

60.9%Raw benchmark valueCI 58.4% - 63.4%

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #3 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68
Percentile: 92.3%
Last updated: recent
Eligibility: headline eligible

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

92.3% percentile inside its fair comparison set

68Raw benchmark valueCI 65 - 71

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #7 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 3.8%
Percentile: 61.5%
Last updated: recent
Eligibility: headline eligible

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

61.5% percentile inside its fair comparison set

3.8%Raw benchmark valueCI 1.4% - 6.1%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #5 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.5%
Percentile: 95.6%
Last updated: recent
Eligibility: headline eligible

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

95.6% percentile inside its fair comparison set

86.5%Raw benchmark valueCI 85.7% - 87.3%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #4 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 51.8%
Percentile: 88%
Last updated: recent
Eligibility: headline eligible

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

88% percentile inside its fair comparison set

51.8%Raw benchmark valueCI 50.7% - 52.8%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #13 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 75%
Percentile: 86.8%
Last updated: recent
Eligibility: headline eligible

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

86.8% percentile inside its fair comparison set

75%Raw benchmark valueCI 73.3% - 76.7%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #15 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 49.1%
Percentile: 72.5%
Last updated: recent
Eligibility: headline eligible

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

72.5% percentile inside its fair comparison set

49.1%Raw benchmark valueCI 44.8% - 53.4%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #4 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.9%
Percentile: 94%
Last updated: recent
Eligibility: headline eligible

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

94% percentile inside its fair comparison set

86.9%Raw benchmark valueCI 83.1% - 90.7%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #6 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,523
Percentile: 98.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: expert. Source rank: #8. Votes: 2590. Organization: openai. License: Proprietary.

98.2% percentile inside its fair comparison set

1,523Raw benchmark valueCI 1,510 - 1,535

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 #7 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: industry_business_and_management_and_financial_operations. Source rank: #9. Votes: 5645. Organization: openai. License: Proprietary.

98.1% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,478 - 1,496

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 #16 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #19. Votes: 6255. Organization: openai. License: Proprietary.

95.4% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,438 - 1,455

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #12 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_legal_and_government. Source rank: #14. Votes: 2182. Organization: openai. License: Proprietary.

96.3% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,472 - 1,499

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 #12 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: industry_life_and_physical_and_social_science. Source rank: #14. Votes: 4805. Organization: openai. License: Proprietary.

96.6% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,487 - 1,505

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #9 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 97.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_mathematical. Source rank: #11. Votes: 1633. Organization: openai. License: Proprietary.

97.4% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,484 - 1,514

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #31 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 89.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: industry_medicine_and_healthcare. Source rank: #39. Votes: 2187. Organization: openai. License: Proprietary.

89.8% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,463 - 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 #14 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_software_and_it_services. Source rank: #17. Votes: 11038. Organization: openai. License: Proprietary.

96% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,502 - 1,516

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 #7 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_writing_and_literature_and_language. Source rank: #9. Votes: 7044. Organization: openai. License: Proprietary.

98.1% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,466 - 1,482

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #4 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: expert. Source rank: #5. Votes: 2590. Organization: openai. License: Proprietary.

98.9% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,500 - 1,525

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 #5 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: industry_business_and_management_and_financial_operations. Source rank: #7. Votes: 5645. Organization: openai. License: Proprietary.

98.7% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,466 - 1,484

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 #12 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #15. Votes: 6255. Organization: openai. License: Proprietary.

96.6% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,436 - 1,453

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 #11 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_legal_and_government. Source rank: #13. Votes: 2182. Organization: openai. License: Proprietary.

96.6% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,466 - 1,494

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 #11 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: industry_life_and_physical_and_social_science. Source rank: #13. Votes: 4805. Organization: openai. License: Proprietary.

96.9% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,473 - 1,491

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #12 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 96.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_mathematical. Source rank: #14. Votes: 1633. Organization: openai. License: Proprietary.

96.4% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,468 - 1,498

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 #42 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 86.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: industry_medicine_and_healthcare. Source rank: #46. Votes: 2187. Organization: openai. License: Proprietary.

86.1% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,439 - 1,466

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 #10 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 97.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_software_and_it_services. Source rank: #13. Votes: 11038. Organization: openai. License: Proprietary.

97.2% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,483 - 1,496

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 #6 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: industry_writing_and_literature_and_language. Source rank: #8. Votes: 7044. Organization: openai. License: Proprietary.

98.5% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,460 - 1,476

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #8 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 51.5%
Percentile: 84.4%
Last updated: recent
Eligibility: headline eligible

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

84.4% percentile inside its fair comparison set

51.5%Raw benchmark valueCI 43.8% - 59.3%

Public Benefits Bench v1

VALS-AI · Professional reasoning · Objective

Answering public-benefits questions across the benefits lifecycle.

Rank #8 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 57.2%
Percentile: 41.7%
Last updated: recent
Eligibility: headline eligible

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

41.7% percentile inside its fair comparison set

57.2%Raw benchmark valueCI 54.7% - 59.8%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #13 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 77%
Percentile: 88.9%
Last updated: archived
Eligibility: headline eligible

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

88.9% percentile inside its fair comparison set

77%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #42 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68.7%
Percentile: 62%
Last updated: archived
Eligibility: headline eligible

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

62% percentile inside its fair comparison set

68.7%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #21 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.2%
Percentile: 81.5%
Last updated: archived
Eligibility: headline eligible

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

81.5% percentile inside its fair comparison set

78.2%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #3 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 52.4%
Percentile: 98.1%
Last updated: archived
Eligibility: headline eligible

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

98.1% percentile inside its fair comparison set

52.4%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #22 · Source label: gpt-5.5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 100%
Percentile: 100%
Last updated: archived
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

Search / tool use4 benchmarks86.3%

Tau2-Bench Telecom

AA · Search / tool use · Objective

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

Rank #98 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 69.3%
Percentile: 68.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

68.6% percentile inside its fair comparison set

69.3%Raw benchmark value

Search Arena

AR · Search / tool use · Human

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

Rank #2 · Source label: gpt-5.5-search

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,225
Percentile: 96.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-search`. Category: overall. Source rank: #2. Votes: 37025. Organization: openai. License: Proprietary.

96.7% percentile inside its fair comparison set

1,225Raw benchmark valueCI 1,219 - 1,231

Search Arena · No Style Control

AR · Search / tool use · Human

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

Rank #2 · Source label: gpt-5.5-search

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,240
Percentile: 96.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-search`. Category: overall. Source rank: #2. Votes: 37025. Organization: openai. License: Proprietary.

96.7% percentile inside its fair comparison set

1,240Raw benchmark valueCI 1,235 - 1,246

BrowseComp

OFF · Search / tool use · Objective

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

Rank #2

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 84.4%
Percentile: 83.3%
Last updated: recent
Eligibility: headline eligible

Verified against OpenAI's GPT-5.5 launch page dated April 23, 2026. Uses the published BrowseComp figure. Checked 2026-04-29. Verification: manual_public_page_verification.

83.3% percentile inside its fair comparison set

84.4%Raw benchmark value

Long context2 benchmarks88.9%

Long Context Reasoning

AA · Long context · Objective

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

Rank #64 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 56.3%
Percentile: 80%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

80% percentile inside its fair comparison set

56.3%Raw benchmark value

CorpFin v2

VALS-AI · Long context · Objective

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

Rank #3 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.4%
Percentile: 97.7%
Last updated: recent
Eligibility: headline eligible

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

97.7% percentile inside its fair comparison set

68.4%Raw benchmark valueCI 66.6% - 70.2%

Vision understanding17 benchmarks92.4%

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 #24 · Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 71.4%
Percentile: 83%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

83% percentile inside its fair comparison set

71.4%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 #7 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,284
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: overall. Source rank: #9. Votes: 10106. Organization: openai. License: Proprietary.

94.5% percentile inside its fair comparison set

1,284Raw benchmark valueCI 1,275 - 1,292

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 #8 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,277
Percentile: 87.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: creative_writing_vision. Source rank: #11. Votes: 563. Organization: openai. License: Proprietary.

87.3% percentile inside its fair comparison set

1,277Raw benchmark valueCI 1,251 - 1,304

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 #4 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,325
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: diagram. Source rank: #5. Votes: 3025. Organization: openai. License: Proprietary.

95.7% percentile inside its fair comparison set

1,325Raw benchmark valueCI 1,313 - 1,338

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 #7 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,281
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: english. Source rank: #9. Votes: 4748. Organization: openai. License: Proprietary.

94.5% percentile inside its fair comparison set

1,281Raw benchmark valueCI 1,270 - 1,293

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 #1 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,341
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: homework. Source rank: #1. Votes: 1617. Organization: openai. License: Proprietary.

100% percentile inside its fair comparison set

1,341Raw benchmark valueCI 1,325 - 1,357

Vision Arena · Humor

AR · Vision understanding · Human

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

Rank #7 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,277
Percentile: 87.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: humor. Source rank: #9. Votes: 334. Organization: openai. License: Proprietary.

87.8% percentile inside its fair comparison set

1,277Raw benchmark valueCI 1,244 - 1,309

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 #8 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,297
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: ocr. Source rank: #10. Votes: 7300. Organization: openai. License: Proprietary.

90% percentile inside its fair comparison set

1,297Raw benchmark valueCI 1,289 - 1,306

Vision Arena · No Style Control

AR · Vision understanding · Human

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

Rank #9 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,294
Percentile: 92.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: overall. Source rank: #11. Votes: 10106. Organization: openai. License: Proprietary.

92.7% percentile inside its fair comparison set

1,294Raw benchmark valueCI 1,286 - 1,302

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 #7 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,297
Percentile: 89.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: creative_writing_vision. Source rank: #9. Votes: 563. Organization: openai. License: Proprietary.

89.1% percentile inside its fair comparison set

1,297Raw benchmark valueCI 1,271 - 1,323

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 #4 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,326
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: diagram. Source rank: #6. Votes: 3025. Organization: openai. License: Proprietary.

95.7% percentile inside its fair comparison set

1,326Raw benchmark valueCI 1,314 - 1,339

Vision Arena · English · No Style Control

AR · Vision understanding · Human

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

Rank #10 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,292
Percentile: 91.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: english. Source rank: #12. Votes: 4748. Organization: openai. License: Proprietary.

91.7% percentile inside its fair comparison set

1,292Raw benchmark valueCI 1,280 - 1,303

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 #3 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,338
Percentile: 97.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: homework. Source rank: #3. Votes: 1617. Organization: openai. License: Proprietary.

97.1% percentile inside its fair comparison set

1,338Raw benchmark valueCI 1,322 - 1,353

Vision Arena · Humor · No Style Control

AR · Vision understanding · Human

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

Rank #8 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,286
Percentile: 85.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: humor. Source rank: #10. Votes: 334. Organization: openai. License: Proprietary.

85.7% percentile inside its fair comparison set

1,286Raw benchmark valueCI 1,254 - 1,319

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 #9 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,305
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: ocr. Source rank: #11. Votes: 7300. Organization: openai. License: Proprietary.

88.6% percentile inside its fair comparison set

1,305Raw benchmark valueCI 1,297 - 1,314

MMMU Pro

VALS-AI · Vision understanding · Objective

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

Rank #3 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.3%
Percentile: 98.3%
Last updated: recent
Eligibility: headline eligible

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

98.3% percentile inside its fair comparison set

88.3%Raw benchmark valueCI 86.7% - 89.8%

MMMU-Pro

OFF · Vision understanding · Objective

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

Rank #1

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 81.2%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Verified against OpenAI's GPT-5.5 launch page dated April 23, 2026. Uses the published no-tools MMMU Pro figure. Checked 2026-04-29. Verification: manual_public_page_verification.

100% percentile inside its fair comparison set

81.2%Raw benchmark value

Document understanding4 benchmarks84.5%

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 #7 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 75%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: overall. Source rank: #9. Votes: 11789. Organization: openai. License: Proprietary.

75% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,470 - 1,485

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 #5 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 83.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: overall. Source rank: #7. Votes: 11789. Organization: openai. License: Proprietary.

83.3% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,478 - 1,493

Vals Multimodal Index

VALS-AI · Document understanding · Combined

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

Rank #3 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68
Percentile: 89.5%
Last updated: recent
Eligibility: headline eligible

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

89.5% percentile inside its fair comparison set

68Raw benchmark valueCI 65 - 71

MortgageTax

VALS-AI · Document understanding · Objective

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

Rank #7 · Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.8%
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

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

90% percentile inside its fair comparison set

68.8%Raw benchmark valueCI 67% - 70.5%

Multilingual16 benchmarks96.1%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #3 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,537
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: chinese. Source rank: #5. Votes: 1395. Organization: openai. License: Proprietary.

99.3% percentile inside its fair comparison set

1,537Raw benchmark valueCI 1,520 - 1,555

Text Arena · French

AR · Multilingual · Human

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

Rank #5 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,511
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: french. Source rank: #6. Votes: 1062. Organization: openai. License: Proprietary.

98.1% percentile inside its fair comparison set

1,511Raw benchmark valueCI 1,490 - 1,532

Text Arena · German

AR · Multilingual · Human

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

Rank #8 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 97%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: german. Source rank: #10. Votes: 417. Organization: openai. License: Proprietary.

97% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,454 - 1,515

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #1 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,536
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: japanese. Source rank: #1. Votes: 256. Organization: openai. License: Proprietary.

100% percentile inside its fair comparison set

1,536Raw benchmark valueCI 1,495 - 1,578

Text Arena · Korean

AR · Multilingual · Human

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

Rank #6 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: korean. Source rank: #6. Votes: 392. Organization: openai. License: Proprietary.

97.6% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,433 - 1,496

Text Arena · Russian

AR · Multilingual · Human

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

Rank #11 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 96.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: russian. Source rank: #14. Votes: 3017. Organization: openai. License: Proprietary.

96.5% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,474 - 1,497

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #22 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 90.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: spanish. Source rank: #27. Votes: 868. Organization: openai. License: Proprietary.

90.2% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,440 - 1,483

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #2 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,544
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: chinese. Source rank: #3. Votes: 1395. Organization: openai. License: Proprietary.

99.7% percentile inside its fair comparison set

1,544Raw benchmark valueCI 1,526 - 1,561

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #7 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 97.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: french. Source rank: #9. Votes: 1062. Organization: openai. License: Proprietary.

97.2% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,476 - 1,517

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #10 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 96.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: german. Source rank: #12. Votes: 417. Organization: openai. License: Proprietary.

96.2% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,443 - 1,504

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #1 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,527
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: japanese. Source rank: #1. Votes: 256. Organization: openai. License: Proprietary.

100% percentile inside its fair comparison set

1,527Raw benchmark valueCI 1,486 - 1,569

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #2 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 99.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: korean. Source rank: #2. Votes: 392. Organization: openai. License: Proprietary.

99.5% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,446 - 1,509

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #11 · Source label: gpt-5.5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 96.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5-high`. Category: russian. Source rank: #14. Votes: 3017. Organization: openai. License: Proprietary.

96.5% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,464 - 1,487

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #20 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 91.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: spanish. Source rank: #22. Votes: 868. Organization: openai. License: Proprietary.

91.1% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,437 - 1,479

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #11 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,315
Percentile: 87%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: chinese. Source rank: #14. Votes: 682. Organization: openai. License: Proprietary.

87% percentile inside its fair comparison set

1,315Raw benchmark valueCI 1,287 - 1,342

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #7 · Source label: gpt-5.5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,349
Percentile: 92.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.5`. Category: chinese. Source rank: #9. Votes: 682. Organization: openai. License: Proprietary.

92.2% percentile inside its fair comparison set

1,349Raw benchmark valueCI 1,321 - 1,376

Source links and registry checks

official

OpenAI models docs

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Artificial Analysis

Jun 20, 2026

source →

official

LiveBench

Jun 20, 2026

source →

official

Terminal-Bench

Jun 20, 2026

source →

GPT-5.5

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

GPT-5.5

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks