Model profile · OpenAI

GPT-5

Closed weightsfrontier · registry tag 2026 frontier

Visible tradeoffs

Reads as visible tradeoffs across the resolved source data.

Visible coverage: 55.5%
Verified coverage: 55.5%
Spread: 97.1%
Last verified: Jun 20, 2026

65%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 / text38 benchmarks67.6%

Intelligence Index

AA · Chat / text · Combined

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

Rank #162 · Source label: GPT-5 (ChatGPT)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 15
Percentile: 59.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

59.2% percentile inside its fair comparison set

15Raw 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 #36 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 28.1%
Percentile: 88.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

88.3% percentile inside its fair comparison set

28.1%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 #162 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 13.8%
Percentile: 46%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

46% percentile inside its fair comparison set

13.8%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 #121 · Source label: GPT-5 (ChatGPT)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 45%
Percentile: 61.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

61.9% percentile inside its fair comparison set

45%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 #230 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $3.4 /1M tokens
Percentile: 18.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

18.1% percentile inside its fair comparison set

$3.4 /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 #212 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.3 /1M input tokens
Percentile: 24.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

24.6% percentile inside its fair comparison set

$1.3 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

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

Rank #239 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $10 /1M output tokens
Percentile: 15.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

15.2% percentile inside its fair comparison set

$10 /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 #118 · Source label: GPT-5 (low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 86.4 tokens/s
Percentile: 44.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

44.3% percentile inside its fair comparison set

86.4 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 #205 · Source label: GPT-5 (high)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 90.42s
Percentile: 2.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

2.9% percentile inside its fair comparison set

90.42sRaw 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 #203 · Source label: GPT-5 (high)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 90.42s
Percentile: 3.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

3.8% percentile inside its fair comparison set

90.42sRaw benchmark value

Openness Index

AA · Chat / text · Combined

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

Rank #173 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 6
Percentile: 7.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `opennessBreakdown.opennessIndex`.

7.5% percentile inside its fair comparison set

6Raw 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 #36 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,449
Percentile: 89.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: overall. Source rank: #47. Votes: 33125. Organization: openai. License: Proprietary.

89.2% percentile inside its fair comparison set

1,449Raw benchmark valueCI 1,444 - 1,453

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 #51 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 84.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: creative_writing. Source rank: #65. Votes: 5151. Organization: openai. License: Proprietary.

84.5% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,397 - 1,415

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 #45 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 86.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: english. Source rank: #57. Votes: 15538. Organization: openai. License: Proprietary.

86.5% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,445 - 1,457

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 #34 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 89.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: exclude_ties. Source rank: #45. Votes: 25433. Organization: openai. License: Proprietary.

89.8% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,446 - 1,458

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 #35 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 89.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: hard_prompts. Source rank: #47. Votes: 20701. Organization: openai. License: Proprietary.

89.5% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,466 - 1,477

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 #42 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 87.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: hard_prompts_english. Source rank: #54. Votes: 10150. Organization: openai. License: Proprietary.

87.3% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,462 - 1,476

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 #42 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 87.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: instruction_following. Source rank: #53. Votes: 10643. Organization: openai. License: Proprietary.

87.4% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,427 - 1,441

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 #36 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 88.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: longer_query. Source rank: #47. Votes: 12595. Organization: openai. License: Proprietary.

88.5% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,449 - 1,462

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 #31 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 90.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: multi_turn. Source rank: #42. Votes: 6201. Organization: openai. License: Proprietary.

90.7% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,458 - 1,475

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 #89 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 72.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: overall. Source rank: #107. Votes: 31928. Organization: openai. License: Proprietary.

72.9% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,401 - 1,410

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 #84 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,368
Percentile: 74.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: creative_writing. Source rank: #104. Votes: 4016. Organization: openai. License: Proprietary.

74.3% percentile inside its fair comparison set

1,368Raw benchmark valueCI 1,358 - 1,377

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 #96 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 70.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: english. Source rank: #115. Votes: 15139. Organization: openai. License: Proprietary.

70.8% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,403 - 1,414

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 #91 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 72.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: exclude_ties. Source rank: #109. Votes: 23604. Organization: openai. License: Proprietary.

72.3% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,380 - 1,392

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 #85 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 74.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: hard_prompts. Source rank: #102. Votes: 14987. Organization: openai. License: Proprietary.

74.2% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,409 - 1,421

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 #84 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,421
Percentile: 74.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: hard_prompts_english. Source rank: #101. Votes: 7688. Organization: openai. License: Proprietary.

74.4% percentile inside its fair comparison set

1,421Raw benchmark valueCI 1,413 - 1,428

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 #86 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,388
Percentile: 73.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: instruction_following. Source rank: #104. Votes: 8266. Organization: openai. License: Proprietary.

73.8% percentile inside its fair comparison set

1,388Raw benchmark valueCI 1,381 - 1,395

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 #87 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 71.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: longer_query. Source rank: #107. Votes: 6729. Organization: openai. License: Proprietary.

71.7% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,393 - 1,408

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 #57 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,426
Percentile: 82.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: multi_turn. Source rank: #71. Votes: 5796. Organization: openai. License: Proprietary.

82.7% percentile inside its fair comparison set

1,426Raw benchmark valueCI 1,418 - 1,434

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 #18 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64%
Percentile: 84.3%
Last updated: archived
Eligibility: headline eligible

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

84.3% percentile inside its fair comparison set

64%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 #14 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.7%
Percentile: 88%
Last updated: archived
Eligibility: headline eligible

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

88% percentile inside its fair comparison set

80.7%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 #27 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 61.4%
Percentile: 75.9%
Last updated: archived
Eligibility: headline eligible

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

75.9% percentile inside its fair comparison set

61.4%Raw benchmark value

Simplify

LB · Chat / text · Objective

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

Rank #13 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62.2%
Percentile: 88.9%
Last updated: archived
Eligibility: headline eligible

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

88.9% percentile inside its fair comparison set

62.2%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 #25 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 67.3%
Percentile: 78.7%
Last updated: archived
Eligibility: headline eligible

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

78.7% percentile inside its fair comparison set

67.3%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 #27 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65%
Percentile: 75.9%
Last updated: archived
Eligibility: headline eligible

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

75.9% percentile inside its fair comparison set

65%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 #22 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 81.5%
Last updated: archived
Eligibility: headline eligible

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

81.5% percentile inside its fair comparison set

98%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 #14 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64.1%
Percentile: 88%
Last updated: archived
Eligibility: headline eligible

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

88% percentile inside its fair comparison set

64.1%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 #34 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80%
Percentile: 75.7%
Last updated: archived
Eligibility: headline eligible

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

75.7% percentile inside its fair comparison set

80%Raw benchmark value

Coding19 benchmarks61.6%

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 #133 · Source label: GPT-5 (ChatGPT)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 12.9%
Percentile: 56.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

56.3% percentile inside its fair comparison set

12.9%Raw benchmark value

SciCode

AA · Coding · Objective

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

Rank #85 · Source label: GPT-5 (ChatGPT)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 37.8%
Percentile: 77.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

77.2% percentile inside its fair comparison set

37.8%Raw 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 #35 · Source label: gpt-5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,394
Percentile: 53.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-medium`. Category: overall. Source rank: #43. Votes: 3755. Organization: openai. License: Proprietary.

53.4% percentile inside its fair comparison set

1,394Raw benchmark valueCI 1,382 - 1,407

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 #35 · Source label: gpt-5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,394
Percentile: 53.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-medium`. Category: webdev. Source rank: #43. Votes: 3755. Organization: openai. License: Proprietary.

53.4% percentile inside its fair comparison set

1,394Raw benchmark valueCI 1,382 - 1,407

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 #35 · Source label: gpt-5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 53.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-medium`. Category: webdev-html. Source rank: #43. Votes: 3755. Organization: openai. License: Proprietary.

53.4% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,388 - 1,416

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 #15 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.9%
Percentile: 84.4%
Last updated: recent
Eligibility: headline eligible

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

84.4% percentile inside its fair comparison set

85.9%Raw benchmark valueCI 84% - 87.8%

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 #40 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69%
Percentile: 27.8%
Last updated: recent
Eligibility: headline eligible

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

27.8% percentile inside its fair comparison set

69%Raw benchmark valueCI 64.9% - 73.1%

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 #30 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 20.1%
Percentile: 40.8%
Last updated: recent
Eligibility: headline eligible

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

40.8% percentile inside its fair comparison set

20.1%Raw benchmark valueCI 13.4% - 26.8%

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 #37 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 88.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: coding. Source rank: #47. Votes: 8808. Organization: openai. License: Proprietary.

88.8% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,490 - 1,505

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 #70 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 78.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: coding. Source rank: #86. Votes: 6358. Organization: openai. License: Proprietary.

78.4% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,427 - 1,443

IOI

VALS-AI · Coding · Objective

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

Rank #15 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 20%
Percentile: 68.2%
Last updated: recent
Eligibility: headline eligible

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

68.2% percentile inside its fair comparison set

20%Raw benchmark valueCI 11% - 29%

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 #37 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 51.7%
Percentile: 67.6%
Last updated: archived
Eligibility: headline eligible

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

67.6% percentile inside its fair comparison set

51.7%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 #64 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72.1%
Percentile: 41.7%
Last updated: archived
Eligibility: headline eligible

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

41.7% percentile inside its fair comparison set

72.1%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 #37 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45%
Percentile: 73.1%
Last updated: archived
Eligibility: headline eligible

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

73.1% percentile inside its fair comparison set

45%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 #34 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45%
Percentile: 76.6%
Last updated: archived
Eligibility: headline eligible

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

76.6% percentile inside its fair comparison set

45%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 #54 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65%
Percentile: 60.2%
Last updated: archived
Eligibility: headline eligible

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

60.2% percentile inside its fair comparison set

65%Raw benchmark value

Coding generation

LB · Coding · Objective

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

Rank #61 · Source label: gpt-5-pro-2025-10-06

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 #65 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 69.6%
Percentile: 42.6%
Last updated: archived
Eligibility: headline eligible

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

42.6% percentile inside its fair comparison set

69.6%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 #9

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 49.6%
Percentile: 73.3%
Last updated: archived
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 (0.53.0). Display model: GPT-5. Integration method: API. Agent URL: https://developers.openai.com/codex/cli/. Reported stderr: 1.478 percentage points.

73.3% percentile inside its fair comparison set

49.6%Raw benchmark value

Reasoning / math / science21 benchmarks74%

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 #187 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 5.4%
Percentile: 49.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

49.7% percentile inside its fair comparison set

5.4%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 #157 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 67.3%
Percentile: 58.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

58.3% percentile inside its fair comparison set

67.3%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 #110 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

65.2% percentile inside its fair comparison set

0%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 #19 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 18%
Percentile: 48.6%
Last updated: recent
Eligibility: headline eligible

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

48.6% percentile inside its fair comparison set

18%Raw benchmark valueCI 10.5% - 25.5%

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 #26 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.6%
Percentile: 71.9%
Last updated: recent
Eligibility: headline eligible

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

71.9% percentile inside its fair comparison set

85.6%Raw benchmark valueCI 82.1% - 89.1%

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 #24 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.5%
Percentile: 74.2%
Last updated: recent
Eligibility: headline eligible

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

74.2% percentile inside its fair comparison set

86.5%Raw benchmark valueCI 85.9% - 87.2%

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 #51 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 84.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: math. Source rank: #62. Votes: 1887. Organization: openai. License: Proprietary.

84.1% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,420 - 1,447

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 #85 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 73.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: math. Source rank: #103. Votes: 1785. Organization: openai. License: Proprietary.

73.2% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,395 - 1,422

TutorBench

SL · Reasoning / math / science · Rubric

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

Rank #3

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 55.3%
Percentile: 80%
Last updated: recent
Eligibility: headline eligible

Manually verified from the official Scale Labs TutorBench leaderboard.

80% percentile inside its fair comparison set

55.3%Raw benchmark value

MultiNRC

SL · Reasoning / math / science · Rubric

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

Rank #5

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 52.1%
Percentile: 60%
Last updated: recent
Eligibility: headline eligible

60% percentile inside its fair comparison set

52.1%Raw benchmark value

EnigmaEval

SL · Reasoning / math / science · Rubric

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

Rank #4

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 64%
Percentile: 80%
Last updated: aging
Eligibility: headline eligible

80% percentile inside its fair comparison set

64%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 #25 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86.2%
Percentile: 77.8%
Last updated: archived
Eligibility: headline eligible

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

77.8% percentile inside its fair comparison set

86.2%Raw benchmark value

Reasoning

LB · Reasoning / math / science · Objective

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

Rank #23 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 81.7%
Percentile: 79.6%
Last updated: archived
Eligibility: headline eligible

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

79.6% percentile inside its fair comparison set

81.7%Raw benchmark value

AMPS Hard

LB · Reasoning / math / science · Objective

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

Rank #19 · Source label: gpt-5-pro-2025-10-06

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 #33 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62%
Percentile: 71.3%
Last updated: archived
Eligibility: headline eligible

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

71.3% percentile inside its fair comparison set

62%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 #4 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 97.1%
Percentile: 99.1%
Last updated: archived
Eligibility: headline eligible

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

99.1% percentile inside its fair comparison set

97.1%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

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

Rank #32 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87.6%
Percentile: 71.3%
Last updated: archived
Eligibility: headline eligible

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

71.3% percentile inside its fair comparison set

87.6%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 #13 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.8%
Percentile: 93.5%
Last updated: archived
Eligibility: headline eligible

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

93.5% percentile inside its fair comparison set

80.8%Raw benchmark value

Zebra puzzle

LB · Reasoning / math / science · Objective

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

Rank #23 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84%
Percentile: 79.4%
Last updated: archived
Eligibility: headline eligible

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

79.4% percentile inside its fair comparison set

84%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 #21 · Source label: gpt-5-pro-2025-10-06

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 #55 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64%
Percentile: 53.7%
Last updated: archived
Eligibility: headline eligible

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

53.7% percentile inside its fair comparison set

64%Raw benchmark value

Professional reasoning30 benchmarks77.9%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #7 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86%
Percentile: 93.3%
Last updated: recent
Eligibility: headline eligible

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

93.3% percentile inside its fair comparison set

86%Raw benchmark valueCI 85.3% - 86.8%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #31 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 73.4%
Percentile: 67%
Last updated: recent
Eligibility: headline eligible

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

67% percentile inside its fair comparison set

73.4%Raw benchmark valueCI 71.7% - 75.1%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #12 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 49.6%
Percentile: 78.4%
Last updated: recent
Eligibility: headline eligible

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

78.4% percentile inside its fair comparison set

49.6%Raw benchmark valueCI 45.5% - 53.7%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #13 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.7%
Percentile: 76%
Last updated: recent
Eligibility: headline eligible

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

76% percentile inside its fair comparison set

83.7%Raw benchmark valueCI 79.9% - 87.4%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #43 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 84.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: expert. Source rank: #53. Votes: 2762. Organization: openai. License: Proprietary.

84.7% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,458 - 1,482

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 #24 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,460
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: industry_business_and_management_and_financial_operations. Source rank: #31. Votes: 6538. Organization: openai. License: Proprietary.

92.8% percentile inside its fair comparison set

1,460Raw benchmark valueCI 1,451 - 1,468

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 #40 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 87.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: industry_entertainment_and_sports_and_media. Source rank: #52. Votes: 6476. Organization: openai. License: Proprietary.

87.9% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,406 - 1,423

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #30 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 90.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: industry_legal_and_government. Source rank: #40. Votes: 2559. Organization: openai. License: Proprietary.

90.3% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,451 - 1,477

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 #44 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,459
Percentile: 86.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: industry_life_and_physical_and_social_science. Source rank: #56. Votes: 5212. Organization: openai. License: Proprietary.

86.7% percentile inside its fair comparison set

1,459Raw benchmark valueCI 1,450 - 1,468

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #53 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 83.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: industry_mathematical. Source rank: #65. Votes: 1747. Organization: openai. License: Proprietary.

83.1% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,428 - 1,456

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #26 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 91.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: industry_medicine_and_healthcare. Source rank: #33. Votes: 2468. Organization: openai. License: Proprietary.

91.5% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,468 - 1,493

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 #35 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 89.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: industry_software_and_it_services. Source rank: #44. Votes: 12869. Organization: openai. License: Proprietary.

89.5% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,482 - 1,495

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 #40 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 88%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: industry_writing_and_literature_and_language. Source rank: #52. Votes: 7651. Organization: openai. License: Proprietary.

88% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,419 - 1,434

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #75 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 73.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: expert. Source rank: #91. Votes: 1588. Organization: openai. License: Proprietary.

73.1% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,405 - 1,436

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 #83 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 74.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: industry_business_and_management_and_financial_operations. Source rank: #99. Votes: 5612. Organization: openai. License: Proprietary.

74.2% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,391 - 1,407

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 #77 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,378
Percentile: 76.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #93. Votes: 5839. Organization: openai. License: Proprietary.

76.5% percentile inside its fair comparison set

1,378Raw benchmark valueCI 1,370 - 1,386

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 #62 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 79.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: industry_legal_and_government. Source rank: #75. Votes: 1951. Organization: openai. License: Proprietary.

79.5% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,416 - 1,443

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 #92 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 71.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: industry_life_and_physical_and_social_science. Source rank: #108. Votes: 5030. Organization: openai. License: Proprietary.

71.8% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,408 - 1,425

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #97 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 68.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: industry_mathematical. Source rank: #115. Votes: 1747. Organization: openai. License: Proprietary.

68.8% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,390 - 1,418

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 #89 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 70.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: industry_medicine_and_healthcare. Source rank: #107. Votes: 1695. Organization: openai. License: Proprietary.

70.2% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,399 - 1,428

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 #91 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 72.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: industry_software_and_it_services. Source rank: #109. Votes: 10924. Organization: openai. License: Proprietary.

72.3% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,413 - 1,426

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 #82 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 75%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: industry_writing_and_literature_and_language. Source rank: #100. Votes: 6777. Organization: openai. License: Proprietary.

75% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,378 - 1,393

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #22 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 43.7%
Percentile: 53.3%
Last updated: recent
Eligibility: headline eligible

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

53.3% percentile inside its fair comparison set

43.7%Raw benchmark valueCI 37.1% - 50.2%

PRBench Legal

SL · Professional reasoning · Rubric

Applied legal reasoning on professional-domain tasks.

Rank #3

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 49%
Percentile: 83.3%
Last updated: recent
Eligibility: headline eligible

83.3% percentile inside its fair comparison set

49%Raw benchmark value

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #50 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 57%
Percentile: 54.6%
Last updated: archived
Eligibility: headline eligible

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

54.6% percentile inside its fair comparison set

57%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #33 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70.5%
Percentile: 70.4%
Last updated: archived
Eligibility: headline eligible

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

70.4% percentile inside its fair comparison set

70.5%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #54 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 26.3%
Percentile: 50.9%
Last updated: archived
Eligibility: headline eligible

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

50.9% percentile inside its fair comparison set

26.3%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #43 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 44.8%
Percentile: 61.1%
Last updated: archived
Eligibility: headline eligible

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

61.1% percentile inside its fair comparison set

44.8%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #7 · Source label: gpt-5-pro-2025-10-06

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

Poker Agent

VALS-AI · Professional reasoning · Objective

Agent profit in poker-style strategic play.

Rank #2 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 1,103.2 score
Percentile: 93.8%
Last updated: archived
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: poker_agent; provider: unknown.

93.8% percentile inside its fair comparison set

1,103.2 scoreRaw benchmark valueCI 1,103.2 score - 1,103.2 score

Search / tool use3 benchmarks22.7%

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 #295 · Source label: GPT-5 (ChatGPT)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 4.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

4.9% percentile inside its fair comparison set

0%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 #18 · Source label: gpt-5-search

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,180
Percentile: 43.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-search`. Category: overall. Source rank: #19. Votes: 20928. Organization: openai. License: Proprietary.

43.3% percentile inside its fair comparison set

1,180Raw benchmark valueCI 1,173 - 1,188

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 #25 · Source label: gpt-5-search

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,132
Percentile: 20%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-search`. Category: overall. Source rank: #27. Votes: 20928. Organization: openai. License: Proprietary.

20% percentile inside its fair comparison set

1,132Raw benchmark valueCI 1,127 - 1,138

Long context2 benchmarks49.3%

Long Context Reasoning

AA · Long context · Objective

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

Rank #170 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 25%
Percentile: 46.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

46.3% percentile inside its fair comparison set

25%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 #43 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 61.1%
Percentile: 52.3%
Last updated: recent
Eligibility: headline eligible

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

52.3% percentile inside its fair comparison set

61.1%Raw benchmark valueCI 59.2% - 63%

Vision understanding24 benchmarks60.5%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #67 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 62.1%
Percentile: 51.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

51.1% percentile inside its fair comparison set

62.1%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

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

Rank #34 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,225
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: overall. Source rank: #44. Votes: 40804. Organization: openai. License: Proprietary.

69.7% percentile inside its fair comparison set

1,225Raw benchmark valueCI 1,218 - 1,233

Vision Arena · Captioning

AR · Vision understanding · Human

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

Rank #12 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,200
Percentile: 57.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: captioning. Source rank: #13. Votes: 399. Organization: openai. License: Proprietary.

57.7% percentile inside its fair comparison set

1,200Raw benchmark valueCI 1,170 - 1,230

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 #33 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,218
Percentile: 41.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: creative_writing_vision. Source rank: #42. Votes: 1291. Organization: openai. License: Proprietary.

41.8% percentile inside its fair comparison set

1,218Raw benchmark valueCI 1,199 - 1,237

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 #30 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,260
Percentile: 58.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: diagram. Source rank: #39. Votes: 2552. Organization: openai. License: Proprietary.

58.6% percentile inside its fair comparison set

1,260Raw benchmark valueCI 1,247 - 1,273

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 #36 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,222
Percentile: 67.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: english. Source rank: #46. Votes: 19659. Organization: openai. License: Proprietary.

67.9% percentile inside its fair comparison set

1,222Raw benchmark valueCI 1,212 - 1,231

Vision Arena · Entity Recognition

AR · Vision understanding · Human

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

Rank #5 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,257
Percentile: 87.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: entity_recognition. Source rank: #6. Votes: 434. Organization: openai. License: Proprietary.

87.5% percentile inside its fair comparison set

1,257Raw benchmark valueCI 1,224 - 1,289

Vision Arena · Homework

AR · Vision understanding · Human

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

Rank #24 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,276
Percentile: 66.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: homework. Source rank: #31. Votes: 1346. Organization: openai. License: Proprietary.

66.2% percentile inside its fair comparison set

1,276Raw benchmark valueCI 1,260 - 1,292

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 #32 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,205
Percentile: 36.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: humor. Source rank: #40. Votes: 1323. Organization: openai. License: Proprietary.

36.7% percentile inside its fair comparison set

1,205Raw benchmark valueCI 1,184 - 1,227

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 #31 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,245
Percentile: 57.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: ocr. Source rank: #40. Votes: 10812. Organization: openai. License: Proprietary.

57.1% percentile inside its fair comparison set

1,245Raw benchmark valueCI 1,236 - 1,254

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 #37 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 67%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: overall. Source rank: #47. Votes: 40804. Organization: openai. License: Proprietary.

67% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,225 - 1,239

Vision Arena · Captioning · No Style Control

AR · Vision understanding · Human

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

Rank #13 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,215
Percentile: 53.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: captioning. Source rank: #14. Votes: 399. Organization: openai. License: Proprietary.

53.8% percentile inside its fair comparison set

1,215Raw benchmark valueCI 1,185 - 1,245

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 #38 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,225
Percentile: 32.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: creative_writing_vision. Source rank: #46. Votes: 1291. Organization: openai. License: Proprietary.

32.7% percentile inside its fair comparison set

1,225Raw benchmark valueCI 1,207 - 1,244

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 #34 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,254
Percentile: 52.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: diagram. Source rank: #42. Votes: 2552. Organization: openai. License: Proprietary.

52.9% percentile inside its fair comparison set

1,254Raw benchmark valueCI 1,241 - 1,267

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 #38 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 66.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: english. Source rank: #47. Votes: 19659. Organization: openai. License: Proprietary.

66.1% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,222 - 1,241

Vision Arena · Entity Recognition · No Style Control

AR · Vision understanding · Human

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

Rank #10 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,261
Percentile: 71.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: entity_recognition. Source rank: #11. Votes: 434. Organization: openai. License: Proprietary.

71.9% percentile inside its fair comparison set

1,261Raw benchmark valueCI 1,233 - 1,290

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 #23 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,280
Percentile: 67.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: homework. Source rank: #29. Votes: 1346. Organization: openai. License: Proprietary.

67.6% percentile inside its fair comparison set

1,280Raw benchmark valueCI 1,263 - 1,296

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 #32 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,220
Percentile: 36.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: humor. Source rank: #41. Votes: 1479. Organization: openai. License: Proprietary.

36.7% percentile inside its fair comparison set

1,220Raw benchmark valueCI 1,201 - 1,239

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

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

Rank #36 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,245
Percentile: 50%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: ocr. Source rank: #44. Votes: 10812. Organization: openai. License: Proprietary.

50% percentile inside its fair comparison set

1,245Raw benchmark valueCI 1,237 - 1,254

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 #23 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 81.5%
Percentile: 62.1%
Last updated: recent
Eligibility: headline eligible

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

62.1% percentile inside its fair comparison set

81.5%Raw benchmark valueCI 79.7% - 83.3%

VTB

SL · Vision understanding · Rubric

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

Rank #5

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 17%
Percentile: 63.6%
Last updated: recent
Eligibility: headline eligible

63.6% percentile inside its fair comparison set

17%Raw benchmark value

VISTA

SL · Vision understanding · Rubric

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

Rank #2

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 79%
Percentile: 92.9%
Last updated: aging
Eligibility: headline eligible

92.9% percentile inside its fair comparison set

79%Raw benchmark value

Vision Arena · Creative Writing

AR · Vision understanding · Human

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

Rank #11 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 68.8%
Last updated: archived
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: creative_writing. Source rank: #12. Votes: 1518. Organization: openai. License: Proprietary.

68.8% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,216 - 1,248

Vision Arena · Creative Writing · 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-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,239
Percentile: 71.9%
Last updated: archived
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: creative_writing. Source rank: #12. Votes: 1518. Organization: openai. License: Proprietary.

71.9% percentile inside its fair comparison set

1,239Raw benchmark valueCI 1,224 - 1,255

Document understanding2 benchmarks73.9%

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 #28 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.5%
Percentile: 55%
Last updated: recent
Eligibility: headline eligible

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

55% percentile inside its fair comparison set

65.5%Raw benchmark valueCI 63.7% - 67.2%

Multimodal mix

OC · Document understanding · Objective

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

Rank #2

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: OpenCompass
Raw value: 75.4%
Percentile: 92.9%
Last updated: recent
Eligibility: headline eligible

92.9% percentile inside its fair comparison set

75.4%Raw benchmark value

Safety1 benchmark61.5%

MASK

SL · Safety · Rubric

Whether a model stays honest instead of covertly optimizing against the user.

Rank #6

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 79.3%
Percentile: 61.5%
Last updated: recent
Eligibility: headline eligible

61.5% percentile inside its fair comparison set

79.3%Raw benchmark value

Embeddings / retrieval1 benchmark100%

Retrieval

MTEB · Embeddings / retrieval · Retrieval

It is one of the few direct signals for retrieval stacks, where embedding quality matters more than chat style.

Rank #1

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: MTEB
Raw value: 58.8 ndcg
Percentile: 100%
Last updated: aging
Eligibility: headline eligible

Embedding endpoint score.

100% percentile inside its fair comparison set

58.8 ndcgRaw benchmark value

Multilingual16 benchmarks75.8%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #35 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 88.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: chinese. Source rank: #45. Votes: 1731. Organization: openai. License: Proprietary.

88.5% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,475 - 1,506

Text Arena · French

AR · Multilingual · Human

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

Rank #33 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,471
Percentile: 85.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: french. Source rank: #44. Votes: 990. Organization: openai. License: Proprietary.

85.2% percentile inside its fair comparison set

1,471Raw benchmark valueCI 1,450 - 1,492

Text Arena · German

AR · Multilingual · Human

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

Rank #36 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 85.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: german. Source rank: #46. Votes: 701. Organization: openai. License: Proprietary.

85.2% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,419 - 1,466

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #23 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 89.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: japanese. Source rank: #31. Votes: 817. Organization: openai. License: Proprietary.

89.2% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,406 - 1,452

Text Arena · Korean

AR · Multilingual · Human

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

Rank #26 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 88%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: korean. Source rank: #33. Votes: 549. Organization: openai. License: Proprietary.

88% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,390 - 1,445

Text Arena · Russian

AR · Multilingual · Human

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

Rank #26 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 91.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: russian. Source rank: #35. Votes: 3571. Organization: openai. License: Proprietary.

91.3% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,448 - 1,469

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #46 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 79%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: spanish. Source rank: #58. Votes: 1178. Organization: openai. License: Proprietary.

79% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,417 - 1,456

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #94 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 68.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: chinese. Source rank: #112. Votes: 1731. Organization: openai. License: Proprietary.

68.5% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,412 - 1,442

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #83 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 62%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: french. Source rank: #100. Votes: 393. Organization: openai. License: Proprietary.

62% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,383 - 1,444

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #60 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 75.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: german. Source rank: #75. Votes: 701. Organization: openai. License: Proprietary.

75.1% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,389 - 1,435

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #29 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 86.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: japanese. Source rank: #38. Votes: 466. Organization: openai. License: Proprietary.

86.2% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,377 - 1,435

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #64 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,366
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: korean. Source rank: #78. Votes: 807. Organization: openai. License: Proprietary.

69.7% percentile inside its fair comparison set

1,366Raw benchmark valueCI 1,344 - 1,388

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #72 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 75.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: russian. Source rank: #89. Votes: 1591. Organization: openai. License: Proprietary.

75.4% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,389 - 1,418

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #90 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,387
Percentile: 58.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: spanish. Source rank: #108. Votes: 771. Organization: openai. License: Proprietary.

58.4% percentile inside its fair comparison set

1,387Raw benchmark valueCI 1,365 - 1,409

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #34 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,259
Percentile: 57.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: chinese. Source rank: #43. Votes: 1279. Organization: openai. License: Proprietary.

57.1% percentile inside its fair comparison set

1,259Raw benchmark valueCI 1,238 - 1,280

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #36 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,258
Percentile: 54.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: chinese. Source rank: #47. Votes: 1279. Organization: openai. License: Proprietary.

54.5% percentile inside its fair comparison set

1,258Raw benchmark valueCI 1,238 - 1,279

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

Closed weightsfrontier · registry tag 2026 frontier

Visible tradeoffs

Reads as visible tradeoffs across the resolved source data.

Visible coverage: 55.5%
Verified coverage: 55.5%
Spread: 97.1%
Last verified: Jun 20, 2026

65%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 / text38 benchmarks67.6%

Intelligence Index

AA · Chat / text · Combined

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

Rank #162 · Source label: GPT-5 (ChatGPT)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 15
Percentile: 59.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

59.2% percentile inside its fair comparison set

15Raw 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 #36 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 28.1%
Percentile: 88.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

88.3% percentile inside its fair comparison set

28.1%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 #162 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 13.8%
Percentile: 46%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

46% percentile inside its fair comparison set

13.8%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 #121 · Source label: GPT-5 (ChatGPT)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 45%
Percentile: 61.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

61.9% percentile inside its fair comparison set

45%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 #230 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $3.4 /1M tokens
Percentile: 18.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

18.1% percentile inside its fair comparison set

$3.4 /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 #212 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.3 /1M input tokens
Percentile: 24.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

24.6% percentile inside its fair comparison set

$1.3 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

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

Rank #239 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $10 /1M output tokens
Percentile: 15.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

15.2% percentile inside its fair comparison set

$10 /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 #118 · Source label: GPT-5 (low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 86.4 tokens/s
Percentile: 44.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

44.3% percentile inside its fair comparison set

86.4 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 #205 · Source label: GPT-5 (high)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 90.42s
Percentile: 2.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

2.9% percentile inside its fair comparison set

90.42sRaw 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 #203 · Source label: GPT-5 (high)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 90.42s
Percentile: 3.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

3.8% percentile inside its fair comparison set

90.42sRaw benchmark value

Openness Index

AA · Chat / text · Combined

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

Rank #173 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 6
Percentile: 7.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `opennessBreakdown.opennessIndex`.

7.5% percentile inside its fair comparison set

6Raw 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 #36 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,449
Percentile: 89.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: overall. Source rank: #47. Votes: 33125. Organization: openai. License: Proprietary.

89.2% percentile inside its fair comparison set

1,449Raw benchmark valueCI 1,444 - 1,453

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 #51 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 84.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: creative_writing. Source rank: #65. Votes: 5151. Organization: openai. License: Proprietary.

84.5% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,397 - 1,415

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 #45 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 86.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: english. Source rank: #57. Votes: 15538. Organization: openai. License: Proprietary.

86.5% percentile inside its fair comparison set

1,451Raw benchmark valueCI 1,445 - 1,457

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 #34 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 89.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: exclude_ties. Source rank: #45. Votes: 25433. Organization: openai. License: Proprietary.

89.8% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,446 - 1,458

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 #35 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 89.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: hard_prompts. Source rank: #47. Votes: 20701. Organization: openai. License: Proprietary.

89.5% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,466 - 1,477

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 #42 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 87.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: hard_prompts_english. Source rank: #54. Votes: 10150. Organization: openai. License: Proprietary.

87.3% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,462 - 1,476

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 #42 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 87.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: instruction_following. Source rank: #53. Votes: 10643. Organization: openai. License: Proprietary.

87.4% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,427 - 1,441

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 #36 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 88.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: longer_query. Source rank: #47. Votes: 12595. Organization: openai. License: Proprietary.

88.5% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,449 - 1,462

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 #31 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 90.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: multi_turn. Source rank: #42. Votes: 6201. Organization: openai. License: Proprietary.

90.7% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,458 - 1,475

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 #89 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 72.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: overall. Source rank: #107. Votes: 31928. Organization: openai. License: Proprietary.

72.9% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,401 - 1,410

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 #84 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,368
Percentile: 74.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: creative_writing. Source rank: #104. Votes: 4016. Organization: openai. License: Proprietary.

74.3% percentile inside its fair comparison set

1,368Raw benchmark valueCI 1,358 - 1,377

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 #96 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 70.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: english. Source rank: #115. Votes: 15139. Organization: openai. License: Proprietary.

70.8% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,403 - 1,414

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 #91 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 72.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: exclude_ties. Source rank: #109. Votes: 23604. Organization: openai. License: Proprietary.

72.3% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,380 - 1,392

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 #85 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 74.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: hard_prompts. Source rank: #102. Votes: 14987. Organization: openai. License: Proprietary.

74.2% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,409 - 1,421

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 #84 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,421
Percentile: 74.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: hard_prompts_english. Source rank: #101. Votes: 7688. Organization: openai. License: Proprietary.

74.4% percentile inside its fair comparison set

1,421Raw benchmark valueCI 1,413 - 1,428

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 #86 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,388
Percentile: 73.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: instruction_following. Source rank: #104. Votes: 8266. Organization: openai. License: Proprietary.

73.8% percentile inside its fair comparison set

1,388Raw benchmark valueCI 1,381 - 1,395

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 #87 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 71.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: longer_query. Source rank: #107. Votes: 6729. Organization: openai. License: Proprietary.

71.7% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,393 - 1,408

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 #57 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,426
Percentile: 82.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: multi_turn. Source rank: #71. Votes: 5796. Organization: openai. License: Proprietary.

82.7% percentile inside its fair comparison set

1,426Raw benchmark valueCI 1,418 - 1,434

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 #18 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64%
Percentile: 84.3%
Last updated: archived
Eligibility: headline eligible

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

84.3% percentile inside its fair comparison set

64%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 #14 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.7%
Percentile: 88%
Last updated: archived
Eligibility: headline eligible

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

88% percentile inside its fair comparison set

80.7%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 #27 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 61.4%
Percentile: 75.9%
Last updated: archived
Eligibility: headline eligible

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

75.9% percentile inside its fair comparison set

61.4%Raw benchmark value

Simplify

LB · Chat / text · Objective

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

Rank #13 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62.2%
Percentile: 88.9%
Last updated: archived
Eligibility: headline eligible

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

88.9% percentile inside its fair comparison set

62.2%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 #25 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 67.3%
Percentile: 78.7%
Last updated: archived
Eligibility: headline eligible

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

78.7% percentile inside its fair comparison set

67.3%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 #27 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65%
Percentile: 75.9%
Last updated: archived
Eligibility: headline eligible

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

75.9% percentile inside its fair comparison set

65%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 #22 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 81.5%
Last updated: archived
Eligibility: headline eligible

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

81.5% percentile inside its fair comparison set

98%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 #14 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64.1%
Percentile: 88%
Last updated: archived
Eligibility: headline eligible

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

88% percentile inside its fair comparison set

64.1%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 #34 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80%
Percentile: 75.7%
Last updated: archived
Eligibility: headline eligible

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

75.7% percentile inside its fair comparison set

80%Raw benchmark value

Coding19 benchmarks61.6%

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 #133 · Source label: GPT-5 (ChatGPT)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 12.9%
Percentile: 56.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

56.3% percentile inside its fair comparison set

12.9%Raw benchmark value

SciCode

AA · Coding · Objective

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

Rank #85 · Source label: GPT-5 (ChatGPT)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 37.8%
Percentile: 77.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

77.2% percentile inside its fair comparison set

37.8%Raw 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 #35 · Source label: gpt-5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,394
Percentile: 53.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-medium`. Category: overall. Source rank: #43. Votes: 3755. Organization: openai. License: Proprietary.

53.4% percentile inside its fair comparison set

1,394Raw benchmark valueCI 1,382 - 1,407

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 #35 · Source label: gpt-5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,394
Percentile: 53.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-medium`. Category: webdev. Source rank: #43. Votes: 3755. Organization: openai. License: Proprietary.

53.4% percentile inside its fair comparison set

1,394Raw benchmark valueCI 1,382 - 1,407

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 #35 · Source label: gpt-5-medium

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 53.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-medium`. Category: webdev-html. Source rank: #43. Votes: 3755. Organization: openai. License: Proprietary.

53.4% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,388 - 1,416

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 #15 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.9%
Percentile: 84.4%
Last updated: recent
Eligibility: headline eligible

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

84.4% percentile inside its fair comparison set

85.9%Raw benchmark valueCI 84% - 87.8%

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 #40 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69%
Percentile: 27.8%
Last updated: recent
Eligibility: headline eligible

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

27.8% percentile inside its fair comparison set

69%Raw benchmark valueCI 64.9% - 73.1%

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 #30 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 20.1%
Percentile: 40.8%
Last updated: recent
Eligibility: headline eligible

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

40.8% percentile inside its fair comparison set

20.1%Raw benchmark valueCI 13.4% - 26.8%

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 #37 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 88.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: coding. Source rank: #47. Votes: 8808. Organization: openai. License: Proprietary.

88.8% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,490 - 1,505

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 #70 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 78.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: coding. Source rank: #86. Votes: 6358. Organization: openai. License: Proprietary.

78.4% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,427 - 1,443

IOI

VALS-AI · Coding · Objective

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

Rank #15 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 20%
Percentile: 68.2%
Last updated: recent
Eligibility: headline eligible

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

68.2% percentile inside its fair comparison set

20%Raw benchmark valueCI 11% - 29%

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 #37 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 51.7%
Percentile: 67.6%
Last updated: archived
Eligibility: headline eligible

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

67.6% percentile inside its fair comparison set

51.7%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 #64 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72.1%
Percentile: 41.7%
Last updated: archived
Eligibility: headline eligible

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

41.7% percentile inside its fair comparison set

72.1%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 #37 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45%
Percentile: 73.1%
Last updated: archived
Eligibility: headline eligible

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

73.1% percentile inside its fair comparison set

45%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 #34 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45%
Percentile: 76.6%
Last updated: archived
Eligibility: headline eligible

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

76.6% percentile inside its fair comparison set

45%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 #54 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 65%
Percentile: 60.2%
Last updated: archived
Eligibility: headline eligible

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

60.2% percentile inside its fair comparison set

65%Raw benchmark value

Coding generation

LB · Coding · Objective

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

Rank #61 · Source label: gpt-5-pro-2025-10-06

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 #65 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 69.6%
Percentile: 42.6%
Last updated: archived
Eligibility: headline eligible

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

42.6% percentile inside its fair comparison set

69.6%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 #9

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 49.6%
Percentile: 73.3%
Last updated: archived
Eligibility: headline eligible

73.3% percentile inside its fair comparison set

49.6%Raw benchmark value

Reasoning / math / science21 benchmarks74%

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 #187 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 5.4%
Percentile: 49.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

49.7% percentile inside its fair comparison set

5.4%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 #157 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 67.3%
Percentile: 58.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

58.3% percentile inside its fair comparison set

67.3%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 #110 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

65.2% percentile inside its fair comparison set

0%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 #19 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 18%
Percentile: 48.6%
Last updated: recent
Eligibility: headline eligible

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

48.6% percentile inside its fair comparison set

18%Raw benchmark valueCI 10.5% - 25.5%

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 #26 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.6%
Percentile: 71.9%
Last updated: recent
Eligibility: headline eligible

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

71.9% percentile inside its fair comparison set

85.6%Raw benchmark valueCI 82.1% - 89.1%

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 #24 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.5%
Percentile: 74.2%
Last updated: recent
Eligibility: headline eligible

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

74.2% percentile inside its fair comparison set

86.5%Raw benchmark valueCI 85.9% - 87.2%

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 #51 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 84.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: math. Source rank: #62. Votes: 1887. Organization: openai. License: Proprietary.

84.1% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,420 - 1,447

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 #85 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 73.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: math. Source rank: #103. Votes: 1785. Organization: openai. License: Proprietary.

73.2% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,395 - 1,422

TutorBench

SL · Reasoning / math / science · Rubric

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

Rank #3

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 55.3%
Percentile: 80%
Last updated: recent
Eligibility: headline eligible

Manually verified from the official Scale Labs TutorBench leaderboard.

80% percentile inside its fair comparison set

55.3%Raw benchmark value

MultiNRC

SL · Reasoning / math / science · Rubric

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

Rank #5

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 52.1%
Percentile: 60%
Last updated: recent
Eligibility: headline eligible

60% percentile inside its fair comparison set

52.1%Raw benchmark value

EnigmaEval

SL · Reasoning / math / science · Rubric

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

Rank #4

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 64%
Percentile: 80%
Last updated: aging
Eligibility: headline eligible

80% percentile inside its fair comparison set

64%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 #25 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86.2%
Percentile: 77.8%
Last updated: archived
Eligibility: headline eligible

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

77.8% percentile inside its fair comparison set

86.2%Raw benchmark value

Reasoning

LB · Reasoning / math / science · Objective

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

Rank #23 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 81.7%
Percentile: 79.6%
Last updated: archived
Eligibility: headline eligible

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

79.6% percentile inside its fair comparison set

81.7%Raw benchmark value

AMPS Hard

LB · Reasoning / math / science · Objective

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

Rank #19 · Source label: gpt-5-pro-2025-10-06

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 #33 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62%
Percentile: 71.3%
Last updated: archived
Eligibility: headline eligible

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

71.3% percentile inside its fair comparison set

62%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 #4 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 97.1%
Percentile: 99.1%
Last updated: archived
Eligibility: headline eligible

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

99.1% percentile inside its fair comparison set

97.1%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

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

Rank #32 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87.6%
Percentile: 71.3%
Last updated: archived
Eligibility: headline eligible

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

71.3% percentile inside its fair comparison set

87.6%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 #13 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80.8%
Percentile: 93.5%
Last updated: archived
Eligibility: headline eligible

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

93.5% percentile inside its fair comparison set

80.8%Raw benchmark value

Zebra puzzle

LB · Reasoning / math / science · Objective

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

Rank #23 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84%
Percentile: 79.4%
Last updated: archived
Eligibility: headline eligible

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

79.4% percentile inside its fair comparison set

84%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 #21 · Source label: gpt-5-pro-2025-10-06

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 #55 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64%
Percentile: 53.7%
Last updated: archived
Eligibility: headline eligible

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

53.7% percentile inside its fair comparison set

64%Raw benchmark value

Professional reasoning30 benchmarks77.9%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #7 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86%
Percentile: 93.3%
Last updated: recent
Eligibility: headline eligible

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

93.3% percentile inside its fair comparison set

86%Raw benchmark valueCI 85.3% - 86.8%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #31 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 73.4%
Percentile: 67%
Last updated: recent
Eligibility: headline eligible

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

67% percentile inside its fair comparison set

73.4%Raw benchmark valueCI 71.7% - 75.1%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #12 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 49.6%
Percentile: 78.4%
Last updated: recent
Eligibility: headline eligible

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

78.4% percentile inside its fair comparison set

49.6%Raw benchmark valueCI 45.5% - 53.7%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #13 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.7%
Percentile: 76%
Last updated: recent
Eligibility: headline eligible

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

76% percentile inside its fair comparison set

83.7%Raw benchmark valueCI 79.9% - 87.4%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #43 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 84.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: expert. Source rank: #53. Votes: 2762. Organization: openai. License: Proprietary.

84.7% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,458 - 1,482

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 #24 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,460
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

92.8% percentile inside its fair comparison set

1,460Raw benchmark valueCI 1,451 - 1,468

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 #40 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 87.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: industry_entertainment_and_sports_and_media. Source rank: #52. Votes: 6476. Organization: openai. License: Proprietary.

87.9% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,406 - 1,423

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #30 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 90.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: industry_legal_and_government. Source rank: #40. Votes: 2559. Organization: openai. License: Proprietary.

90.3% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,451 - 1,477

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 #44 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,459
Percentile: 86.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: industry_life_and_physical_and_social_science. Source rank: #56. Votes: 5212. Organization: openai. License: Proprietary.

86.7% percentile inside its fair comparison set

1,459Raw benchmark valueCI 1,450 - 1,468

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #53 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 83.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: industry_mathematical. Source rank: #65. Votes: 1747. Organization: openai. License: Proprietary.

83.1% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,428 - 1,456

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #26 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 91.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: industry_medicine_and_healthcare. Source rank: #33. Votes: 2468. Organization: openai. License: Proprietary.

91.5% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,468 - 1,493

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 #35 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 89.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: industry_software_and_it_services. Source rank: #44. Votes: 12869. Organization: openai. License: Proprietary.

89.5% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,482 - 1,495

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 #40 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 88%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: industry_writing_and_literature_and_language. Source rank: #52. Votes: 7651. Organization: openai. License: Proprietary.

88% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,419 - 1,434

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #75 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 73.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: expert. Source rank: #91. Votes: 1588. Organization: openai. License: Proprietary.

73.1% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,405 - 1,436

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 #83 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 74.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: industry_business_and_management_and_financial_operations. Source rank: #99. Votes: 5612. Organization: openai. License: Proprietary.

74.2% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,391 - 1,407

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 #77 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,378
Percentile: 76.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #93. Votes: 5839. Organization: openai. License: Proprietary.

76.5% percentile inside its fair comparison set

1,378Raw benchmark valueCI 1,370 - 1,386

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 #62 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 79.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: industry_legal_and_government. Source rank: #75. Votes: 1951. Organization: openai. License: Proprietary.

79.5% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,416 - 1,443

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 #92 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 71.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: industry_life_and_physical_and_social_science. Source rank: #108. Votes: 5030. Organization: openai. License: Proprietary.

71.8% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,408 - 1,425

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #97 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 68.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: industry_mathematical. Source rank: #115. Votes: 1747. Organization: openai. License: Proprietary.

68.8% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,390 - 1,418

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 #89 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 70.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: industry_medicine_and_healthcare. Source rank: #107. Votes: 1695. Organization: openai. License: Proprietary.

70.2% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,399 - 1,428

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 #91 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 72.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: industry_software_and_it_services. Source rank: #109. Votes: 10924. Organization: openai. License: Proprietary.

72.3% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,413 - 1,426

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 #82 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 75%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: industry_writing_and_literature_and_language. Source rank: #100. Votes: 6777. Organization: openai. License: Proprietary.

75% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,378 - 1,393

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #22 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 43.7%
Percentile: 53.3%
Last updated: recent
Eligibility: headline eligible

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

53.3% percentile inside its fair comparison set

43.7%Raw benchmark valueCI 37.1% - 50.2%

PRBench Legal

SL · Professional reasoning · Rubric

Applied legal reasoning on professional-domain tasks.

Rank #3

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 49%
Percentile: 83.3%
Last updated: recent
Eligibility: headline eligible

83.3% percentile inside its fair comparison set

49%Raw benchmark value

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #50 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 57%
Percentile: 54.6%
Last updated: archived
Eligibility: headline eligible

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

54.6% percentile inside its fair comparison set

57%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #33 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70.5%
Percentile: 70.4%
Last updated: archived
Eligibility: headline eligible

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

70.4% percentile inside its fair comparison set

70.5%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #54 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 26.3%
Percentile: 50.9%
Last updated: archived
Eligibility: headline eligible

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

50.9% percentile inside its fair comparison set

26.3%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #43 · Source label: gpt-5-pro-2025-10-06

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 44.8%
Percentile: 61.1%
Last updated: archived
Eligibility: headline eligible

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

61.1% percentile inside its fair comparison set

44.8%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #7 · Source label: gpt-5-pro-2025-10-06

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

Poker Agent

VALS-AI · Professional reasoning · Objective

Agent profit in poker-style strategic play.

Rank #2 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 1,103.2 score
Percentile: 93.8%
Last updated: archived
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: poker_agent; provider: unknown.

93.8% percentile inside its fair comparison set

1,103.2 scoreRaw benchmark valueCI 1,103.2 score - 1,103.2 score

Search / tool use3 benchmarks22.7%

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 #295 · Source label: GPT-5 (ChatGPT)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 4.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

4.9% percentile inside its fair comparison set

0%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 #18 · Source label: gpt-5-search

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,180
Percentile: 43.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-search`. Category: overall. Source rank: #19. Votes: 20928. Organization: openai. License: Proprietary.

43.3% percentile inside its fair comparison set

1,180Raw benchmark valueCI 1,173 - 1,188

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 #25 · Source label: gpt-5-search

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,132
Percentile: 20%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-search`. Category: overall. Source rank: #27. Votes: 20928. Organization: openai. License: Proprietary.

20% percentile inside its fair comparison set

1,132Raw benchmark valueCI 1,127 - 1,138

Long context2 benchmarks49.3%

Long Context Reasoning

AA · Long context · Objective

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

Rank #170 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 25%
Percentile: 46.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

46.3% percentile inside its fair comparison set

25%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 #43 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 61.1%
Percentile: 52.3%
Last updated: recent
Eligibility: headline eligible

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

52.3% percentile inside its fair comparison set

61.1%Raw benchmark valueCI 59.2% - 63%

Vision understanding24 benchmarks60.5%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #67 · Source label: GPT-5 (minimal)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 62.1%
Percentile: 51.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

51.1% percentile inside its fair comparison set

62.1%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

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

Rank #34 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,225
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: overall. Source rank: #44. Votes: 40804. Organization: openai. License: Proprietary.

69.7% percentile inside its fair comparison set

1,225Raw benchmark valueCI 1,218 - 1,233

Vision Arena · Captioning

AR · Vision understanding · Human

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

Rank #12 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,200
Percentile: 57.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: captioning. Source rank: #13. Votes: 399. Organization: openai. License: Proprietary.

57.7% percentile inside its fair comparison set

1,200Raw benchmark valueCI 1,170 - 1,230

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 #33 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,218
Percentile: 41.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: creative_writing_vision. Source rank: #42. Votes: 1291. Organization: openai. License: Proprietary.

41.8% percentile inside its fair comparison set

1,218Raw benchmark valueCI 1,199 - 1,237

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 #30 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,260
Percentile: 58.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: diagram. Source rank: #39. Votes: 2552. Organization: openai. License: Proprietary.

58.6% percentile inside its fair comparison set

1,260Raw benchmark valueCI 1,247 - 1,273

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 #36 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,222
Percentile: 67.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: english. Source rank: #46. Votes: 19659. Organization: openai. License: Proprietary.

67.9% percentile inside its fair comparison set

1,222Raw benchmark valueCI 1,212 - 1,231

Vision Arena · Entity Recognition

AR · Vision understanding · Human

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

Rank #5 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,257
Percentile: 87.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: entity_recognition. Source rank: #6. Votes: 434. Organization: openai. License: Proprietary.

87.5% percentile inside its fair comparison set

1,257Raw benchmark valueCI 1,224 - 1,289

Vision Arena · Homework

AR · Vision understanding · Human

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

Rank #24 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,276
Percentile: 66.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: homework. Source rank: #31. Votes: 1346. Organization: openai. License: Proprietary.

66.2% percentile inside its fair comparison set

1,276Raw benchmark valueCI 1,260 - 1,292

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 #32 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,205
Percentile: 36.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: humor. Source rank: #40. Votes: 1323. Organization: openai. License: Proprietary.

36.7% percentile inside its fair comparison set

1,205Raw benchmark valueCI 1,184 - 1,227

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 #31 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,245
Percentile: 57.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: ocr. Source rank: #40. Votes: 10812. Organization: openai. License: Proprietary.

57.1% percentile inside its fair comparison set

1,245Raw benchmark valueCI 1,236 - 1,254

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 #37 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 67%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: overall. Source rank: #47. Votes: 40804. Organization: openai. License: Proprietary.

67% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,225 - 1,239

Vision Arena · Captioning · No Style Control

AR · Vision understanding · Human

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

Rank #13 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,215
Percentile: 53.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: captioning. Source rank: #14. Votes: 399. Organization: openai. License: Proprietary.

53.8% percentile inside its fair comparison set

1,215Raw benchmark valueCI 1,185 - 1,245

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 #38 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,225
Percentile: 32.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: creative_writing_vision. Source rank: #46. Votes: 1291. Organization: openai. License: Proprietary.

32.7% percentile inside its fair comparison set

1,225Raw benchmark valueCI 1,207 - 1,244

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 #34 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,254
Percentile: 52.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: diagram. Source rank: #42. Votes: 2552. Organization: openai. License: Proprietary.

52.9% percentile inside its fair comparison set

1,254Raw benchmark valueCI 1,241 - 1,267

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 #38 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 66.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: english. Source rank: #47. Votes: 19659. Organization: openai. License: Proprietary.

66.1% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,222 - 1,241

Vision Arena · Entity Recognition · No Style Control

AR · Vision understanding · Human

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

Rank #10 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,261
Percentile: 71.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: entity_recognition. Source rank: #11. Votes: 434. Organization: openai. License: Proprietary.

71.9% percentile inside its fair comparison set

1,261Raw benchmark valueCI 1,233 - 1,290

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 #23 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,280
Percentile: 67.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: homework. Source rank: #29. Votes: 1346. Organization: openai. License: Proprietary.

67.6% percentile inside its fair comparison set

1,280Raw benchmark valueCI 1,263 - 1,296

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 #32 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,220
Percentile: 36.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: humor. Source rank: #41. Votes: 1479. Organization: openai. License: Proprietary.

36.7% percentile inside its fair comparison set

1,220Raw benchmark valueCI 1,201 - 1,239

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

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

Rank #36 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,245
Percentile: 50%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: ocr. Source rank: #44. Votes: 10812. Organization: openai. License: Proprietary.

50% percentile inside its fair comparison set

1,245Raw benchmark valueCI 1,237 - 1,254

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 #23 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 81.5%
Percentile: 62.1%
Last updated: recent
Eligibility: headline eligible

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

62.1% percentile inside its fair comparison set

81.5%Raw benchmark valueCI 79.7% - 83.3%

VTB

SL · Vision understanding · Rubric

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

Rank #5

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 17%
Percentile: 63.6%
Last updated: recent
Eligibility: headline eligible

63.6% percentile inside its fair comparison set

17%Raw benchmark value

VISTA

SL · Vision understanding · Rubric

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

Rank #2

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 79%
Percentile: 92.9%
Last updated: aging
Eligibility: headline eligible

92.9% percentile inside its fair comparison set

79%Raw benchmark value

Vision Arena · Creative Writing

AR · Vision understanding · Human

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

Rank #11 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 68.8%
Last updated: archived
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: creative_writing. Source rank: #12. Votes: 1518. Organization: openai. License: Proprietary.

68.8% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,216 - 1,248

Vision Arena · Creative Writing · 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-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,239
Percentile: 71.9%
Last updated: archived
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: creative_writing. Source rank: #12. Votes: 1518. Organization: openai. License: Proprietary.

71.9% percentile inside its fair comparison set

1,239Raw benchmark valueCI 1,224 - 1,255

Document understanding2 benchmarks73.9%

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 #28 · Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.5%
Percentile: 55%
Last updated: recent
Eligibility: headline eligible

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

55% percentile inside its fair comparison set

65.5%Raw benchmark valueCI 63.7% - 67.2%

Multimodal mix

OC · Document understanding · Objective

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

Rank #2

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: OpenCompass
Raw value: 75.4%
Percentile: 92.9%
Last updated: recent
Eligibility: headline eligible

92.9% percentile inside its fair comparison set

75.4%Raw benchmark value

Safety1 benchmark61.5%

MASK

SL · Safety · Rubric

Whether a model stays honest instead of covertly optimizing against the user.

Rank #6

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 79.3%
Percentile: 61.5%
Last updated: recent
Eligibility: headline eligible

61.5% percentile inside its fair comparison set

79.3%Raw benchmark value

Embeddings / retrieval1 benchmark100%

Retrieval

MTEB · Embeddings / retrieval · Retrieval

It is one of the few direct signals for retrieval stacks, where embedding quality matters more than chat style.

Rank #1

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: MTEB
Raw value: 58.8 ndcg
Percentile: 100%
Last updated: aging
Eligibility: headline eligible

Embedding endpoint score.

100% percentile inside its fair comparison set

58.8 ndcgRaw benchmark value

Multilingual16 benchmarks75.8%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #35 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 88.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: chinese. Source rank: #45. Votes: 1731. Organization: openai. License: Proprietary.

88.5% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,475 - 1,506

Text Arena · French

AR · Multilingual · Human

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

Rank #33 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,471
Percentile: 85.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: french. Source rank: #44. Votes: 990. Organization: openai. License: Proprietary.

85.2% percentile inside its fair comparison set

1,471Raw benchmark valueCI 1,450 - 1,492

Text Arena · German

AR · Multilingual · Human

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

Rank #36 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 85.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: german. Source rank: #46. Votes: 701. Organization: openai. License: Proprietary.

85.2% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,419 - 1,466

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #23 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 89.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: japanese. Source rank: #31. Votes: 817. Organization: openai. License: Proprietary.

89.2% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,406 - 1,452

Text Arena · Korean

AR · Multilingual · Human

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

Rank #26 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 88%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: korean. Source rank: #33. Votes: 549. Organization: openai. License: Proprietary.

88% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,390 - 1,445

Text Arena · Russian

AR · Multilingual · Human

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

Rank #26 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 91.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: russian. Source rank: #35. Votes: 3571. Organization: openai. License: Proprietary.

91.3% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,448 - 1,469

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #46 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 79%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: spanish. Source rank: #58. Votes: 1178. Organization: openai. License: Proprietary.

79% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,417 - 1,456

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #94 · Source label: gpt-5.3-chat-latest

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 68.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.3-chat-latest`. Category: chinese. Source rank: #112. Votes: 1731. Organization: openai. License: Proprietary.

68.5% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,412 - 1,442

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #83 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 62%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: french. Source rank: #100. Votes: 393. Organization: openai. License: Proprietary.

62% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,383 - 1,444

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #60 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 75.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: german. Source rank: #75. Votes: 701. Organization: openai. License: Proprietary.

75.1% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,389 - 1,435

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #29 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 86.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: japanese. Source rank: #38. Votes: 466. Organization: openai. License: Proprietary.

86.2% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,377 - 1,435

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #64 · Source label: gpt-5-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,366
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-high`. Category: korean. Source rank: #78. Votes: 807. Organization: openai. License: Proprietary.

69.7% percentile inside its fair comparison set

1,366Raw benchmark valueCI 1,344 - 1,388

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #72 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 75.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: russian. Source rank: #89. Votes: 1591. Organization: openai. License: Proprietary.

75.4% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,389 - 1,418

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #90 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,387
Percentile: 58.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: spanish. Source rank: #108. Votes: 771. Organization: openai. License: Proprietary.

58.4% percentile inside its fair comparison set

1,387Raw benchmark valueCI 1,365 - 1,409

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #34 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,259
Percentile: 57.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: chinese. Source rank: #43. Votes: 1279. Organization: openai. License: Proprietary.

57.1% percentile inside its fair comparison set

1,259Raw benchmark valueCI 1,238 - 1,280

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #36 · Source label: gpt-5-chat

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,258
Percentile: 54.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5-chat`. Category: chinese. Source rank: #47. Votes: 1279. Organization: openai. License: Proprietary.

54.5% percentile inside its fair comparison set

1,258Raw benchmark valueCI 1,238 - 1,279

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

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

GPT-5

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks