Model profile · OpenAI

GPT-5.6 Terra

Closed weightspremium · registry tag 2026 balanced

Thin verified coverage

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

Visible coverage: 53.4%
Verified coverage: 53.4%
Spread: 93.2%
Last verified: Oct 3, 2026

62%capability fit

textcodevisiondocumentsearch17 aliases41 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

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

Chat / text36 benchmarks65.3%

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 #157 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 21
Percentile: 71.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

71.9% percentile inside its fair comparison set

21Raw 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 #100 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 36.8%
Percentile: 78.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

78.1% percentile inside its fair comparison set

36.8%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 #423 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 5%
Percentile: 6.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

6.8% percentile inside its fair comparison set

5%Raw benchmark value

IFBench

AA · Chat / text · Objective

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

Rank #68 · Source label: GPT-5.6 Terra (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 59.7%
Percentile: 80.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

80.7% percentile inside its fair comparison set

59.7%Raw benchmark value

Input price

AA · Chat / text · Speed / cost

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

Rank #272 · Source label: GPT-5.6 Terra (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $2 /1M input tokens
Percentile: 26.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

26.8% percentile inside its fair comparison set

$2 /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 #300 · Source label: GPT-5.6 Terra (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $12 /1M output tokens
Percentile: 15.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

15.5% percentile inside its fair comparison set

$12 /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 #138 · Source label: GPT-5.6 Terra (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 80.4 tokens/s
Percentile: 47.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

47.7% percentile inside its fair comparison set

80.4 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 #258 · Source label: GPT-5.6 Terra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 176.80s
Percentile: 2.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

2.7% percentile inside its fair comparison set

176.80sRaw 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 #256 · Source label: GPT-5.6 Terra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 176.80s
Percentile: 2.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

2.7% percentile inside its fair comparison set

176.80sRaw 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 #47 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 87.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: overall. Source rank: #51. Votes: 37663. Organization: openai. License: Proprietary.

87.8% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,461 - 1,470

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 #69 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,426
Percentile: 81.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: creative_writing. Source rank: #77. Votes: 7957. Organization: openai. License: Proprietary.

81.8% percentile inside its fair comparison set

1,426Raw benchmark valueCI 1,418 - 1,433

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 #54 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,471
Percentile: 85.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: english. Source rank: #58. Votes: 15342. Organization: openai. License: Proprietary.

85.9% percentile inside its fair comparison set

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

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 #47 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 87.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: exclude_ties. Source rank: #51. Votes: 28039. Organization: openai. License: Proprietary.

87.8% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,467 - 1,478

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 #46 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 88%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: hard_prompts. Source rank: #48. Votes: 24754. Organization: openai. License: Proprietary.

88% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,484 - 1,494

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 #53 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 86.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: hard_prompts_english. Source rank: #55. Votes: 9901. Organization: openai. License: Proprietary.

86.1% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,483 - 1,496

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 #45 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,461
Percentile: 88.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: instruction_following. Source rank: #47. Votes: 13418. Organization: openai. License: Proprietary.

88.3% percentile inside its fair comparison set

1,461Raw benchmark valueCI 1,455 - 1,468

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 #61 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 83.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: longer_query. Source rank: #65. Votes: 17693. Organization: openai. License: Proprietary.

83.1% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,460 - 1,472

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 #55 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 85.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: multi_turn. Source rank: #61. Votes: 6154. Organization: openai. License: Proprietary.

85.6% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,461 - 1,478

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 #54 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 85.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: overall. Source rank: #58. Votes: 37663. Organization: openai. License: Proprietary.

85.9% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,442 - 1,451

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 #74 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 80.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: creative_writing. Source rank: #81. Votes: 7957. Organization: openai. License: Proprietary.

80.5% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,401 - 1,416

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 #74 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 80.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: english. Source rank: #79. Votes: 15342. Organization: openai. License: Proprietary.

80.6% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,441 - 1,453

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 #53 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,444
Percentile: 86.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: exclude_ties. Source rank: #57. Votes: 28039. Organization: openai. License: Proprietary.

86.2% percentile inside its fair comparison set

1,444Raw benchmark valueCI 1,438 - 1,449

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 #45 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 88.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: hard_prompts. Source rank: #48. Votes: 24754. Organization: openai. License: Proprietary.

88.3% percentile inside its fair comparison set

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

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 #52 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 86.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: hard_prompts_english. Source rank: #54. Votes: 9901. Organization: openai. License: Proprietary.

86.4% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,457 - 1,471

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 #45 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 88.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: instruction_following. Source rank: #48. Votes: 13418. Organization: openai. License: Proprietary.

88.3% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,447 - 1,459

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 #59 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 83.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: longer_query. Source rank: #62. Votes: 17693. Organization: openai. License: Proprietary.

83.7% percentile inside its fair comparison set

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

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 #63 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 83.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: multi_turn. Source rank: #69. Votes: 6154. Organization: openai. License: Proprietary.

83.4% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,442 - 1,459

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 #45 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64.6%
Percentile: 32.3%
Last updated: stale
Eligibility: headline eligible

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

32.3% percentile inside its fair comparison set

64.6%Raw benchmark value

Language

LB · Chat / text · Objective

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

Rank #22 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.9%
Percentile: 67.7%
Last updated: stale
Eligibility: headline eligible

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

67.7% percentile inside its fair comparison set

82.9%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 #58 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 57%
Percentile: 12.3%
Last updated: stale
Eligibility: headline eligible

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

12.3% percentile inside its fair comparison set

57%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 #43 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 61.4%
Percentile: 35.4%
Last updated: stale
Eligibility: headline eligible

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

35.4% percentile inside its fair comparison set

61.4%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 #54 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 66.8%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

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

18.5% percentile inside its fair comparison set

66.8%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 #24 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.2%
Percentile: 64.6%
Last updated: stale
Eligibility: headline eligible

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

64.6% percentile inside its fair comparison set

73.2%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 #53 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 93%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

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

20% percentile inside its fair comparison set

93%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 #17 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 69.7%
Percentile: 75.4%
Last updated: stale
Eligibility: headline eligible

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

75.4% percentile inside its fair comparison set

69.7%Raw benchmark value

Typos

LB · Chat / text · Objective

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

Rank #9 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

89.2% percentile inside its fair comparison set

86%Raw benchmark value

Coding19 benchmarks58.8%

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 #15 · Source label: GPT-5.6 Terra (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43.9%
Percentile: 95.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

95.8% percentile inside its fair comparison set

43.9%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 #112 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 45.1%
Percentile: 43.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

43.9% percentile inside its fair comparison set

45.1%Raw benchmark value

Text Arena · Coding

AR · Coding · Human

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

Rank #44 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,515
Percentile: 88.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: coding. Source rank: #44. Votes: 10166. Organization: openai. License: Proprietary.

88.4% percentile inside its fair comparison set

1,515Raw benchmark valueCI 1,508 - 1,522

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 #47 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 87.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: coding. Source rank: #48. Votes: 10166. Organization: openai. License: Proprietary.

87.6% percentile inside its fair comparison set

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

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 #28 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74.6%
Percentile: 71%
Last updated: recent
Eligibility: headline eligible

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

71% percentile inside its fair comparison set

74.6%Raw benchmark valueCI 66.4% - 82.8%

Code Migration

VALS-AI · Coding · Objective

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

Rank #11 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 47.8%
Percentile: 85.3%
Last updated: recent
Eligibility: headline eligible

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

85.3% percentile inside its fair comparison set

47.8%Raw benchmark valueCI 39.4% - 56.2%

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 #7 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.6%
Percentile: 83.8%
Last updated: recent
Eligibility: headline eligible

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

83.8% percentile inside its fair comparison set

87.6%Raw benchmark valueCI 74.8% - 100.4%

ProgramBench

VALS-AI · Coding · Objective

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

Rank #20 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0.5%
Percentile: 72.4%
Last updated: recent
Eligibility: headline eligible

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

72.4% percentile inside its fair comparison set

0.5%Raw benchmark valueCI 0% - 1.5%

Terminal-Bench 2.1

VALS-AI · Coding · Objective

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

Rank #15 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 77.5%
Percentile: 80.6%
Last updated: recent
Eligibility: headline eligible

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

80.6% percentile inside its fair comparison set

77.5%Raw benchmark valueCI 73.1% - 81.9%

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 #5 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 95.4%
Percentile: 95.1%
Last updated: recent
Eligibility: headline eligible

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

95.1% percentile inside its fair comparison set

95.4%Raw benchmark valueCI 93.6% - 97.2%

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 #27 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.9%
Percentile: 79.2%
Last updated: recent
Eligibility: headline eligible

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

79.2% percentile inside its fair comparison set

85.9%Raw benchmark valueCI 83.9% - 87.9%

Terminal-Bench 4.0

TERMINAL-BENCH · Coding · Objective

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

Rank #21 · Source label: GPT-5.6 Terra (max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 21.5%
Percentile: 23.1%
Last updated: stale
Eligibility: headline eligible

Parsed from the public Terminal-Bench 4.0 official published leaderboard (status: display). Collapse policy: highest verified score per canonical model. Selected agent: Codex. Display model: GPT-5.6 Terra. Agent URL: https://openai.com/codex/. Reported stderr: 1.658 percentage points.

23.1% percentile inside its fair comparison set

21.5%Raw benchmark valueCI 18.3% - 24.8%

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 #28 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 55%
Percentile: 58.5%
Last updated: stale
Eligibility: headline eligible

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

58.5% percentile inside its fair comparison set

55%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 #31 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.2%
Percentile: 53.8%
Last updated: stale
Eligibility: headline eligible

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

53.8% percentile inside its fair comparison set

78.2%Raw benchmark value

JavaScript

LB · Coding · Objective

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

Rank #18 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68.2%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

68.2%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 #19 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 46.7%
Percentile: 72.3%
Last updated: stale
Eligibility: headline eligible

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

72.3% percentile inside its fair comparison set

46.7%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 #44 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

46.2% percentile inside its fair comparison set

50%Raw benchmark value

Coding generation

LB · Coding · Objective

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

Rank #40 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.1%
Percentile: 41.5%
Last updated: stale
Eligibility: headline eligible

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

41.5% percentile inside its fair comparison set

76.1%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 #18 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

78.5% percentile inside its fair comparison set

80.4%Raw benchmark value

Reasoning / math / science18 benchmarks72.5%

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 #209 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11.4%
Percentile: 60.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

60.7% percentile inside its fair comparison set

11.4%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 #186 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 74.6%
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

62.5% percentile inside its fair comparison set

74.6%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 #135 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 2%
Percentile: 70.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

70.7% percentile inside its fair comparison set

2%Raw benchmark value

Text Arena · Math

AR · Reasoning / math / science · Human

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

Rank #34 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,478
Percentile: 90.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: math. Source rank: #36. Votes: 1664. Organization: openai. License: Proprietary.

90.8% percentile inside its fair comparison set

1,478Raw benchmark valueCI 1,464 - 1,493

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 #49 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 86.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: math. Source rank: #51. Votes: 1664. Organization: openai. License: Proprietary.

86.6% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,448 - 1,477

ProofBench

VALS-AI · Reasoning / math / science · Objective

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

Rank #14 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74%
Percentile: 69%
Last updated: recent
Eligibility: headline eligible

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

69% percentile inside its fair comparison set

74%Raw benchmark valueCI 65.4% - 82.6%

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 #24 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 90.9%
Percentile: 81.5%
Last updated: recent
Eligibility: headline eligible

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

81.5% percentile inside its fair comparison set

90.9%Raw benchmark valueCI 87.2% - 94.6%

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 #40 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.7%
Percentile: 68.8%
Last updated: recent
Eligibility: headline eligible

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

68.8% percentile inside its fair comparison set

86.7%Raw benchmark valueCI 86% - 87.3%

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #17 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94.9%
Percentile: 75.4%
Last updated: stale
Eligibility: headline eligible

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

75.4% percentile inside its fair comparison set

94.9%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 #11 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 90.6%
Percentile: 84.6%
Last updated: stale
Eligibility: headline eligible

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

84.6% percentile inside its fair comparison set

90.6%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 #24 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

83.1% percentile inside its fair comparison set

98%Raw benchmark value

Integrals with game

LB · Reasoning / math / science · Objective

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

Rank #16 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 95%
Percentile: 76.9%
Last updated: stale
Eligibility: headline eligible

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

76.9% percentile inside its fair comparison set

95%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 #44 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

49.2% percentile inside its fair comparison set

95.1%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

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

Rank #22 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 91.5%
Percentile: 67.7%
Last updated: stale
Eligibility: headline eligible

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

67.7% percentile inside its fair comparison set

91.5%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 #3 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86.5%
Percentile: 96.9%
Last updated: stale
Eligibility: headline eligible

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

96.9% percentile inside its fair comparison set

86.5%Raw benchmark value

Zebra puzzle

LB · Reasoning / math / science · Objective

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

Rank #3 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

100% percentile inside its fair comparison set

100%Raw benchmark value

Spatial

LB · Reasoning / math / science · Objective

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

Rank #7 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

100% percentile inside its fair comparison set

100%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 #25 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76%
Percentile: 64.6%
Last updated: stale
Eligibility: headline eligible

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

64.6% percentile inside its fair comparison set

76%Raw benchmark value

Professional reasoning35 benchmarks72%

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #4 · Source label: GPT-5.6 Terra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 38.9%
Percentile: 90.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

90.6% percentile inside its fair comparison set

38.9%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #34 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 89.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: expert. Source rank: #35. Votes: 4391. Organization: openai. License: Proprietary.

89.9% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,495 - 1,514

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 #43 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_business_and_management_and_financial_operations. Source rank: #45. Votes: 7079. Organization: openai. License: Proprietary.

88.6% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,459 - 1,475

Text Arena · Industry Entertainment And Sports And Media

AR · Professional reasoning · Human

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

Rank #61 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 84%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_entertainment_and_sports_and_media. Source rank: #68. Votes: 9653. Organization: openai. License: Proprietary.

84% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,424 - 1,439

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #41 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 88.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_legal_and_government. Source rank: #43. Votes: 3229. Organization: openai. License: Proprietary.

88.5% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,466 - 1,488

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 #61 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 84%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_life_and_physical_and_social_science. Source rank: #67. Votes: 6139. Organization: openai. License: Proprietary.

84% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,468 - 1,485

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #32 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 91.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_mathematical. Source rank: #33. Votes: 2121. Organization: openai. License: Proprietary.

91.3% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,475 - 1,502

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #85 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,459
Percentile: 75.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_medicine_and_healthcare. Source rank: #94. Votes: 2718. Organization: openai. License: Proprietary.

75.7% percentile inside its fair comparison set

1,459Raw benchmark valueCI 1,447 - 1,472

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 #44 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_software_and_it_services. Source rank: #45. Votes: 14645. Organization: openai. License: Proprietary.

88.6% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,499 - 1,511

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 #59 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 84.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_writing_and_literature_and_language. Source rank: #64. Votes: 10426. Organization: openai. License: Proprietary.

84.5% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,438 - 1,451

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #33 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 90.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: expert. Source rank: #34. Votes: 4391. Organization: openai. License: Proprietary.

90.2% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,483 - 1,502

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 #44 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 88.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_business_and_management_and_financial_operations. Source rank: #47. Votes: 7079. Organization: openai. License: Proprietary.

88.3% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,440 - 1,455

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 #62 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 83.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_entertainment_and_sports_and_media. Source rank: #68. Votes: 9653. Organization: openai. License: Proprietary.

83.7% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,409 - 1,423

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 #45 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 87.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_legal_and_government. Source rank: #47. Votes: 3229. Organization: openai. License: Proprietary.

87.4% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,453 - 1,475

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 #66 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 82.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_life_and_physical_and_social_science. Source rank: #70. Votes: 6139. Organization: openai. License: Proprietary.

82.6% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,446 - 1,463

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #41 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 88.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_mathematical. Source rank: #43. Votes: 2121. Organization: openai. License: Proprietary.

88.8% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,463 - 1,489

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 #107 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 69.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_medicine_and_healthcare. Source rank: #115. Votes: 2718. Organization: openai. License: Proprietary.

69.4% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,417 - 1,441

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

AR · Professional reasoning · Human

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

Rank #47 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 87.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_software_and_it_services. Source rank: #49. Votes: 14645. Organization: openai. License: Proprietary.

87.8% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,473 - 1,485

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

AR · Professional reasoning · Human

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

Rank #61 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 84%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_writing_and_literature_and_language. Source rank: #66. Votes: 10426. Organization: openai. License: Proprietary.

84% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,422 - 1,436

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #18 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 53
Percentile: 57.5%
Last updated: recent
Eligibility: headline eligible

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

57.5% percentile inside its fair comparison set

53Raw benchmark valueCI 51 - 56

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #21 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 41.3%
Percentile: 72.1%
Last updated: recent
Eligibility: headline eligible

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

72.1% percentile inside its fair comparison set

41.3%Raw benchmark valueCI 34.6% - 48.1%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #52 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0.8%
Percentile: 27.5%
Last updated: recent
Eligibility: headline eligible

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

27.5% percentile inside its fair comparison set

0.8%Raw benchmark valueCI 0% - 2.5%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #24 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.1%
Percentile: 83%
Last updated: recent
Eligibility: headline eligible

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

83% percentile inside its fair comparison set

85.1%Raw benchmark valueCI 84.2% - 86%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #20 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54.4%
Percentile: 72.5%
Last updated: recent
Eligibility: headline eligible

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

72.5% percentile inside its fair comparison set

54.4%Raw benchmark valueCI 50.4% - 58.5%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #43 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 43.4%
Percentile: 55.8%
Last updated: recent
Eligibility: headline eligible

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

55.8% percentile inside its fair comparison set

43.4%Raw benchmark valueCI 39.2% - 47.7%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #48 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82.9%
Percentile: 51%
Last updated: recent
Eligibility: headline eligible

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

51% percentile inside its fair comparison set

82.9%Raw benchmark valueCI 79.1% - 86.7%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #33 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 47%
Percentile: 60.5%
Last updated: recent
Eligibility: headline eligible

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

60.5% percentile inside its fair comparison set

47%Raw benchmark valueCI 40.3% - 53.7%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #24 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 62.4%
Percentile: 48.9%
Last updated: recent
Eligibility: headline eligible

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

48.9% percentile inside its fair comparison set

62.4%Raw benchmark valueCI 59.9% - 64.9%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #10 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 58.9%
Percentile: 72.7%
Last updated: recent
Eligibility: headline eligible

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

72.7% percentile inside its fair comparison set

58.9%Raw benchmark valueCI 50.1% - 67.7%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #6 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 76.2%
Percentile: 96.1%
Last updated: recent
Eligibility: headline eligible

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

96.1% percentile inside its fair comparison set

76.2%Raw benchmark valueCI 74.5% - 77.8%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #16 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 79.3%
Percentile: 76.9%
Last updated: stale
Eligibility: headline eligible

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

76.9% percentile inside its fair comparison set

79.3%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #21 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 77.9%
Percentile: 69.2%
Last updated: stale
Eligibility: headline eligible

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

69.2% percentile inside its fair comparison set

77.9%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #25 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87.7%
Percentile: 63.1%
Last updated: stale
Eligibility: headline eligible

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

63.1% percentile inside its fair comparison set

87.7%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #21 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 50.3%
Percentile: 69.2%
Last updated: stale
Eligibility: headline eligible

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

69.2% percentile inside its fair comparison set

50.3%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #10 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

100% percentile inside its fair comparison set

100%Raw benchmark value

Search / tool use1 benchmark64%

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 #123 · Source label: GPT-5.6 Terra (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 60.5%
Percentile: 64%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

64% percentile inside its fair comparison set

60.5%Raw benchmark value

Long context2 benchmarks65.4%

Long Context Reasoning

AA · Long context · Objective

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

Rank #203 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 58.7%
Percentile: 55.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

55.6% percentile inside its fair comparison set

58.7%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 #30 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.3%
Percentile: 75.2%
Last updated: aging
Eligibility: headline eligible

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

75.2% percentile inside its fair comparison set

65.3%Raw benchmark valueCI 63.5% - 67.1%

Vision understanding16 benchmarks67.2%

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 #110 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 66.7%
Percentile: 47.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

47.6% percentile inside its fair comparison set

66.7%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 #33 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,268
Percentile: 77%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: overall. Source rank: #36. Votes: 10292. Organization: openai. License: Proprietary.

77% percentile inside its fair comparison set

1,268Raw benchmark valueCI 1,261 - 1,276

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 #31 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,257
Percentile: 63.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: creative_writing_vision. Source rank: #36. Votes: 846. Organization: openai. License: Proprietary.

63.4% percentile inside its fair comparison set

1,257Raw benchmark valueCI 1,235 - 1,278

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 #32 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,300
Percentile: 68.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: diagram. Source rank: #35. Votes: 2684. Organization: openai. License: Proprietary.

68.7% percentile inside its fair comparison set

1,300Raw benchmark valueCI 1,288 - 1,312

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 #32 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,270
Percentile: 77.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: english. Source rank: #35. Votes: 3498. Organization: openai. License: Proprietary.

77.5% percentile inside its fair comparison set

1,270Raw benchmark valueCI 1,258 - 1,281

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 #13 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,325
Percentile: 87.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: homework. Source rank: #14. Votes: 1078. Organization: openai. License: Proprietary.

87.5% percentile inside its fair comparison set

1,325Raw benchmark valueCI 1,307 - 1,344

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 #40 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,233
Percentile: 46.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: humor. Source rank: #45. Votes: 457. Organization: openai. License: Proprietary.

46.6% percentile inside its fair comparison set

1,233Raw benchmark valueCI 1,205 - 1,261

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 #37 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,278
Percentile: 64%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: ocr. Source rank: #40. Votes: 7039. Organization: openai. License: Proprietary.

64% percentile inside its fair comparison set

1,278Raw benchmark valueCI 1,270 - 1,286

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-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,271
Percentile: 74.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: overall. Source rank: #40. Votes: 10292. Organization: openai. License: Proprietary.

74.1% percentile inside its fair comparison set

1,271Raw benchmark valueCI 1,264 - 1,279

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 #43 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,251
Percentile: 48.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: creative_writing_vision. Source rank: #48. Votes: 846. Organization: openai. License: Proprietary.

48.8% percentile inside its fair comparison set

1,251Raw benchmark valueCI 1,230 - 1,273

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 #31 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,297
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: diagram. Source rank: #34. Votes: 2684. Organization: openai. License: Proprietary.

69.7% percentile inside its fair comparison set

1,297Raw benchmark valueCI 1,284 - 1,309

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 #39 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,272
Percentile: 72.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: english. Source rank: #42. Votes: 3498. Organization: openai. License: Proprietary.

72.5% percentile inside its fair comparison set

1,272Raw benchmark valueCI 1,261 - 1,284

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 #21 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,317
Percentile: 79.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: homework. Source rank: #23. Votes: 1078. Organization: openai. License: Proprietary.

79.2% percentile inside its fair comparison set

1,317Raw benchmark valueCI 1,299 - 1,335

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 #45 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,233
Percentile: 39.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: humor. Source rank: #50. Votes: 457. Organization: openai. License: Proprietary.

39.7% percentile inside its fair comparison set

1,233Raw benchmark valueCI 1,205 - 1,261

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 #39 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,278
Percentile: 62%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: ocr. Source rank: #42. Votes: 7039. Organization: openai. License: Proprietary.

62% percentile inside its fair comparison set

1,278Raw benchmark valueCI 1,270 - 1,286

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 #20 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.5%
Percentile: 77.1%
Last updated: recent
Eligibility: headline eligible

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

77.1% percentile inside its fair comparison set

86.5%Raw benchmark valueCI 84.9% - 88.1%

Document understanding4 benchmarks66.8%

Document Arena

AR · Document understanding · Human

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

Rank #13 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 70%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: overall. Source rank: #14. Votes: 5787. Organization: openai. License: Proprietary.

70% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,468 - 1,485

Document Arena · No Style Control

AR · Document understanding · Human

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

Rank #12 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 72.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: overall. Source rank: #13. Votes: 5787. Organization: openai. License: Proprietary.

72.5% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,463 - 1,480

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 #26 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67.3%
Percentile: 70.9%
Last updated: recent
Eligibility: headline eligible

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

70.9% percentile inside its fair comparison set

67.3%Raw benchmark valueCI 65.5% - 69.1%

Vals Multimodal Index

VALS-AI · Document understanding · Combined

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

Rank #14 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65
Percentile: 59.4%
Last updated: aging
Eligibility: headline eligible

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

59.4% percentile inside its fair comparison set

65Raw benchmark valueCI 62 - 68

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #34 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,516
Percentile: 90.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: chinese. Source rank: #35. Votes: 2949. Organization: openai. License: Proprietary.

90.6% percentile inside its fair comparison set

1,516Raw benchmark valueCI 1,505 - 1,528

Text Arena · French

AR · Multilingual · Human

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

Rank #28 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 89.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: french. Source rank: #29. Votes: 1146. Organization: openai. License: Proprietary.

89.5% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,476 - 1,514

Text Arena · German

AR · Multilingual · Human

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

Rank #23 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 91.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: german. Source rank: #24. Votes: 592. Organization: openai. License: Proprietary.

91.9% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,458 - 1,507

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #25 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 90.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: japanese. Source rank: #26. Votes: 559. Organization: openai. License: Proprietary.

90.1% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,439 - 1,494

Text Arena · Korean

AR · Multilingual · Human

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

Rank #42 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 83.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: korean. Source rank: #49. Votes: 733. Organization: openai. License: Proprietary.

83.2% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,401 - 1,446

Text Arena · Non English

AR · Multilingual · Human

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

Rank #45 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 88.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: non_english. Source rank: #50. Votes: 22312. Organization: openai. License: Proprietary.

88.3% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,449 - 1,460

Text Arena · Polish

AR · Multilingual · Human

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

Rank #43 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 78.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: polish. Source rank: #50. Votes: 530. Organization: openai. License: Proprietary.

78.9% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,436 - 1,487

Text Arena · Russian

AR · Multilingual · Human

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

Rank #44 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 87.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: russian. Source rank: #50. Votes: 4275. Organization: openai. License: Proprietary.

87.4% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,457 - 1,476

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #44 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 83.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: spanish. Source rank: #48. Votes: 1083. Organization: openai. License: Proprietary.

83.4% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,443 - 1,481

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #33 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,515
Percentile: 90.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: chinese. Source rank: #35. Votes: 2949. Organization: openai. License: Proprietary.

90.9% percentile inside its fair comparison set

1,515Raw benchmark valueCI 1,503 - 1,526

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #35 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 86.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: french. Source rank: #37. Votes: 1146. Organization: openai. License: Proprietary.

86.8% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,454 - 1,492

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #35 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: german. Source rank: #37. Votes: 592. Organization: openai. License: Proprietary.

87.5% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,439 - 1,487

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #28 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 88.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: japanese. Source rank: #31. Votes: 559. Organization: openai. License: Proprietary.

88.9% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,420 - 1,474

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #35 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,425
Percentile: 86.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: korean. Source rank: #38. Votes: 733. Organization: openai. License: Proprietary.

86.1% percentile inside its fair comparison set

1,425Raw benchmark valueCI 1,403 - 1,448

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #47 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 87.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: non_english. Source rank: #51. Votes: 22312. Organization: openai. License: Proprietary.

87.8% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,434 - 1,444

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #48 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 76.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: polish. Source rank: #54. Votes: 530. Organization: openai. License: Proprietary.

76.4% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,420 - 1,470

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #45 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 87.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: russian. Source rank: #50. Votes: 4275. Organization: openai. License: Proprietary.

87.1% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,441 - 1,459

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #53 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 79.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: spanish. Source rank: #56. Votes: 1083. Organization: openai. License: Proprietary.

79.9% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,431 - 1,468

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #26 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,315
Percentile: 76%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: chinese. Source rank: #28. Votes: 613. Organization: openai. License: Proprietary.

76% percentile inside its fair comparison set

1,315Raw benchmark valueCI 1,290 - 1,340

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #25 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,339
Percentile: 76.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: chinese. Source rank: #27. Votes: 613. Organization: openai. License: Proprietary.

76.9% percentile inside its fair comparison set

1,339Raw benchmark valueCI 1,315 - 1,364

Source links and registry checks

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

official

LiveBench

Oct 3, 2026

source →

official

Terminal-Bench

Oct 3, 2026

source →

Model profile · OpenAI

GPT-5.6 Terra

Closed weightspremium · registry tag 2026 balanced

Thin verified coverage

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

Visible coverage: 53.4%
Verified coverage: 53.4%
Spread: 93.2%
Last verified: Oct 3, 2026

62%capability fit

textcodevisiondocumentsearch17 aliases41 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

Chat / text36 benchmarks65.3%

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 #157 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 21
Percentile: 71.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

71.9% percentile inside its fair comparison set

21Raw 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 #100 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 36.8%
Percentile: 78.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

78.1% percentile inside its fair comparison set

36.8%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 #423 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 5%
Percentile: 6.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

6.8% percentile inside its fair comparison set

5%Raw benchmark value

IFBench

AA · Chat / text · Objective

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

Rank #68 · Source label: GPT-5.6 Terra (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 59.7%
Percentile: 80.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

80.7% percentile inside its fair comparison set

59.7%Raw benchmark value

Input price

AA · Chat / text · Speed / cost

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

Rank #272 · Source label: GPT-5.6 Terra (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $2 /1M input tokens
Percentile: 26.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

26.8% percentile inside its fair comparison set

$2 /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 #300 · Source label: GPT-5.6 Terra (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $12 /1M output tokens
Percentile: 15.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

15.5% percentile inside its fair comparison set

$12 /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 #138 · Source label: GPT-5.6 Terra (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 80.4 tokens/s
Percentile: 47.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

47.7% percentile inside its fair comparison set

80.4 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 #258 · Source label: GPT-5.6 Terra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 176.80s
Percentile: 2.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

2.7% percentile inside its fair comparison set

176.80sRaw 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 #256 · Source label: GPT-5.6 Terra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 176.80s
Percentile: 2.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

2.7% percentile inside its fair comparison set

176.80sRaw 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 #47 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 87.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: overall. Source rank: #51. Votes: 37663. Organization: openai. License: Proprietary.

87.8% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,461 - 1,470

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 #69 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,426
Percentile: 81.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: creative_writing. Source rank: #77. Votes: 7957. Organization: openai. License: Proprietary.

81.8% percentile inside its fair comparison set

1,426Raw benchmark valueCI 1,418 - 1,433

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 #54 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,471
Percentile: 85.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: english. Source rank: #58. Votes: 15342. Organization: openai. License: Proprietary.

85.9% percentile inside its fair comparison set

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

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 #47 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 87.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: exclude_ties. Source rank: #51. Votes: 28039. Organization: openai. License: Proprietary.

87.8% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,467 - 1,478

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 #46 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 88%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: hard_prompts. Source rank: #48. Votes: 24754. Organization: openai. License: Proprietary.

88% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,484 - 1,494

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 #53 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 86.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: hard_prompts_english. Source rank: #55. Votes: 9901. Organization: openai. License: Proprietary.

86.1% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,483 - 1,496

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 #45 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,461
Percentile: 88.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: instruction_following. Source rank: #47. Votes: 13418. Organization: openai. License: Proprietary.

88.3% percentile inside its fair comparison set

1,461Raw benchmark valueCI 1,455 - 1,468

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 #61 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 83.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: longer_query. Source rank: #65. Votes: 17693. Organization: openai. License: Proprietary.

83.1% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,460 - 1,472

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 #55 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 85.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: multi_turn. Source rank: #61. Votes: 6154. Organization: openai. License: Proprietary.

85.6% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,461 - 1,478

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 #54 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 85.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: overall. Source rank: #58. Votes: 37663. Organization: openai. License: Proprietary.

85.9% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,442 - 1,451

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 #74 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 80.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: creative_writing. Source rank: #81. Votes: 7957. Organization: openai. License: Proprietary.

80.5% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,401 - 1,416

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 #74 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 80.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: english. Source rank: #79. Votes: 15342. Organization: openai. License: Proprietary.

80.6% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,441 - 1,453

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 #53 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,444
Percentile: 86.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: exclude_ties. Source rank: #57. Votes: 28039. Organization: openai. License: Proprietary.

86.2% percentile inside its fair comparison set

1,444Raw benchmark valueCI 1,438 - 1,449

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 #45 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 88.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: hard_prompts. Source rank: #48. Votes: 24754. Organization: openai. License: Proprietary.

88.3% percentile inside its fair comparison set

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

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 #52 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 86.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: hard_prompts_english. Source rank: #54. Votes: 9901. Organization: openai. License: Proprietary.

86.4% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,457 - 1,471

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 #45 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 88.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: instruction_following. Source rank: #48. Votes: 13418. Organization: openai. License: Proprietary.

88.3% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,447 - 1,459

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 #59 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,451
Percentile: 83.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: longer_query. Source rank: #62. Votes: 17693. Organization: openai. License: Proprietary.

83.7% percentile inside its fair comparison set

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

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 #63 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 83.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: multi_turn. Source rank: #69. Votes: 6154. Organization: openai. License: Proprietary.

83.4% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,442 - 1,459

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 #45 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64.6%
Percentile: 32.3%
Last updated: stale
Eligibility: headline eligible

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

32.3% percentile inside its fair comparison set

64.6%Raw benchmark value

Language

LB · Chat / text · Objective

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

Rank #22 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.9%
Percentile: 67.7%
Last updated: stale
Eligibility: headline eligible

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

67.7% percentile inside its fair comparison set

82.9%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 #58 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 57%
Percentile: 12.3%
Last updated: stale
Eligibility: headline eligible

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

12.3% percentile inside its fair comparison set

57%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 #43 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 61.4%
Percentile: 35.4%
Last updated: stale
Eligibility: headline eligible

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

35.4% percentile inside its fair comparison set

61.4%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 #54 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 66.8%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

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

18.5% percentile inside its fair comparison set

66.8%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 #24 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.2%
Percentile: 64.6%
Last updated: stale
Eligibility: headline eligible

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

64.6% percentile inside its fair comparison set

73.2%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 #53 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 93%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

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

20% percentile inside its fair comparison set

93%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 #17 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 69.7%
Percentile: 75.4%
Last updated: stale
Eligibility: headline eligible

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

75.4% percentile inside its fair comparison set

69.7%Raw benchmark value

Typos

LB · Chat / text · Objective

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

Rank #9 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

89.2% percentile inside its fair comparison set

86%Raw benchmark value

Coding19 benchmarks58.8%

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 #15 · Source label: GPT-5.6 Terra (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43.9%
Percentile: 95.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

95.8% percentile inside its fair comparison set

43.9%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 #112 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 45.1%
Percentile: 43.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

43.9% percentile inside its fair comparison set

45.1%Raw benchmark value

Text Arena · Coding

AR · Coding · Human

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

Rank #44 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,515
Percentile: 88.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: coding. Source rank: #44. Votes: 10166. Organization: openai. License: Proprietary.

88.4% percentile inside its fair comparison set

1,515Raw benchmark valueCI 1,508 - 1,522

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 #47 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 87.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: coding. Source rank: #48. Votes: 10166. Organization: openai. License: Proprietary.

87.6% percentile inside its fair comparison set

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

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 #28 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74.6%
Percentile: 71%
Last updated: recent
Eligibility: headline eligible

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

71% percentile inside its fair comparison set

74.6%Raw benchmark valueCI 66.4% - 82.8%

Code Migration

VALS-AI · Coding · Objective

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

Rank #11 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 47.8%
Percentile: 85.3%
Last updated: recent
Eligibility: headline eligible

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

85.3% percentile inside its fair comparison set

47.8%Raw benchmark valueCI 39.4% - 56.2%

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 #7 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.6%
Percentile: 83.8%
Last updated: recent
Eligibility: headline eligible

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

83.8% percentile inside its fair comparison set

87.6%Raw benchmark valueCI 74.8% - 100.4%

ProgramBench

VALS-AI · Coding · Objective

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

Rank #20 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0.5%
Percentile: 72.4%
Last updated: recent
Eligibility: headline eligible

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

72.4% percentile inside its fair comparison set

0.5%Raw benchmark valueCI 0% - 1.5%

Terminal-Bench 2.1

VALS-AI · Coding · Objective

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

Rank #15 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 77.5%
Percentile: 80.6%
Last updated: recent
Eligibility: headline eligible

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

80.6% percentile inside its fair comparison set

77.5%Raw benchmark valueCI 73.1% - 81.9%

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 #5 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 95.4%
Percentile: 95.1%
Last updated: recent
Eligibility: headline eligible

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

95.1% percentile inside its fair comparison set

95.4%Raw benchmark valueCI 93.6% - 97.2%

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 #27 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.9%
Percentile: 79.2%
Last updated: recent
Eligibility: headline eligible

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

79.2% percentile inside its fair comparison set

85.9%Raw benchmark valueCI 83.9% - 87.9%

Terminal-Bench 4.0

TERMINAL-BENCH · Coding · Objective

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

Rank #21 · Source label: GPT-5.6 Terra (max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 21.5%
Percentile: 23.1%
Last updated: stale
Eligibility: headline eligible

23.1% percentile inside its fair comparison set

21.5%Raw benchmark valueCI 18.3% - 24.8%

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 #28 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 55%
Percentile: 58.5%
Last updated: stale
Eligibility: headline eligible

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

58.5% percentile inside its fair comparison set

55%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 #31 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.2%
Percentile: 53.8%
Last updated: stale
Eligibility: headline eligible

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

53.8% percentile inside its fair comparison set

78.2%Raw benchmark value

JavaScript

LB · Coding · Objective

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

Rank #18 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68.2%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

68.2%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 #19 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 46.7%
Percentile: 72.3%
Last updated: stale
Eligibility: headline eligible

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

72.3% percentile inside its fair comparison set

46.7%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 #44 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

46.2% percentile inside its fair comparison set

50%Raw benchmark value

Coding generation

LB · Coding · Objective

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

Rank #40 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.1%
Percentile: 41.5%
Last updated: stale
Eligibility: headline eligible

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

41.5% percentile inside its fair comparison set

76.1%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 #18 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

78.5% percentile inside its fair comparison set

80.4%Raw benchmark value

Reasoning / math / science18 benchmarks72.5%

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 #209 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11.4%
Percentile: 60.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

60.7% percentile inside its fair comparison set

11.4%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 #186 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 74.6%
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

62.5% percentile inside its fair comparison set

74.6%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 #135 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 2%
Percentile: 70.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

70.7% percentile inside its fair comparison set

2%Raw benchmark value

Text Arena · Math

AR · Reasoning / math / science · Human

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

Rank #34 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,478
Percentile: 90.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: math. Source rank: #36. Votes: 1664. Organization: openai. License: Proprietary.

90.8% percentile inside its fair comparison set

1,478Raw benchmark valueCI 1,464 - 1,493

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 #49 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 86.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: math. Source rank: #51. Votes: 1664. Organization: openai. License: Proprietary.

86.6% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,448 - 1,477

ProofBench

VALS-AI · Reasoning / math / science · Objective

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

Rank #14 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74%
Percentile: 69%
Last updated: recent
Eligibility: headline eligible

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

69% percentile inside its fair comparison set

74%Raw benchmark valueCI 65.4% - 82.6%

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 #24 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 90.9%
Percentile: 81.5%
Last updated: recent
Eligibility: headline eligible

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

81.5% percentile inside its fair comparison set

90.9%Raw benchmark valueCI 87.2% - 94.6%

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 #40 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.7%
Percentile: 68.8%
Last updated: recent
Eligibility: headline eligible

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

68.8% percentile inside its fair comparison set

86.7%Raw benchmark valueCI 86% - 87.3%

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #17 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94.9%
Percentile: 75.4%
Last updated: stale
Eligibility: headline eligible

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

75.4% percentile inside its fair comparison set

94.9%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 #11 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 90.6%
Percentile: 84.6%
Last updated: stale
Eligibility: headline eligible

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

84.6% percentile inside its fair comparison set

90.6%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 #24 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

83.1% percentile inside its fair comparison set

98%Raw benchmark value

Integrals with game

LB · Reasoning / math / science · Objective

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

Rank #16 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 95%
Percentile: 76.9%
Last updated: stale
Eligibility: headline eligible

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

76.9% percentile inside its fair comparison set

95%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 #44 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

49.2% percentile inside its fair comparison set

95.1%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

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

Rank #22 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 91.5%
Percentile: 67.7%
Last updated: stale
Eligibility: headline eligible

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

67.7% percentile inside its fair comparison set

91.5%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 #3 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86.5%
Percentile: 96.9%
Last updated: stale
Eligibility: headline eligible

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

96.9% percentile inside its fair comparison set

86.5%Raw benchmark value

Zebra puzzle

LB · Reasoning / math / science · Objective

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

Rank #3 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

100% percentile inside its fair comparison set

100%Raw benchmark value

Spatial

LB · Reasoning / math / science · Objective

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

Rank #7 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

100% percentile inside its fair comparison set

100%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 #25 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76%
Percentile: 64.6%
Last updated: stale
Eligibility: headline eligible

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

64.6% percentile inside its fair comparison set

76%Raw benchmark value

Professional reasoning35 benchmarks72%

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #4 · Source label: GPT-5.6 Terra (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 38.9%
Percentile: 90.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

90.6% percentile inside its fair comparison set

38.9%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #34 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 89.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: expert. Source rank: #35. Votes: 4391. Organization: openai. License: Proprietary.

89.9% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,495 - 1,514

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 #43 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

88.6% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,459 - 1,475

Text Arena · Industry Entertainment And Sports And Media

AR · Professional reasoning · Human

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

Rank #61 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 84%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_entertainment_and_sports_and_media. Source rank: #68. Votes: 9653. Organization: openai. License: Proprietary.

84% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,424 - 1,439

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #41 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 88.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_legal_and_government. Source rank: #43. Votes: 3229. Organization: openai. License: Proprietary.

88.5% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,466 - 1,488

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 #61 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 84%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_life_and_physical_and_social_science. Source rank: #67. Votes: 6139. Organization: openai. License: Proprietary.

84% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,468 - 1,485

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #32 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 91.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_mathematical. Source rank: #33. Votes: 2121. Organization: openai. License: Proprietary.

91.3% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,475 - 1,502

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #85 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,459
Percentile: 75.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_medicine_and_healthcare. Source rank: #94. Votes: 2718. Organization: openai. License: Proprietary.

75.7% percentile inside its fair comparison set

1,459Raw benchmark valueCI 1,447 - 1,472

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 #44 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 88.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_software_and_it_services. Source rank: #45. Votes: 14645. Organization: openai. License: Proprietary.

88.6% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,499 - 1,511

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 #59 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 84.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_writing_and_literature_and_language. Source rank: #64. Votes: 10426. Organization: openai. License: Proprietary.

84.5% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,438 - 1,451

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #33 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 90.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: expert. Source rank: #34. Votes: 4391. Organization: openai. License: Proprietary.

90.2% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,483 - 1,502

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 #44 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 88.3%
Last updated: recent
Eligibility: headline eligible

88.3% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,440 - 1,455

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 #62 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 83.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_entertainment_and_sports_and_media. Source rank: #68. Votes: 9653. Organization: openai. License: Proprietary.

83.7% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,409 - 1,423

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 #45 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 87.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_legal_and_government. Source rank: #47. Votes: 3229. Organization: openai. License: Proprietary.

87.4% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,453 - 1,475

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 #66 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 82.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_life_and_physical_and_social_science. Source rank: #70. Votes: 6139. Organization: openai. License: Proprietary.

82.6% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,446 - 1,463

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #41 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 88.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_mathematical. Source rank: #43. Votes: 2121. Organization: openai. License: Proprietary.

88.8% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,463 - 1,489

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 #107 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 69.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_medicine_and_healthcare. Source rank: #115. Votes: 2718. Organization: openai. License: Proprietary.

69.4% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,417 - 1,441

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

AR · Professional reasoning · Human

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

Rank #47 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 87.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_software_and_it_services. Source rank: #49. Votes: 14645. Organization: openai. License: Proprietary.

87.8% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,473 - 1,485

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

AR · Professional reasoning · Human

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

Rank #61 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 84%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: industry_writing_and_literature_and_language. Source rank: #66. Votes: 10426. Organization: openai. License: Proprietary.

84% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,422 - 1,436

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #18 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 53
Percentile: 57.5%
Last updated: recent
Eligibility: headline eligible

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

57.5% percentile inside its fair comparison set

53Raw benchmark valueCI 51 - 56

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #21 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 41.3%
Percentile: 72.1%
Last updated: recent
Eligibility: headline eligible

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

72.1% percentile inside its fair comparison set

41.3%Raw benchmark valueCI 34.6% - 48.1%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #52 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0.8%
Percentile: 27.5%
Last updated: recent
Eligibility: headline eligible

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

27.5% percentile inside its fair comparison set

0.8%Raw benchmark valueCI 0% - 2.5%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #24 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.1%
Percentile: 83%
Last updated: recent
Eligibility: headline eligible

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

83% percentile inside its fair comparison set

85.1%Raw benchmark valueCI 84.2% - 86%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #20 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54.4%
Percentile: 72.5%
Last updated: recent
Eligibility: headline eligible

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

72.5% percentile inside its fair comparison set

54.4%Raw benchmark valueCI 50.4% - 58.5%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #43 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 43.4%
Percentile: 55.8%
Last updated: recent
Eligibility: headline eligible

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

55.8% percentile inside its fair comparison set

43.4%Raw benchmark valueCI 39.2% - 47.7%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #48 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82.9%
Percentile: 51%
Last updated: recent
Eligibility: headline eligible

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

51% percentile inside its fair comparison set

82.9%Raw benchmark valueCI 79.1% - 86.7%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #33 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 47%
Percentile: 60.5%
Last updated: recent
Eligibility: headline eligible

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

60.5% percentile inside its fair comparison set

47%Raw benchmark valueCI 40.3% - 53.7%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #24 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 62.4%
Percentile: 48.9%
Last updated: recent
Eligibility: headline eligible

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

48.9% percentile inside its fair comparison set

62.4%Raw benchmark valueCI 59.9% - 64.9%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #10 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 58.9%
Percentile: 72.7%
Last updated: recent
Eligibility: headline eligible

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

72.7% percentile inside its fair comparison set

58.9%Raw benchmark valueCI 50.1% - 67.7%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #6 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 76.2%
Percentile: 96.1%
Last updated: recent
Eligibility: headline eligible

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

96.1% percentile inside its fair comparison set

76.2%Raw benchmark valueCI 74.5% - 77.8%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #16 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 79.3%
Percentile: 76.9%
Last updated: stale
Eligibility: headline eligible

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

76.9% percentile inside its fair comparison set

79.3%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #21 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 77.9%
Percentile: 69.2%
Last updated: stale
Eligibility: headline eligible

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

69.2% percentile inside its fair comparison set

77.9%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #25 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87.7%
Percentile: 63.1%
Last updated: stale
Eligibility: headline eligible

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

63.1% percentile inside its fair comparison set

87.7%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #21 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 50.3%
Percentile: 69.2%
Last updated: stale
Eligibility: headline eligible

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

69.2% percentile inside its fair comparison set

50.3%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #10 · Source label: gpt-5.6-terra-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

100% percentile inside its fair comparison set

100%Raw benchmark value

Search / tool use1 benchmark64%

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 #123 · Source label: GPT-5.6 Terra (Low)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 60.5%
Percentile: 64%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

64% percentile inside its fair comparison set

60.5%Raw benchmark value

Long context2 benchmarks65.4%

Long Context Reasoning

AA · Long context · Objective

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

Rank #203 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 58.7%
Percentile: 55.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

55.6% percentile inside its fair comparison set

58.7%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 #30 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.3%
Percentile: 75.2%
Last updated: aging
Eligibility: headline eligible

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

75.2% percentile inside its fair comparison set

65.3%Raw benchmark valueCI 63.5% - 67.1%

Vision understanding16 benchmarks67.2%

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 #110 · Source label: GPT-5.6 Terra (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 66.7%
Percentile: 47.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

47.6% percentile inside its fair comparison set

66.7%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 #33 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,268
Percentile: 77%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: overall. Source rank: #36. Votes: 10292. Organization: openai. License: Proprietary.

77% percentile inside its fair comparison set

1,268Raw benchmark valueCI 1,261 - 1,276

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 #31 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,257
Percentile: 63.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: creative_writing_vision. Source rank: #36. Votes: 846. Organization: openai. License: Proprietary.

63.4% percentile inside its fair comparison set

1,257Raw benchmark valueCI 1,235 - 1,278

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 #32 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,300
Percentile: 68.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: diagram. Source rank: #35. Votes: 2684. Organization: openai. License: Proprietary.

68.7% percentile inside its fair comparison set

1,300Raw benchmark valueCI 1,288 - 1,312

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 #32 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,270
Percentile: 77.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: english. Source rank: #35. Votes: 3498. Organization: openai. License: Proprietary.

77.5% percentile inside its fair comparison set

1,270Raw benchmark valueCI 1,258 - 1,281

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 #13 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,325
Percentile: 87.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: homework. Source rank: #14. Votes: 1078. Organization: openai. License: Proprietary.

87.5% percentile inside its fair comparison set

1,325Raw benchmark valueCI 1,307 - 1,344

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 #40 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,233
Percentile: 46.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: humor. Source rank: #45. Votes: 457. Organization: openai. License: Proprietary.

46.6% percentile inside its fair comparison set

1,233Raw benchmark valueCI 1,205 - 1,261

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 #37 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,278
Percentile: 64%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: ocr. Source rank: #40. Votes: 7039. Organization: openai. License: Proprietary.

64% percentile inside its fair comparison set

1,278Raw benchmark valueCI 1,270 - 1,286

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-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,271
Percentile: 74.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: overall. Source rank: #40. Votes: 10292. Organization: openai. License: Proprietary.

74.1% percentile inside its fair comparison set

1,271Raw benchmark valueCI 1,264 - 1,279

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 #43 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,251
Percentile: 48.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: creative_writing_vision. Source rank: #48. Votes: 846. Organization: openai. License: Proprietary.

48.8% percentile inside its fair comparison set

1,251Raw benchmark valueCI 1,230 - 1,273

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 #31 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,297
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: diagram. Source rank: #34. Votes: 2684. Organization: openai. License: Proprietary.

69.7% percentile inside its fair comparison set

1,297Raw benchmark valueCI 1,284 - 1,309

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 #39 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,272
Percentile: 72.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: english. Source rank: #42. Votes: 3498. Organization: openai. License: Proprietary.

72.5% percentile inside its fair comparison set

1,272Raw benchmark valueCI 1,261 - 1,284

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 #21 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,317
Percentile: 79.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: homework. Source rank: #23. Votes: 1078. Organization: openai. License: Proprietary.

79.2% percentile inside its fair comparison set

1,317Raw benchmark valueCI 1,299 - 1,335

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 #45 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,233
Percentile: 39.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: humor. Source rank: #50. Votes: 457. Organization: openai. License: Proprietary.

39.7% percentile inside its fair comparison set

1,233Raw benchmark valueCI 1,205 - 1,261

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 #39 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,278
Percentile: 62%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: ocr. Source rank: #42. Votes: 7039. Organization: openai. License: Proprietary.

62% percentile inside its fair comparison set

1,278Raw benchmark valueCI 1,270 - 1,286

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 #20 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.5%
Percentile: 77.1%
Last updated: recent
Eligibility: headline eligible

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

77.1% percentile inside its fair comparison set

86.5%Raw benchmark valueCI 84.9% - 88.1%

Document understanding4 benchmarks66.8%

Document Arena

AR · Document understanding · Human

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

Rank #13 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 70%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: overall. Source rank: #14. Votes: 5787. Organization: openai. License: Proprietary.

70% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,468 - 1,485

Document Arena · No Style Control

AR · Document understanding · Human

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

Rank #12 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 72.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: overall. Source rank: #13. Votes: 5787. Organization: openai. License: Proprietary.

72.5% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,463 - 1,480

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 #26 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67.3%
Percentile: 70.9%
Last updated: recent
Eligibility: headline eligible

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

70.9% percentile inside its fair comparison set

67.3%Raw benchmark valueCI 65.5% - 69.1%

Vals Multimodal Index

VALS-AI · Document understanding · Combined

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

Rank #14 · Source label: openai/gpt-5.6-terra

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65
Percentile: 59.4%
Last updated: aging
Eligibility: headline eligible

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

59.4% percentile inside its fair comparison set

65Raw benchmark valueCI 62 - 68

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #34 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,516
Percentile: 90.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: chinese. Source rank: #35. Votes: 2949. Organization: openai. License: Proprietary.

90.6% percentile inside its fair comparison set

1,516Raw benchmark valueCI 1,505 - 1,528

Text Arena · French

AR · Multilingual · Human

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

Rank #28 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 89.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: french. Source rank: #29. Votes: 1146. Organization: openai. License: Proprietary.

89.5% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,476 - 1,514

Text Arena · German

AR · Multilingual · Human

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

Rank #23 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 91.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: german. Source rank: #24. Votes: 592. Organization: openai. License: Proprietary.

91.9% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,458 - 1,507

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #25 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 90.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: japanese. Source rank: #26. Votes: 559. Organization: openai. License: Proprietary.

90.1% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,439 - 1,494

Text Arena · Korean

AR · Multilingual · Human

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

Rank #42 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 83.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: korean. Source rank: #49. Votes: 733. Organization: openai. License: Proprietary.

83.2% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,401 - 1,446

Text Arena · Non English

AR · Multilingual · Human

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

Rank #45 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 88.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: non_english. Source rank: #50. Votes: 22312. Organization: openai. License: Proprietary.

88.3% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,449 - 1,460

Text Arena · Polish

AR · Multilingual · Human

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

Rank #43 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 78.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: polish. Source rank: #50. Votes: 530. Organization: openai. License: Proprietary.

78.9% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,436 - 1,487

Text Arena · Russian

AR · Multilingual · Human

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

Rank #44 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 87.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: russian. Source rank: #50. Votes: 4275. Organization: openai. License: Proprietary.

87.4% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,457 - 1,476

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #44 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 83.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: spanish. Source rank: #48. Votes: 1083. Organization: openai. License: Proprietary.

83.4% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,443 - 1,481

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #33 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,515
Percentile: 90.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: chinese. Source rank: #35. Votes: 2949. Organization: openai. License: Proprietary.

90.9% percentile inside its fair comparison set

1,515Raw benchmark valueCI 1,503 - 1,526

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #35 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 86.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: french. Source rank: #37. Votes: 1146. Organization: openai. License: Proprietary.

86.8% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,454 - 1,492

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #35 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: german. Source rank: #37. Votes: 592. Organization: openai. License: Proprietary.

87.5% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,439 - 1,487

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #28 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 88.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: japanese. Source rank: #31. Votes: 559. Organization: openai. License: Proprietary.

88.9% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,420 - 1,474

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #35 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,425
Percentile: 86.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: korean. Source rank: #38. Votes: 733. Organization: openai. License: Proprietary.

86.1% percentile inside its fair comparison set

1,425Raw benchmark valueCI 1,403 - 1,448

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #47 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 87.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: non_english. Source rank: #51. Votes: 22312. Organization: openai. License: Proprietary.

87.8% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,434 - 1,444

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #48 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 76.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: polish. Source rank: #54. Votes: 530. Organization: openai. License: Proprietary.

76.4% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,420 - 1,470

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #45 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 87.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: russian. Source rank: #50. Votes: 4275. Organization: openai. License: Proprietary.

87.1% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,441 - 1,459

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #53 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 79.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: spanish. Source rank: #56. Votes: 1083. Organization: openai. License: Proprietary.

79.9% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,431 - 1,468

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #26 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,315
Percentile: 76%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: chinese. Source rank: #28. Votes: 613. Organization: openai. License: Proprietary.

76% percentile inside its fair comparison set

1,315Raw benchmark valueCI 1,290 - 1,340

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #25 · Source label: gpt-5.6-terra-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,339
Percentile: 76.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-terra-xhigh`. Category: chinese. Source rank: #27. Votes: 613. Organization: openai. License: Proprietary.

76.9% percentile inside its fair comparison set

1,339Raw benchmark valueCI 1,315 - 1,364

Source links and registry checks

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

official

LiveBench

Oct 3, 2026

source →

official

Terminal-Bench

Oct 3, 2026

source →

GPT-5.6 Terra

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

GPT-5.6 Terra

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks