Model profile · OpenAI

GPT-5.6 Luna

Closed weightsbudget · registry tag 2026 efficient

Thin verified coverage

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

Visible coverage: 50.7%
Verified coverage: 50.7%
Spread: 100%
Last verified: Oct 3, 2026

52%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 / text35 benchmarks52%

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 #205 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 16
Percentile: 63.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

63.2% percentile inside its fair comparison set

16Raw 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 #131 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 28.6%
Percentile: 71.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

71.3% percentile inside its fair comparison set

28.6%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

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

Rank #379 · Source label: GPT-5.6 Luna (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 7.4%
Percentile: 16.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

16.6% percentile inside its fair comparison set

7.4%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 #99 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.2 /1M input tokens
Percentile: 72.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

72.6% percentile inside its fair comparison set

$0.2 /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 #134 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.2 /1M output tokens
Percentile: 62.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

62.4% percentile inside its fair comparison set

$1.2 /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 #102 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 107.4 tokens/s
Percentile: 61.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

61.5% percentile inside its fair comparison set

107.4 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 #247 · Source label: GPT-5.6 Luna (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 107.35s
Percentile: 6.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

6.8% percentile inside its fair comparison set

107.35sRaw 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 #245 · Source label: GPT-5.6 Luna (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 107.35s
Percentile: 6.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

6.9% percentile inside its fair comparison set

107.35sRaw 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 #68 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 82.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: overall. Source rank: #75. Votes: 38275. Organization: openai. License: Proprietary.

82.2% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,449 - 1,457

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 #84 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 77.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: creative_writing. Source rank: #93. Votes: 7974. Organization: openai. License: Proprietary.

77.8% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,401 - 1,417

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 #60 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 84.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: english. Source rank: #66. Votes: 15530. Organization: openai. License: Proprietary.

84.3% percentile inside its fair comparison set

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

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 #68 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 82.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: exclude_ties. Source rank: #75. Votes: 28693. Organization: openai. License: Proprietary.

82.2% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,450 - 1,461

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 #68 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 82.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: hard_prompts. Source rank: #74. Votes: 25282. Organization: openai. License: Proprietary.

82.2% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,471 - 1,481

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 #58 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 84.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: hard_prompts_english. Source rank: #60. Votes: 10272. Organization: openai. License: Proprietary.

84.8% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,481 - 1,495

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 81.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: instruction_following. Source rank: #74. Votes: 13649. Organization: openai. License: Proprietary.

81.9% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,439 - 1,451

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 #77 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 78.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: longer_query. Source rank: #84. Votes: 18098. Organization: openai. License: Proprietary.

78.6% percentile inside its fair comparison set

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

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 #72 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 81%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: multi_turn. Source rank: #80. Votes: 6163. Organization: openai. License: Proprietary.

81% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,449 - 1,465

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 #85 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 77.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: overall. Source rank: #92. Votes: 38275. Organization: openai. License: Proprietary.

77.7% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,427 - 1,435

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 #98 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,395
Percentile: 74.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: creative_writing. Source rank: #107. Votes: 7974. Organization: openai. License: Proprietary.

74.1% percentile inside its fair comparison set

1,395Raw benchmark valueCI 1,387 - 1,403

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 #85 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 77.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: english. Source rank: #91. Votes: 15530. Organization: openai. License: Proprietary.

77.7% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,435 - 1,447

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 #87 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 77.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: exclude_ties. Source rank: #94. Votes: 28693. Organization: openai. License: Proprietary.

77.1% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,417 - 1,428

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 #64 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 83.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: hard_prompts. Source rank: #67. Votes: 25282. Organization: openai. License: Proprietary.

83.2% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,447 - 1,457

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 #58 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,460
Percentile: 84.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: hard_prompts_english. Source rank: #61. Votes: 10272. Organization: openai. License: Proprietary.

84.8% percentile inside its fair comparison set

1,460Raw benchmark valueCI 1,454 - 1,467

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 #57 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 85.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: instruction_following. Source rank: #60. Votes: 13649. Organization: openai. License: Proprietary.

85.1% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,432 - 1,445

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 #78 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 78.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: longer_query. Source rank: #82. Votes: 18098. Organization: openai. License: Proprietary.

78.3% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,431 - 1,443

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 #87 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 77%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: multi_turn. Source rank: #95. Votes: 6163. Organization: openai. License: Proprietary.

77% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,425 - 1,442

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 #58 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 60.1%
Percentile: 12.3%
Last updated: stale
Eligibility: headline eligible

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

12.3% percentile inside its fair comparison set

60.1%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 #58 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72.6%
Percentile: 12.3%
Last updated: stale
Eligibility: headline eligible

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

12.3% percentile inside its fair comparison set

72.6%Raw benchmark value

Paraphrase

LB · Chat / text · Objective

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

Rank #66 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 47.8%
Percentile: 0%
Last updated: stale
Eligibility: headline eligible

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

0% percentile inside its fair comparison set

47.8%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 #49 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58.7%
Percentile: 26.2%
Last updated: stale
Eligibility: headline eligible

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

26.2% percentile inside its fair comparison set

58.7%Raw benchmark value

Story generation

LB · Chat / text · Objective

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

Rank #45 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 69.1%
Percentile: 32.3%
Last updated: stale
Eligibility: headline eligible

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

32.3% percentile inside its fair comparison set

69.1%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 #52 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64.9%
Percentile: 21.5%
Last updated: stale
Eligibility: headline eligible

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

21.5% percentile inside its fair comparison set

64.9%Raw benchmark value

Connections

LB · Chat / text · Objective

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

Rank #42 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.5%
Percentile: 38.5%
Last updated: stale
Eligibility: headline eligible

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

38.5% percentile inside its fair comparison set

96.5%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 #57 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 51.2%
Percentile: 13.8%
Last updated: stale
Eligibility: headline eligible

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

13.8% percentile inside its fair comparison set

51.2%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 #62 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70%
Percentile: 10.8%
Last updated: stale
Eligibility: headline eligible

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

10.8% percentile inside its fair comparison set

70%Raw benchmark value

Coding17 benchmarks43.4%

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 #137 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 40.4%
Percentile: 31.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

31.3% percentile inside its fair comparison set

40.4%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 #68 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,501
Percentile: 81.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: coding. Source rank: #74. Votes: 10458. Organization: openai. License: Proprietary.

81.9% percentile inside its fair comparison set

1,501Raw benchmark valueCI 1,495 - 1,508

Text Arena · Coding · No Style Control

AR · Coding · Human

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

Rank #70 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 81.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: coding. Source rank: #74. Votes: 10458. Organization: openai. License: Proprietary.

81.4% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,459 - 1,473

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 #25 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 77.1%
Percentile: 74.2%
Last updated: recent
Eligibility: headline eligible

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

74.2% percentile inside its fair comparison set

77.1%Raw benchmark valueCI 71% - 83.1%

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 #19 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 44.6%
Percentile: 73.5%
Last updated: recent
Eligibility: headline eligible

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

73.5% percentile inside its fair comparison set

44.6%Raw benchmark valueCI 36.2% - 52.9%

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 #14 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 61.8%
Percentile: 64.9%
Last updated: recent
Eligibility: headline eligible

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

64.9% percentile inside its fair comparison set

61.8%Raw benchmark valueCI 39% - 84.5%

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 #35 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0%
Percentile: 51.7%
Last updated: recent
Eligibility: headline eligible

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

51.7% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

Terminal-Bench 2.1

VALS-AI · Coding · Objective

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 79%
Percentile: 85.1%
Last updated: recent
Eligibility: headline eligible

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

85.1% percentile inside its fair comparison set

79%Raw benchmark valueCI 77.1% - 81%

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 #9 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 93%
Percentile: 90.2%
Last updated: recent
Eligibility: headline eligible

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

90.2% percentile inside its fair comparison set

93%Raw benchmark valueCI 90.8% - 95.2%

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 #24 · Source label: GPT-5.6 Luna (max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 17.3%
Percentile: 11.5%
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 Luna. Agent URL: https://openai.com/codex/. Reported stderr: 1.454 percentage points.

11.5% percentile inside its fair comparison set

17.3%Raw benchmark valueCI 14.4% - 20.1%

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 #46 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 48.4%
Percentile: 30.8%
Last updated: stale
Eligibility: headline eligible

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

30.8% percentile inside its fair comparison set

48.4%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 #9 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.9%
Percentile: 87.7%
Last updated: stale
Eligibility: headline eligible

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

87.7% percentile inside its fair comparison set

82.9%Raw benchmark value

JavaScript

LB · Coding · Objective

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

Rank #37 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

58.5% percentile inside its fair comparison set

63.6%Raw benchmark value

TypeScript

LB · Coding · Objective

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

Rank #42 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 36.7%
Percentile: 41.5%
Last updated: stale
Eligibility: headline eligible

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

41.5% percentile inside its fair comparison set

36.7%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 #57 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

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

20% percentile inside its fair comparison set

45%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 #29 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.9%
Percentile: 63.1%
Last updated: stale
Eligibility: headline eligible

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

63.1% percentile inside its fair comparison set

78.9%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 #2 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

87%Raw benchmark value

Reasoning / math / science18 benchmarks53.7%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

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

Rank #279 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 7.2%
Percentile: 47.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

47.4% percentile inside its fair comparison set

7.2%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 #268 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 64.5%
Percentile: 45.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

45.8% percentile inside its fair comparison set

64.5%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 #186 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.3%
Percentile: 59.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

59.5% percentile inside its fair comparison set

0.3%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 #37 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: math. Source rank: #39. Votes: 1780. Organization: openai. License: Proprietary.

90% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,463 - 1,491

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 85%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: math. Source rank: #57. Votes: 1780. Organization: openai. License: Proprietary.

85% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,444 - 1,472

ProofBench

VALS-AI · Reasoning / math / science · Objective

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 60%
Percentile: 59.5%
Last updated: recent
Eligibility: headline eligible

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

59.5% percentile inside its fair comparison set

60%Raw benchmark valueCI 50.3% - 69.7%

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 #18 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 91.7%
Percentile: 86.3%
Last updated: recent
Eligibility: headline eligible

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

86.3% percentile inside its fair comparison set

91.7%Raw benchmark valueCI 88.3% - 95.1%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

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

Rank #50 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86%
Percentile: 60.8%
Last updated: recent
Eligibility: headline eligible

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

60.8% percentile inside its fair comparison set

86%Raw benchmark valueCI 85.4% - 86.7%

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #45 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87.2%
Percentile: 32.3%
Last updated: stale
Eligibility: headline eligible

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

32.3% percentile inside its fair comparison set

87.2%Raw benchmark value

Reasoning

LB · Reasoning / math / science · Objective

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

Rank #36 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 85.6%
Percentile: 46.2%
Last updated: stale
Eligibility: headline eligible

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

46.2% percentile inside its fair comparison set

85.6%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 #25 · Source label: gpt-5.6-luna-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 #45 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70%
Percentile: 32.3%
Last updated: stale
Eligibility: headline eligible

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

32.3% percentile inside its fair comparison set

70%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 #63 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 92.2%
Percentile: 6.2%
Last updated: stale
Eligibility: headline eligible

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

6.2% percentile inside its fair comparison set

92.2%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 #46 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 88.6%
Percentile: 30.8%
Last updated: stale
Eligibility: headline eligible

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

30.8% percentile inside its fair comparison set

88.6%Raw benchmark value

Theory of mind

LB · Reasoning / math / science · Objective

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

Rank #53 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.1%
Percentile: 23.1%
Last updated: stale
Eligibility: headline eligible

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

23.1% percentile inside its fair comparison set

73.1%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 #41 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 93.5%
Percentile: 38.5%
Last updated: stale
Eligibility: headline eligible

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

38.5% percentile inside its fair comparison set

93.5%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 #44 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

41.5% percentile inside its fair comparison set

96%Raw benchmark value

Logic with navigation

LB · Reasoning / math / science · Objective

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

80%Raw benchmark value

Professional reasoning35 benchmarks63%

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #7 · Source label: GPT-5.6 Luna (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 35.8%
Percentile: 81.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

81.3% percentile inside its fair comparison set

35.8%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #56 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 83.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: expert. Source rank: #58. Votes: 4355. Organization: openai. License: Proprietary.

83.2% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,482 - 1,501

Text Arena · Industry Business And Management And Financial Operations

AR · Professional reasoning · Human

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

Rank #51 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 86.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_business_and_management_and_financial_operations. Source rank: #54. Votes: 7253. Organization: openai. License: Proprietary.

86.4% percentile inside its fair comparison set

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 80.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_entertainment_and_sports_and_media. Source rank: #82. Votes: 10020. Organization: openai. License: Proprietary.

80.5% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,411 - 1,425

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #67 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 81.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_legal_and_government. Source rank: #74. Votes: 3241. Organization: openai. License: Proprietary.

81.1% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,452 - 1,474

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 #81 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 78.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_life_and_physical_and_social_science. Source rank: #89. Votes: 6193. Organization: openai. License: Proprietary.

78.6% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,453 - 1,470

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #38 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 89.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_mathematical. Source rank: #39. Votes: 2142. Organization: openai. License: Proprietary.

89.6% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,473 - 1,500

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #118 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 66.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_medicine_and_healthcare. Source rank: #132. Votes: 2828. Organization: openai. License: Proprietary.

66.2% percentile inside its fair comparison set

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,493
Percentile: 84%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_software_and_it_services. Source rank: #66. Votes: 14928. Organization: openai. License: Proprietary.

84% percentile inside its fair comparison set

1,493Raw benchmark valueCI 1,487 - 1,499

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 81.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_writing_and_literature_and_language. Source rank: #76. Votes: 10472. Organization: openai. License: Proprietary.

81.9% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,426 - 1,440

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 85.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: expert. Source rank: #50. Votes: 4355. Organization: openai. License: Proprietary.

85.9% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,469 - 1,488

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 #50 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 86.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_business_and_management_and_financial_operations. Source rank: #53. Votes: 7253. Organization: openai. License: Proprietary.

86.7% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,432 - 1,448

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 #83 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 78.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_entertainment_and_sports_and_media. Source rank: #90. Votes: 10020. Organization: openai. License: Proprietary.

78.1% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,395 - 1,409

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 #68 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 80.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_legal_and_government. Source rank: #72. Votes: 3241. Organization: openai. License: Proprietary.

80.8% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,436 - 1,458

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 71.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_life_and_physical_and_social_science. Source rank: #115. Votes: 6193. Organization: openai. License: Proprietary.

71.7% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,426 - 1,442

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 87.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_mathematical. Source rank: #47. Votes: 2142. Organization: openai. License: Proprietary.

87.6% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,458 - 1,485

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 #142 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 59.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_medicine_and_healthcare. Source rank: #158. Votes: 2828. Organization: openai. License: Proprietary.

59.2% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,386 - 1,410

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 82.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_software_and_it_services. Source rank: #69. Votes: 14928. Organization: openai. License: Proprietary.

82.7% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,458 - 1,470

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 #71 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 81.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_writing_and_literature_and_language. Source rank: #77. Votes: 10472. Organization: openai. License: Proprietary.

81.3% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,412 - 1,425

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 52
Percentile: 50%
Last updated: recent
Eligibility: headline eligible

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

50% percentile inside its fair comparison set

52Raw benchmark valueCI 50 - 54

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 36.5%
Percentile: 52.9%
Last updated: recent
Eligibility: headline eligible

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

52.9% percentile inside its fair comparison set

36.5%Raw benchmark valueCI 30% - 43.1%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #49 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 1.3%
Percentile: 31.9%
Last updated: recent
Eligibility: headline eligible

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

31.9% percentile inside its fair comparison set

1.3%Raw benchmark valueCI 0% - 2.9%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #42 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84%
Percentile: 69.6%
Last updated: recent
Eligibility: headline eligible

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

69.6% percentile inside its fair comparison set

84%Raw benchmark valueCI 83.2% - 84.9%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #19 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 55%
Percentile: 73.9%
Last updated: recent
Eligibility: headline eligible

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

73.9% percentile inside its fair comparison set

55%Raw benchmark valueCI 54.4% - 55.6%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #49 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 42.4%
Percentile: 49.5%
Last updated: recent
Eligibility: headline eligible

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

49.5% percentile inside its fair comparison set

42.4%Raw benchmark valueCI 37.9% - 46.8%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.4%
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

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

66.7% percentile inside its fair comparison set

84.4%Raw benchmark valueCI 79.3% - 89.5%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #45 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 44.2%
Percentile: 45.7%
Last updated: recent
Eligibility: headline eligible

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

45.7% percentile inside its fair comparison set

44.2%Raw benchmark valueCI 37.7% - 50.7%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #27 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 61.2%
Percentile: 42.2%
Last updated: recent
Eligibility: headline eligible

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

42.2% percentile inside its fair comparison set

61.2%Raw benchmark valueCI 58.7% - 63.6%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 60.4%
Percentile: 84.8%
Last updated: recent
Eligibility: headline eligible

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

84.8% percentile inside its fair comparison set

60.4%Raw benchmark valueCI 51.1% - 69.8%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #7 · Source label: openai/gpt-5.6-luna

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 #28 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78%
Percentile: 58.5%
Last updated: stale
Eligibility: headline eligible

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

58.5% percentile inside its fair comparison set

78%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #45 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.6%
Percentile: 32.3%
Last updated: stale
Eligibility: headline eligible

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

32.3% percentile inside its fair comparison set

73.6%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #27 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86.5%
Percentile: 60%
Last updated: stale
Eligibility: headline eligible

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

60% percentile inside its fair comparison set

86.5%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #36 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 47.6%
Percentile: 46.2%
Last updated: stale
Eligibility: headline eligible

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

46.2% percentile inside its fair comparison set

47.6%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #11 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

100% percentile inside its fair comparison set

100%Raw benchmark value

Long context2 benchmarks55.4%

Long Context Reasoning

AA · Long context · Objective

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

Rank #255 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 42.7%
Percentile: 44.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

44.2% percentile inside its fair comparison set

42.7%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 #40 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 64.2%
Percentile: 66.7%
Last updated: aging
Eligibility: headline eligible

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

66.7% percentile inside its fair comparison set

64.2%Raw benchmark valueCI 62.4% - 66.1%

Vision understanding16 benchmarks58.1%

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 #144 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 60.3%
Percentile: 31.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

31.3% percentile inside its fair comparison set

60.3%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 #40 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,260
Percentile: 71.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: overall. Source rank: #44. Votes: 10446. Organization: openai. License: Proprietary.

71.9% percentile inside its fair comparison set

1,260Raw benchmark valueCI 1,252 - 1,267

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 #29 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,257
Percentile: 65.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: creative_writing_vision. Source rank: #34. Votes: 912. Organization: openai. License: Proprietary.

65.9% percentile inside its fair comparison set

1,257Raw benchmark valueCI 1,237 - 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 #42 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,281
Percentile: 58.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: diagram. Source rank: #46. Votes: 2612. Organization: openai. License: Proprietary.

58.6% percentile inside its fair comparison set

1,281Raw benchmark valueCI 1,269 - 1,293

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,263
Percentile: 72.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: english. Source rank: #42. Votes: 3561. Organization: openai. License: Proprietary.

72.5% percentile inside its fair comparison set

1,263Raw benchmark valueCI 1,252 - 1,275

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,296
Percentile: 67.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: homework. Source rank: #36. Votes: 1056. Organization: openai. License: Proprietary.

67.7% percentile inside its fair comparison set

1,296Raw benchmark valueCI 1,277 - 1,315

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,195
Percentile: 26%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: humor. Source rank: #64. Votes: 456. Organization: openai. License: Proprietary.

26% percentile inside its fair comparison set

1,195Raw benchmark valueCI 1,166 - 1,224

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 #42 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,269
Percentile: 59%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: ocr. Source rank: #46. Votes: 7056. Organization: openai. License: Proprietary.

59% percentile inside its fair comparison set

1,269Raw benchmark valueCI 1,261 - 1,277

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 #48 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,260
Percentile: 66.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: overall. Source rank: #52. Votes: 10446. Organization: openai. License: Proprietary.

66.2% percentile inside its fair comparison set

1,260Raw benchmark valueCI 1,253 - 1,268

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

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

Rank #38 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,258
Percentile: 54.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: creative_writing_vision. Source rank: #43. Votes: 912. Organization: openai. License: Proprietary.

54.9% percentile inside its fair comparison set

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,275
Percentile: 54.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: diagram. Source rank: #50. Votes: 2612. Organization: openai. License: Proprietary.

54.5% percentile inside its fair comparison set

1,275Raw benchmark valueCI 1,263 - 1,287

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,264
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: english. Source rank: #52. Votes: 3561. Organization: openai. License: Proprietary.

65.2% percentile inside its fair comparison set

1,264Raw benchmark valueCI 1,252 - 1,275

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,290
Percentile: 59.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: homework. Source rank: #44. Votes: 1056. Organization: openai. License: Proprietary.

59.4% percentile inside its fair comparison set

1,290Raw benchmark valueCI 1,271 - 1,308

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,190
Percentile: 16.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: humor. Source rank: #73. Votes: 456. Organization: openai. License: Proprietary.

16.4% percentile inside its fair comparison set

1,190Raw benchmark valueCI 1,161 - 1,218

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,267
Percentile: 52%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: ocr. Source rank: #53. Votes: 7056. Organization: openai. License: Proprietary.

52% percentile inside its fair comparison set

1,267Raw benchmark valueCI 1,259 - 1,275

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 #25 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85%
Percentile: 71.1%
Last updated: recent
Eligibility: headline eligible

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

71.1% percentile inside its fair comparison set

85%Raw benchmark valueCI 83.3% - 86.7%

Document understanding4 benchmarks66.2%

Document Arena

AR · Document understanding · Human

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

Rank #22 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 47.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: overall. Source rank: #23. Votes: 5766. Organization: openai. License: Proprietary.

47.5% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,454 - 1,470

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 50%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: overall. Source rank: #23. Votes: 5766. Organization: openai. License: Proprietary.

50% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,449 - 1,465

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67.3%
Percentile: 69.8%
Last updated: recent
Eligibility: headline eligible

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

69.8% 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 #7 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69
Percentile: 81.3%
Last updated: aging
Eligibility: headline eligible

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

81.3% percentile inside its fair comparison set

69Raw benchmark valueCI 68 - 71

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #93 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 73.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: chinese. Source rank: #100. Votes: 3017. Organization: openai. License: Proprietary.

73.9% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,464 - 1,487

Text Arena · French

AR · Multilingual · Human

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

Rank #46 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 82.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: french. Source rank: #50. Votes: 1212. Organization: openai. License: Proprietary.

82.5% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,464 - 1,501

Text Arena · German

AR · Multilingual · Human

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

Rank #30 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 89.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: german. Source rank: #32. Votes: 655. Organization: openai. License: Proprietary.

89.3% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,452 - 1,500

Text Arena · Japanese

AR · Multilingual · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 80.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: japanese. Source rank: #54. Votes: 573. Organization: openai. License: Proprietary.

80.7% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,403 - 1,457

Text Arena · Korean

AR · Multilingual · Human

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

Rank #56 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 77.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: korean. Source rank: #63. Votes: 712. Organization: openai. License: Proprietary.

77.5% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,391 - 1,437

Text Arena · Non English

AR · Multilingual · Human

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

Rank #74 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 80.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: non_english. Source rank: #81. Votes: 22740. Organization: openai. License: Proprietary.

80.6% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,431 - 1,442

Text Arena · Polish

AR · Multilingual · Human

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

Rank #74 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 63.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: polish. Source rank: #87. Votes: 555. Organization: openai. License: Proprietary.

63.3% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,410 - 1,460

Text Arena · Russian

AR · Multilingual · Human

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

Rank #73 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 78.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: russian. Source rank: #81. Votes: 4356. Organization: openai. License: Proprietary.

78.9% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,439 - 1,458

Text Arena · Spanish

AR · Multilingual · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 83.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: spanish. Source rank: #46. Votes: 1070. Organization: openai. License: Proprietary.

83.8% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,444 - 1,482

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #79 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 77.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: chinese. Source rank: #85. Votes: 3017. Organization: openai. License: Proprietary.

77.8% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,458 - 1,480

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #62 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 76.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: french. Source rank: #66. Votes: 1212. Organization: openai. License: Proprietary.

76.3% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,437 - 1,474

Text Arena · German · No Style Control

AR · Multilingual · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 84.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: german. Source rank: #46. Votes: 655. Organization: openai. License: Proprietary.

84.9% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,430 - 1,478

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #51 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 79.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: japanese. Source rank: #57. Votes: 573. Organization: openai. License: Proprietary.

79.4% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,387 - 1,440

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 83.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: korean. Source rank: #48. Votes: 712. Organization: openai. License: Proprietary.

83.2% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,392 - 1,437

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #86 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 77.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: non_english. Source rank: #93. Votes: 22740. Organization: openai. License: Proprietary.

77.4% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,412 - 1,423

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #102 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 49.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: polish. Source rank: #115. Votes: 555. Organization: openai. License: Proprietary.

49.2% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,379 - 1,430

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #77 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 77.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: russian. Source rank: #83. Votes: 4356. Organization: openai. License: Proprietary.

77.7% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,419 - 1,438

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #64 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 75.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: spanish. Source rank: #67. Votes: 1070. Organization: openai. License: Proprietary.

75.7% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,427 - 1,464

Vision Arena · Chinese

AR · Multilingual · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,279
Percentile: 55.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: chinese. Source rank: #52. Votes: 608. Organization: openai. License: Proprietary.

55.8% percentile inside its fair comparison set

1,279Raw benchmark valueCI 1,253 - 1,304

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,293
Percentile: 54.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: chinese. Source rank: #53. Votes: 608. Organization: openai. License: Proprietary.

54.8% percentile inside its fair comparison set

1,293Raw benchmark valueCI 1,268 - 1,318

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 Luna

Closed weightsbudget · registry tag 2026 efficient

Thin verified coverage

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

Visible coverage: 50.7%
Verified coverage: 50.7%
Spread: 100%
Last verified: Oct 3, 2026

52%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 / text35 benchmarks52%

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 #205 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 16
Percentile: 63.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

63.2% percentile inside its fair comparison set

16Raw 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 #131 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 28.6%
Percentile: 71.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

71.3% percentile inside its fair comparison set

28.6%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

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

Rank #379 · Source label: GPT-5.6 Luna (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 7.4%
Percentile: 16.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

16.6% percentile inside its fair comparison set

7.4%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 #99 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.2 /1M input tokens
Percentile: 72.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

72.6% percentile inside its fair comparison set

$0.2 /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 #134 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.2 /1M output tokens
Percentile: 62.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

62.4% percentile inside its fair comparison set

$1.2 /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 #102 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 107.4 tokens/s
Percentile: 61.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

61.5% percentile inside its fair comparison set

107.4 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 #247 · Source label: GPT-5.6 Luna (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 107.35s
Percentile: 6.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

6.8% percentile inside its fair comparison set

107.35sRaw 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 #245 · Source label: GPT-5.6 Luna (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 107.35s
Percentile: 6.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

6.9% percentile inside its fair comparison set

107.35sRaw 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 #68 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 82.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: overall. Source rank: #75. Votes: 38275. Organization: openai. License: Proprietary.

82.2% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,449 - 1,457

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 #84 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 77.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: creative_writing. Source rank: #93. Votes: 7974. Organization: openai. License: Proprietary.

77.8% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,401 - 1,417

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 #60 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 84.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: english. Source rank: #66. Votes: 15530. Organization: openai. License: Proprietary.

84.3% percentile inside its fair comparison set

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

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 #68 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 82.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: exclude_ties. Source rank: #75. Votes: 28693. Organization: openai. License: Proprietary.

82.2% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,450 - 1,461

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 #68 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 82.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: hard_prompts. Source rank: #74. Votes: 25282. Organization: openai. License: Proprietary.

82.2% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,471 - 1,481

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 #58 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 84.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: hard_prompts_english. Source rank: #60. Votes: 10272. Organization: openai. License: Proprietary.

84.8% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,481 - 1,495

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 81.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: instruction_following. Source rank: #74. Votes: 13649. Organization: openai. License: Proprietary.

81.9% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,439 - 1,451

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 #77 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 78.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: longer_query. Source rank: #84. Votes: 18098. Organization: openai. License: Proprietary.

78.6% percentile inside its fair comparison set

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

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 #72 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 81%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: multi_turn. Source rank: #80. Votes: 6163. Organization: openai. License: Proprietary.

81% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,449 - 1,465

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 #85 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 77.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: overall. Source rank: #92. Votes: 38275. Organization: openai. License: Proprietary.

77.7% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,427 - 1,435

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 #98 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,395
Percentile: 74.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: creative_writing. Source rank: #107. Votes: 7974. Organization: openai. License: Proprietary.

74.1% percentile inside its fair comparison set

1,395Raw benchmark valueCI 1,387 - 1,403

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 #85 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 77.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: english. Source rank: #91. Votes: 15530. Organization: openai. License: Proprietary.

77.7% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,435 - 1,447

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 #87 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 77.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: exclude_ties. Source rank: #94. Votes: 28693. Organization: openai. License: Proprietary.

77.1% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,417 - 1,428

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 #64 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 83.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: hard_prompts. Source rank: #67. Votes: 25282. Organization: openai. License: Proprietary.

83.2% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,447 - 1,457

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 #58 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,460
Percentile: 84.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: hard_prompts_english. Source rank: #61. Votes: 10272. Organization: openai. License: Proprietary.

84.8% percentile inside its fair comparison set

1,460Raw benchmark valueCI 1,454 - 1,467

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 #57 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 85.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: instruction_following. Source rank: #60. Votes: 13649. Organization: openai. License: Proprietary.

85.1% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,432 - 1,445

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 #78 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 78.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: longer_query. Source rank: #82. Votes: 18098. Organization: openai. License: Proprietary.

78.3% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,431 - 1,443

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 #87 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 77%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: multi_turn. Source rank: #95. Votes: 6163. Organization: openai. License: Proprietary.

77% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,425 - 1,442

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 #58 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 60.1%
Percentile: 12.3%
Last updated: stale
Eligibility: headline eligible

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

12.3% percentile inside its fair comparison set

60.1%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 #58 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72.6%
Percentile: 12.3%
Last updated: stale
Eligibility: headline eligible

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

12.3% percentile inside its fair comparison set

72.6%Raw benchmark value

Paraphrase

LB · Chat / text · Objective

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

Rank #66 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 47.8%
Percentile: 0%
Last updated: stale
Eligibility: headline eligible

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

0% percentile inside its fair comparison set

47.8%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 #49 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58.7%
Percentile: 26.2%
Last updated: stale
Eligibility: headline eligible

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

26.2% percentile inside its fair comparison set

58.7%Raw benchmark value

Story generation

LB · Chat / text · Objective

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

Rank #45 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 69.1%
Percentile: 32.3%
Last updated: stale
Eligibility: headline eligible

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

32.3% percentile inside its fair comparison set

69.1%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 #52 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 64.9%
Percentile: 21.5%
Last updated: stale
Eligibility: headline eligible

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

21.5% percentile inside its fair comparison set

64.9%Raw benchmark value

Connections

LB · Chat / text · Objective

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

Rank #42 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.5%
Percentile: 38.5%
Last updated: stale
Eligibility: headline eligible

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

38.5% percentile inside its fair comparison set

96.5%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 #57 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 51.2%
Percentile: 13.8%
Last updated: stale
Eligibility: headline eligible

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

13.8% percentile inside its fair comparison set

51.2%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 #62 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70%
Percentile: 10.8%
Last updated: stale
Eligibility: headline eligible

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

10.8% percentile inside its fair comparison set

70%Raw benchmark value

Coding17 benchmarks43.4%

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 #137 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 40.4%
Percentile: 31.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

31.3% percentile inside its fair comparison set

40.4%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 #68 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,501
Percentile: 81.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: coding. Source rank: #74. Votes: 10458. Organization: openai. License: Proprietary.

81.9% percentile inside its fair comparison set

1,501Raw benchmark valueCI 1,495 - 1,508

Text Arena · Coding · No Style Control

AR · Coding · Human

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

Rank #70 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 81.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: coding. Source rank: #74. Votes: 10458. Organization: openai. License: Proprietary.

81.4% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,459 - 1,473

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 #25 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 77.1%
Percentile: 74.2%
Last updated: recent
Eligibility: headline eligible

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

74.2% percentile inside its fair comparison set

77.1%Raw benchmark valueCI 71% - 83.1%

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 #19 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 44.6%
Percentile: 73.5%
Last updated: recent
Eligibility: headline eligible

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

73.5% percentile inside its fair comparison set

44.6%Raw benchmark valueCI 36.2% - 52.9%

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 #14 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 61.8%
Percentile: 64.9%
Last updated: recent
Eligibility: headline eligible

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

64.9% percentile inside its fair comparison set

61.8%Raw benchmark valueCI 39% - 84.5%

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 #35 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0%
Percentile: 51.7%
Last updated: recent
Eligibility: headline eligible

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

51.7% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

Terminal-Bench 2.1

VALS-AI · Coding · Objective

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 79%
Percentile: 85.1%
Last updated: recent
Eligibility: headline eligible

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

85.1% percentile inside its fair comparison set

79%Raw benchmark valueCI 77.1% - 81%

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 #9 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 93%
Percentile: 90.2%
Last updated: recent
Eligibility: headline eligible

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

90.2% percentile inside its fair comparison set

93%Raw benchmark valueCI 90.8% - 95.2%

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 #24 · Source label: GPT-5.6 Luna (max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 17.3%
Percentile: 11.5%
Last updated: stale
Eligibility: headline eligible

11.5% percentile inside its fair comparison set

17.3%Raw benchmark valueCI 14.4% - 20.1%

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 #46 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 48.4%
Percentile: 30.8%
Last updated: stale
Eligibility: headline eligible

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

30.8% percentile inside its fair comparison set

48.4%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 #9 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.9%
Percentile: 87.7%
Last updated: stale
Eligibility: headline eligible

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

87.7% percentile inside its fair comparison set

82.9%Raw benchmark value

JavaScript

LB · Coding · Objective

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

Rank #37 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

58.5% percentile inside its fair comparison set

63.6%Raw benchmark value

TypeScript

LB · Coding · Objective

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

Rank #42 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 36.7%
Percentile: 41.5%
Last updated: stale
Eligibility: headline eligible

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

41.5% percentile inside its fair comparison set

36.7%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 #57 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

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

20% percentile inside its fair comparison set

45%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 #29 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.9%
Percentile: 63.1%
Last updated: stale
Eligibility: headline eligible

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

63.1% percentile inside its fair comparison set

78.9%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 #2 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

87%Raw benchmark value

Reasoning / math / science18 benchmarks53.7%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

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

Rank #279 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 7.2%
Percentile: 47.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

47.4% percentile inside its fair comparison set

7.2%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 #268 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 64.5%
Percentile: 45.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

45.8% percentile inside its fair comparison set

64.5%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 #186 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.3%
Percentile: 59.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

59.5% percentile inside its fair comparison set

0.3%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 #37 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: math. Source rank: #39. Votes: 1780. Organization: openai. License: Proprietary.

90% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,463 - 1,491

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 85%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: math. Source rank: #57. Votes: 1780. Organization: openai. License: Proprietary.

85% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,444 - 1,472

ProofBench

VALS-AI · Reasoning / math / science · Objective

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 60%
Percentile: 59.5%
Last updated: recent
Eligibility: headline eligible

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

59.5% percentile inside its fair comparison set

60%Raw benchmark valueCI 50.3% - 69.7%

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 #18 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 91.7%
Percentile: 86.3%
Last updated: recent
Eligibility: headline eligible

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

86.3% percentile inside its fair comparison set

91.7%Raw benchmark valueCI 88.3% - 95.1%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

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

Rank #50 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86%
Percentile: 60.8%
Last updated: recent
Eligibility: headline eligible

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

60.8% percentile inside its fair comparison set

86%Raw benchmark valueCI 85.4% - 86.7%

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #45 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87.2%
Percentile: 32.3%
Last updated: stale
Eligibility: headline eligible

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

32.3% percentile inside its fair comparison set

87.2%Raw benchmark value

Reasoning

LB · Reasoning / math / science · Objective

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

Rank #36 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 85.6%
Percentile: 46.2%
Last updated: stale
Eligibility: headline eligible

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

46.2% percentile inside its fair comparison set

85.6%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 #25 · Source label: gpt-5.6-luna-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 #45 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70%
Percentile: 32.3%
Last updated: stale
Eligibility: headline eligible

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

32.3% percentile inside its fair comparison set

70%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 #63 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 92.2%
Percentile: 6.2%
Last updated: stale
Eligibility: headline eligible

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

6.2% percentile inside its fair comparison set

92.2%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 #46 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 88.6%
Percentile: 30.8%
Last updated: stale
Eligibility: headline eligible

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

30.8% percentile inside its fair comparison set

88.6%Raw benchmark value

Theory of mind

LB · Reasoning / math / science · Objective

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

Rank #53 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.1%
Percentile: 23.1%
Last updated: stale
Eligibility: headline eligible

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

23.1% percentile inside its fair comparison set

73.1%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 #41 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 93.5%
Percentile: 38.5%
Last updated: stale
Eligibility: headline eligible

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

38.5% percentile inside its fair comparison set

93.5%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 #44 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

41.5% percentile inside its fair comparison set

96%Raw benchmark value

Logic with navigation

LB · Reasoning / math / science · Objective

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

80%Raw benchmark value

Professional reasoning35 benchmarks63%

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #7 · Source label: GPT-5.6 Luna (Max)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 35.8%
Percentile: 81.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

81.3% percentile inside its fair comparison set

35.8%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #56 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 83.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: expert. Source rank: #58. Votes: 4355. Organization: openai. License: Proprietary.

83.2% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,482 - 1,501

Text Arena · Industry Business And Management And Financial Operations

AR · Professional reasoning · Human

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

Rank #51 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 86.4%
Last updated: recent
Eligibility: headline eligible

86.4% percentile inside its fair comparison set

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 80.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_entertainment_and_sports_and_media. Source rank: #82. Votes: 10020. Organization: openai. License: Proprietary.

80.5% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,411 - 1,425

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #67 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 81.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_legal_and_government. Source rank: #74. Votes: 3241. Organization: openai. License: Proprietary.

81.1% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,452 - 1,474

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 #81 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 78.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_life_and_physical_and_social_science. Source rank: #89. Votes: 6193. Organization: openai. License: Proprietary.

78.6% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,453 - 1,470

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #38 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 89.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_mathematical. Source rank: #39. Votes: 2142. Organization: openai. License: Proprietary.

89.6% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,473 - 1,500

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #118 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 66.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_medicine_and_healthcare. Source rank: #132. Votes: 2828. Organization: openai. License: Proprietary.

66.2% percentile inside its fair comparison set

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,493
Percentile: 84%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_software_and_it_services. Source rank: #66. Votes: 14928. Organization: openai. License: Proprietary.

84% percentile inside its fair comparison set

1,493Raw benchmark valueCI 1,487 - 1,499

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 81.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_writing_and_literature_and_language. Source rank: #76. Votes: 10472. Organization: openai. License: Proprietary.

81.9% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,426 - 1,440

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 85.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: expert. Source rank: #50. Votes: 4355. Organization: openai. License: Proprietary.

85.9% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,469 - 1,488

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 #50 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 86.7%
Last updated: recent
Eligibility: headline eligible

86.7% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,432 - 1,448

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 #83 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 78.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_entertainment_and_sports_and_media. Source rank: #90. Votes: 10020. Organization: openai. License: Proprietary.

78.1% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,395 - 1,409

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 #68 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 80.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_legal_and_government. Source rank: #72. Votes: 3241. Organization: openai. License: Proprietary.

80.8% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,436 - 1,458

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 71.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_life_and_physical_and_social_science. Source rank: #115. Votes: 6193. Organization: openai. License: Proprietary.

71.7% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,426 - 1,442

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 87.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_mathematical. Source rank: #47. Votes: 2142. Organization: openai. License: Proprietary.

87.6% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,458 - 1,485

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 #142 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 59.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_medicine_and_healthcare. Source rank: #158. Votes: 2828. Organization: openai. License: Proprietary.

59.2% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,386 - 1,410

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 82.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_software_and_it_services. Source rank: #69. Votes: 14928. Organization: openai. License: Proprietary.

82.7% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,458 - 1,470

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 #71 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 81.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: industry_writing_and_literature_and_language. Source rank: #77. Votes: 10472. Organization: openai. License: Proprietary.

81.3% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,412 - 1,425

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 52
Percentile: 50%
Last updated: recent
Eligibility: headline eligible

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

50% percentile inside its fair comparison set

52Raw benchmark valueCI 50 - 54

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 36.5%
Percentile: 52.9%
Last updated: recent
Eligibility: headline eligible

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

52.9% percentile inside its fair comparison set

36.5%Raw benchmark valueCI 30% - 43.1%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #49 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 1.3%
Percentile: 31.9%
Last updated: recent
Eligibility: headline eligible

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

31.9% percentile inside its fair comparison set

1.3%Raw benchmark valueCI 0% - 2.9%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #42 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84%
Percentile: 69.6%
Last updated: recent
Eligibility: headline eligible

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

69.6% percentile inside its fair comparison set

84%Raw benchmark valueCI 83.2% - 84.9%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #19 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 55%
Percentile: 73.9%
Last updated: recent
Eligibility: headline eligible

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

73.9% percentile inside its fair comparison set

55%Raw benchmark valueCI 54.4% - 55.6%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #49 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 42.4%
Percentile: 49.5%
Last updated: recent
Eligibility: headline eligible

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

49.5% percentile inside its fair comparison set

42.4%Raw benchmark valueCI 37.9% - 46.8%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.4%
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

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

66.7% percentile inside its fair comparison set

84.4%Raw benchmark valueCI 79.3% - 89.5%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #45 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 44.2%
Percentile: 45.7%
Last updated: recent
Eligibility: headline eligible

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

45.7% percentile inside its fair comparison set

44.2%Raw benchmark valueCI 37.7% - 50.7%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #27 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 61.2%
Percentile: 42.2%
Last updated: recent
Eligibility: headline eligible

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

42.2% percentile inside its fair comparison set

61.2%Raw benchmark valueCI 58.7% - 63.6%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 60.4%
Percentile: 84.8%
Last updated: recent
Eligibility: headline eligible

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

84.8% percentile inside its fair comparison set

60.4%Raw benchmark valueCI 51.1% - 69.8%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #7 · Source label: openai/gpt-5.6-luna

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 #28 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78%
Percentile: 58.5%
Last updated: stale
Eligibility: headline eligible

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

58.5% percentile inside its fair comparison set

78%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #45 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.6%
Percentile: 32.3%
Last updated: stale
Eligibility: headline eligible

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

32.3% percentile inside its fair comparison set

73.6%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #27 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 86.5%
Percentile: 60%
Last updated: stale
Eligibility: headline eligible

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

60% percentile inside its fair comparison set

86.5%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #36 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 47.6%
Percentile: 46.2%
Last updated: stale
Eligibility: headline eligible

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

46.2% percentile inside its fair comparison set

47.6%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #11 · Source label: gpt-5.6-luna-max

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

100% percentile inside its fair comparison set

100%Raw benchmark value

Long context2 benchmarks55.4%

Long Context Reasoning

AA · Long context · Objective

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

Rank #255 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 42.7%
Percentile: 44.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

44.2% percentile inside its fair comparison set

42.7%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 #40 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 64.2%
Percentile: 66.7%
Last updated: aging
Eligibility: headline eligible

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

66.7% percentile inside its fair comparison set

64.2%Raw benchmark valueCI 62.4% - 66.1%

Vision understanding16 benchmarks58.1%

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 #144 · Source label: GPT-5.6 Luna (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 60.3%
Percentile: 31.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

31.3% percentile inside its fair comparison set

60.3%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 #40 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,260
Percentile: 71.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: overall. Source rank: #44. Votes: 10446. Organization: openai. License: Proprietary.

71.9% percentile inside its fair comparison set

1,260Raw benchmark valueCI 1,252 - 1,267

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 #29 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,257
Percentile: 65.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: creative_writing_vision. Source rank: #34. Votes: 912. Organization: openai. License: Proprietary.

65.9% percentile inside its fair comparison set

1,257Raw benchmark valueCI 1,237 - 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 #42 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,281
Percentile: 58.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: diagram. Source rank: #46. Votes: 2612. Organization: openai. License: Proprietary.

58.6% percentile inside its fair comparison set

1,281Raw benchmark valueCI 1,269 - 1,293

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,263
Percentile: 72.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: english. Source rank: #42. Votes: 3561. Organization: openai. License: Proprietary.

72.5% percentile inside its fair comparison set

1,263Raw benchmark valueCI 1,252 - 1,275

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,296
Percentile: 67.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: homework. Source rank: #36. Votes: 1056. Organization: openai. License: Proprietary.

67.7% percentile inside its fair comparison set

1,296Raw benchmark valueCI 1,277 - 1,315

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,195
Percentile: 26%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: humor. Source rank: #64. Votes: 456. Organization: openai. License: Proprietary.

26% percentile inside its fair comparison set

1,195Raw benchmark valueCI 1,166 - 1,224

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 #42 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,269
Percentile: 59%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: ocr. Source rank: #46. Votes: 7056. Organization: openai. License: Proprietary.

59% percentile inside its fair comparison set

1,269Raw benchmark valueCI 1,261 - 1,277

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 #48 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,260
Percentile: 66.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: overall. Source rank: #52. Votes: 10446. Organization: openai. License: Proprietary.

66.2% percentile inside its fair comparison set

1,260Raw benchmark valueCI 1,253 - 1,268

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

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

Rank #38 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,258
Percentile: 54.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: creative_writing_vision. Source rank: #43. Votes: 912. Organization: openai. License: Proprietary.

54.9% percentile inside its fair comparison set

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,275
Percentile: 54.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: diagram. Source rank: #50. Votes: 2612. Organization: openai. License: Proprietary.

54.5% percentile inside its fair comparison set

1,275Raw benchmark valueCI 1,263 - 1,287

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,264
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: english. Source rank: #52. Votes: 3561. Organization: openai. License: Proprietary.

65.2% percentile inside its fair comparison set

1,264Raw benchmark valueCI 1,252 - 1,275

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,290
Percentile: 59.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: homework. Source rank: #44. Votes: 1056. Organization: openai. License: Proprietary.

59.4% percentile inside its fair comparison set

1,290Raw benchmark valueCI 1,271 - 1,308

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,190
Percentile: 16.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: humor. Source rank: #73. Votes: 456. Organization: openai. License: Proprietary.

16.4% percentile inside its fair comparison set

1,190Raw benchmark valueCI 1,161 - 1,218

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,267
Percentile: 52%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: ocr. Source rank: #53. Votes: 7056. Organization: openai. License: Proprietary.

52% percentile inside its fair comparison set

1,267Raw benchmark valueCI 1,259 - 1,275

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 #25 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85%
Percentile: 71.1%
Last updated: recent
Eligibility: headline eligible

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

71.1% percentile inside its fair comparison set

85%Raw benchmark valueCI 83.3% - 86.7%

Document understanding4 benchmarks66.2%

Document Arena

AR · Document understanding · Human

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

Rank #22 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 47.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: overall. Source rank: #23. Votes: 5766. Organization: openai. License: Proprietary.

47.5% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,454 - 1,470

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 50%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: overall. Source rank: #23. Votes: 5766. Organization: openai. License: Proprietary.

50% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,449 - 1,465

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67.3%
Percentile: 69.8%
Last updated: recent
Eligibility: headline eligible

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

69.8% 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 #7 · Source label: openai/gpt-5.6-luna

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69
Percentile: 81.3%
Last updated: aging
Eligibility: headline eligible

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

81.3% percentile inside its fair comparison set

69Raw benchmark valueCI 68 - 71

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #93 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 73.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: chinese. Source rank: #100. Votes: 3017. Organization: openai. License: Proprietary.

73.9% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,464 - 1,487

Text Arena · French

AR · Multilingual · Human

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

Rank #46 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 82.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: french. Source rank: #50. Votes: 1212. Organization: openai. License: Proprietary.

82.5% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,464 - 1,501

Text Arena · German

AR · Multilingual · Human

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

Rank #30 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 89.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: german. Source rank: #32. Votes: 655. Organization: openai. License: Proprietary.

89.3% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,452 - 1,500

Text Arena · Japanese

AR · Multilingual · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 80.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: japanese. Source rank: #54. Votes: 573. Organization: openai. License: Proprietary.

80.7% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,403 - 1,457

Text Arena · Korean

AR · Multilingual · Human

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

Rank #56 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 77.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: korean. Source rank: #63. Votes: 712. Organization: openai. License: Proprietary.

77.5% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,391 - 1,437

Text Arena · Non English

AR · Multilingual · Human

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

Rank #74 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 80.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: non_english. Source rank: #81. Votes: 22740. Organization: openai. License: Proprietary.

80.6% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,431 - 1,442

Text Arena · Polish

AR · Multilingual · Human

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

Rank #74 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 63.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: polish. Source rank: #87. Votes: 555. Organization: openai. License: Proprietary.

63.3% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,410 - 1,460

Text Arena · Russian

AR · Multilingual · Human

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

Rank #73 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 78.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: russian. Source rank: #81. Votes: 4356. Organization: openai. License: Proprietary.

78.9% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,439 - 1,458

Text Arena · Spanish

AR · Multilingual · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 83.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: spanish. Source rank: #46. Votes: 1070. Organization: openai. License: Proprietary.

83.8% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,444 - 1,482

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #79 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 77.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: chinese. Source rank: #85. Votes: 3017. Organization: openai. License: Proprietary.

77.8% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,458 - 1,480

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #62 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 76.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: french. Source rank: #66. Votes: 1212. Organization: openai. License: Proprietary.

76.3% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,437 - 1,474

Text Arena · German · No Style Control

AR · Multilingual · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 84.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: german. Source rank: #46. Votes: 655. Organization: openai. License: Proprietary.

84.9% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,430 - 1,478

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #51 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 79.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: japanese. Source rank: #57. Votes: 573. Organization: openai. License: Proprietary.

79.4% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,387 - 1,440

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 83.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: korean. Source rank: #48. Votes: 712. Organization: openai. License: Proprietary.

83.2% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,392 - 1,437

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #86 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 77.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: non_english. Source rank: #93. Votes: 22740. Organization: openai. License: Proprietary.

77.4% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,412 - 1,423

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #102 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 49.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: polish. Source rank: #115. Votes: 555. Organization: openai. License: Proprietary.

49.2% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,379 - 1,430

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #77 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 77.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: russian. Source rank: #83. Votes: 4356. Organization: openai. License: Proprietary.

77.7% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,419 - 1,438

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #64 · Source label: gpt-5.6-luna-xhigh

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 75.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: spanish. Source rank: #67. Votes: 1070. Organization: openai. License: Proprietary.

75.7% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,427 - 1,464

Vision Arena · Chinese

AR · Multilingual · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,279
Percentile: 55.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: chinese. Source rank: #52. Votes: 608. Organization: openai. License: Proprietary.

55.8% percentile inside its fair comparison set

1,279Raw benchmark valueCI 1,253 - 1,304

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

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

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,293
Percentile: 54.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gpt-5.6-luna-xhigh`. Category: chinese. Source rank: #53. Votes: 608. Organization: openai. License: Proprietary.

54.8% percentile inside its fair comparison set

1,293Raw benchmark valueCI 1,268 - 1,318

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 Luna

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

GPT-5.6 Luna

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks