Model profile · OpenAI

GPT-4.1

Closed weightspremium · registry tag 2025 historical workhorse

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 19.2%
Verified coverage: 19.2%
Spread: n/a
Last verified: Jun 20, 2026

textcodevisiondocument4 aliases39 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

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

Chat / text28 benchmarks66.7%

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 #126 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 19
Percentile: 68.4%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

68.4% percentile inside its fair comparison set

19Raw 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 #68 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24.2%
Percentile: 77.5%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

77.5% percentile inside its fair comparison set

24.2%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 #109 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 20.4%
Percentile: 63.8%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

63.8% percentile inside its fair comparison set

20.4%Raw benchmark value

IFBench

AA · Chat / text · Objective

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

Rank #145 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43%
Percentile: 55.2%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

55.2% percentile inside its fair comparison set

43%Raw benchmark value

Blended price

AA · Chat / text · Speed / cost

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

Rank #235 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $3.5 /1M tokens
Percentile: 16.3%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

16.3% percentile inside its fair comparison set

$3.5 /1M tokensRaw benchmark value

Input price

AA · Chat / text · Speed / cost

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

Rank #236 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $2 /1M input tokens
Percentile: 17.8%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

17.8% percentile inside its fair comparison set

$2 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

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

Rank #229 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $8 /1M output tokens
Percentile: 18.5%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

18.5% percentile inside its fair comparison set

$8 /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 #64 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 137.7 tokens/s
Percentile: 70%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

70% percentile inside its fair comparison set

137.7 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

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

Rank #31 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.93s
Percentile: 85.7%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

85.7% percentile inside its fair comparison set

0.93sRaw 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 #19 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.93s
Percentile: 91.4%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

91.4% percentile inside its fair comparison set

0.93sRaw 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 #83 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 74.8%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: overall. Source rank: #102. Votes: 50981. Organization: openai. License: Proprietary.

74.8% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,410 - 1,417

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 #58 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 82.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: creative_writing. Source rank: #72. Votes: 6701. Organization: openai. License: Proprietary.

82.4% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,394 - 1,410

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 #87 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 73.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: english. Source rank: #107. Votes: 25688. Organization: openai. License: Proprietary.

73.5% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,417 - 1,427

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 #81 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 75.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: exclude_ties. Source rank: #100. Votes: 36223. Organization: openai. License: Proprietary.

75.4% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,397 - 1,407

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 #84 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 74.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: hard_prompts. Source rank: #104. Votes: 22164. Organization: openai. License: Proprietary.

74.5% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,426 - 1,436

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 #86 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 73.8%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: hard_prompts_english. Source rank: #105. Votes: 11905. Organization: openai. License: Proprietary.

73.8% percentile inside its fair comparison set

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

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 #80 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,403
Percentile: 75.7%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: instruction_following. Source rank: #99. Votes: 13289. Organization: openai. License: Proprietary.

75.7% percentile inside its fair comparison set

1,403Raw benchmark valueCI 1,397 - 1,408

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 #76 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 75.3%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: longer_query. Source rank: #96. Votes: 9823. Organization: openai. License: Proprietary.

75.3% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,418 - 1,431

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 #62 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 81.1%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: multi_turn. Source rank: #79. Votes: 8958. Organization: openai. License: Proprietary.

81.1% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,423 - 1,437

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 #105 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 68%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: overall. Source rank: #127. Votes: 50981. Organization: openai. License: Proprietary.

68% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,378 - 1,386

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 #91 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,364
Percentile: 72.1%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: creative_writing. Source rank: #112. Votes: 6701. Organization: openai. License: Proprietary.

72.1% percentile inside its fair comparison set

1,364Raw benchmark valueCI 1,356 - 1,371

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 #108 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 67.1%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: english. Source rank: #129. Votes: 25688. Organization: openai. License: Proprietary.

67.1% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,386 - 1,395

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 #105 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,355
Percentile: 68%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: exclude_ties. Source rank: #127. Votes: 36223. Organization: openai. License: Proprietary.

68% percentile inside its fair comparison set

1,355Raw benchmark valueCI 1,350 - 1,360

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 #107 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 67.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: hard_prompts. Source rank: #129. Votes: 22164. Organization: openai. License: Proprietary.

67.4% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,378 - 1,387

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 #107 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 67.3%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: hard_prompts_english. Source rank: #129. Votes: 11905. Organization: openai. License: Proprietary.

67.3% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,384 - 1,396

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 #105 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,366
Percentile: 68%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: instruction_following. Source rank: #128. Votes: 13289. Organization: openai. License: Proprietary.

68% percentile inside its fair comparison set

1,366Raw benchmark valueCI 1,361 - 1,372

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 #103 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,383
Percentile: 66.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: longer_query. Source rank: #126. Votes: 9823. Organization: openai. License: Proprietary.

66.4% percentile inside its fair comparison set

1,383Raw benchmark valueCI 1,376 - 1,389

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 #93 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 71.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: multi_turn. Source rank: #113. Votes: 8958. Organization: openai. License: Proprietary.

71.5% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,390 - 1,404

Coding5 benchmarks58.9%

Terminal-Bench Hard

AA · Coding · Objective

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

Rank #131 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 13.6%
Percentile: 57%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

57% percentile inside its fair comparison set

13.6%Raw benchmark value

SciCode

AA · Coding · Objective

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

Rank #84 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 38.1%
Percentile: 77.4%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `scicode`.

77.4% percentile inside its fair comparison set

38.1%Raw benchmark value

LiveCodeBench

VALS-AI · Coding · Objective

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

Rank #71 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54.7%
Percentile: 22.2%
Last updated: recent
Eligibility: historical_model

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

22.2% percentile inside its fair comparison set

54.7%Raw benchmark valueCI 52.5% - 56.9%

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 #86 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 73.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: coding. Source rank: #106. Votes: 9314. Organization: openai. License: Proprietary.

73.4% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,450 - 1,463

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 #114 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 64.7%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: coding. Source rank: #138. Votes: 9314. Organization: openai. License: Proprietary.

64.7% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,384 - 1,397

Reasoning / math / science7 benchmarks47.7%

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 #265 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 4.6%
Percentile: 28.9%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `hle`.

28.9% percentile inside its fair comparison set

4.6%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

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

Rank #163 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 66.6%
Percentile: 56.7%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

56.7% percentile inside its fair comparison set

66.6%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

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

Rank #237 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

Parsed from Artificial Analysis public leaderboard field `critpt`.

65.2% percentile inside its fair comparison set

0%Raw benchmark value

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 #68 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.4%
Percentile: 24.7%
Last updated: recent
Eligibility: historical_model

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

24.7% percentile inside its fair comparison set

65.4%Raw benchmark valueCI 60.7% - 70.1%

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 #56 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 80.5%
Percentile: 38.2%
Last updated: recent
Eligibility: historical_model

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

38.2% percentile inside its fair comparison set

80.5%Raw benchmark valueCI 79.7% - 81.2%

Text Arena · Math

AR · Reasoning / math / science · Human

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

Rank #126 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,373
Percentile: 60.2%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: math. Source rank: #151. Votes: 3226. Organization: openai. License: Proprietary.

60.2% percentile inside its fair comparison set

1,373Raw benchmark valueCI 1,363 - 1,383

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 #127 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,367
Percentile: 59.9%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: math. Source rank: #153. Votes: 3226. Organization: openai. License: Proprietary.

59.9% percentile inside its fair comparison set

1,367Raw benchmark valueCI 1,357 - 1,377

Professional reasoning20 benchmarks69.6%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #35 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.1%
Percentile: 62.2%
Last updated: recent
Eligibility: historical_model

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

62.2% percentile inside its fair comparison set

83.1%Raw benchmark valueCI 82.3% - 83.9%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #12 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 75.1%
Percentile: 87.9%
Last updated: recent
Eligibility: historical_model

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

87.9% percentile inside its fair comparison set

75.1%Raw benchmark valueCI 73.4% - 76.7%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #102 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 63.3%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: expert. Source rank: #125. Votes: 2508. Organization: openai. License: Proprietary.

63.3% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,394 - 1,418

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 #75 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 76.7%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_business_and_management_and_financial_operations. Source rank: #92. Votes: 8287. Organization: openai. License: Proprietary.

76.7% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,408 - 1,422

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 #58 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 82.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_entertainment_and_sports_and_media. Source rank: #71. Votes: 9064. Organization: openai. License: Proprietary.

82.4% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,393 - 1,406

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #60 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 80.2%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_legal_and_government. Source rank: #78. Votes: 3276. Organization: openai. License: Proprietary.

80.2% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,427 - 1,448

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 #89 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 72.8%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_life_and_physical_and_social_science. Source rank: #111. Votes: 8544. Organization: openai. License: Proprietary.

72.8% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,417 - 1,431

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #126 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,372
Percentile: 59.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_mathematical. Source rank: #152. Votes: 3056. Organization: openai. License: Proprietary.

59.4% percentile inside its fair comparison set

1,372Raw benchmark valueCI 1,362 - 1,383

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #88 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 70.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_medicine_and_healthcare. Source rank: #108. Votes: 2801. Organization: openai. License: Proprietary.

70.5% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,421 - 1,444

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 #89 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 72.9%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_software_and_it_services. Source rank: #108. Votes: 16826. Organization: openai. License: Proprietary.

72.9% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,437 - 1,448

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 #66 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 79.9%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_writing_and_literature_and_language. Source rank: #84. Votes: 11392. Organization: openai. License: Proprietary.

79.9% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,398 - 1,410

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #114 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,364
Percentile: 58.9%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: expert. Source rank: #139. Votes: 2508. Organization: openai. License: Proprietary.

58.9% percentile inside its fair comparison set

1,364Raw benchmark valueCI 1,352 - 1,376

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 #109 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,368
Percentile: 66%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_business_and_management_and_financial_operations. Source rank: #131. Votes: 8287. Organization: openai. License: Proprietary.

66% percentile inside its fair comparison set

1,368Raw benchmark valueCI 1,361 - 1,375

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 #89 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,364
Percentile: 72.8%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_entertainment_and_sports_and_media. Source rank: #109. Votes: 9064. Organization: openai. License: Proprietary.

72.8% percentile inside its fair comparison set

1,364Raw benchmark valueCI 1,357 - 1,370

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 #97 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 67.8%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_legal_and_government. Source rank: #118. Votes: 3276. Organization: openai. License: Proprietary.

67.8% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,389 - 1,410

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 #116 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 64.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_life_and_physical_and_social_science. Source rank: #138. Votes: 8544. Organization: openai. License: Proprietary.

64.4% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,375 - 1,388

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #132 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,358
Percentile: 57.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_mathematical. Source rank: #159. Votes: 3056. Organization: openai. License: Proprietary.

57.5% percentile inside its fair comparison set

1,358Raw benchmark valueCI 1,347 - 1,369

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 #117 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 60.7%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_medicine_and_healthcare. Source rank: #140. Votes: 2801. Organization: openai. License: Proprietary.

60.7% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,367 - 1,391

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 #116 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,391
Percentile: 64.6%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_software_and_it_services. Source rank: #139. Votes: 16826. Organization: openai. License: Proprietary.

64.6% percentile inside its fair comparison set

1,391Raw benchmark valueCI 1,385 - 1,396

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 #97 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,370
Percentile: 70.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_writing_and_literature_and_language. Source rank: #119. Votes: 11392. Organization: openai. License: Proprietary.

70.4% percentile inside its fair comparison set

1,370Raw benchmark valueCI 1,364 - 1,376

Search / tool use1 benchmark57%

Tau2-Bench Telecom

AA · Search / tool use · Objective

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

Rank #134 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.1%
Percentile: 57%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

57% percentile inside its fair comparison set

47.1%Raw benchmark value

Long context2 benchmarks75.7%

Long Context Reasoning

AA · Long context · Objective

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

Rank #45 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61%
Percentile: 86.7%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

86.7% percentile inside its fair comparison set

61%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 #32 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 63.1%
Percentile: 64.8%
Last updated: recent
Eligibility: historical_model

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

64.8% percentile inside its fair comparison set

63.1%Raw benchmark valueCI 61.2% - 64.9%

Vision understanding22 benchmarks45.4%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #74 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61.2%
Percentile: 45.9%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

45.9% percentile inside its fair comparison set

61.2%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 #41 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,214
Percentile: 63.3%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: overall. Source rank: #51. Votes: 42090. Organization: openai. License: Proprietary.

63.3% percentile inside its fair comparison set

1,214Raw benchmark valueCI 1,208 - 1,221

Vision Arena · Captioning

AR · Vision understanding · Human

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

Rank #10 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,208
Percentile: 65.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: captioning. Source rank: #11. Votes: 440. Organization: openai. License: Proprietary.

65.4% percentile inside its fair comparison set

1,208Raw benchmark valueCI 1,178 - 1,238

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

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

Rank #31 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,227
Percentile: 45.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: creative_writing_vision. Source rank: #38. Votes: 1280. Organization: openai. License: Proprietary.

45.5% percentile inside its fair comparison set

1,227Raw benchmark valueCI 1,208 - 1,246

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 #40 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,233
Percentile: 44.3%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: diagram. Source rank: #52. Votes: 2824. Organization: openai. License: Proprietary.

44.3% percentile inside its fair comparison set

1,233Raw benchmark valueCI 1,220 - 1,246

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 #41 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,211
Percentile: 63.3%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: english. Source rank: #53. Votes: 20042. Organization: openai. License: Proprietary.

63.3% percentile inside its fair comparison set

1,211Raw benchmark valueCI 1,202 - 1,220

Vision Arena · Entity Recognition

AR · Vision understanding · Human

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

Rank #25 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,184
Percentile: 25%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: entity_recognition. Source rank: #27. Votes: 403. Organization: openai. License: Proprietary.

25% percentile inside its fair comparison set

1,184Raw benchmark valueCI 1,154 - 1,214

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 #36 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,248
Percentile: 48.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: homework. Source rank: #47. Votes: 1535. Organization: openai. License: Proprietary.

48.5% percentile inside its fair comparison set

1,248Raw benchmark valueCI 1,232 - 1,263

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 #37 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,181
Percentile: 26.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: humor. Source rank: #49. Votes: 1408. Organization: openai. License: Proprietary.

26.5% percentile inside its fair comparison set

1,181Raw benchmark valueCI 1,161 - 1,200

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 #39 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,226
Percentile: 45.7%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: ocr. Source rank: #50. Votes: 11601. Organization: openai. License: Proprietary.

45.7% percentile inside its fair comparison set

1,226Raw benchmark valueCI 1,217 - 1,235

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 #42 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,210
Percentile: 62.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: overall. Source rank: #54. Votes: 42090. Organization: openai. License: Proprietary.

62.4% percentile inside its fair comparison set

1,210Raw benchmark valueCI 1,204 - 1,217

Vision Arena · Captioning · No Style Control

AR · Vision understanding · Human

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

Rank #18 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,204
Percentile: 34.6%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: captioning. Source rank: #17. Votes: 440. Organization: openai. License: Proprietary.

34.6% percentile inside its fair comparison set

1,204Raw benchmark valueCI 1,175 - 1,233

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 #39 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,222
Percentile: 30.9%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: creative_writing_vision. Source rank: #49. Votes: 1280. Organization: openai. License: Proprietary.

30.9% percentile inside its fair comparison set

1,222Raw benchmark valueCI 1,203 - 1,241

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 #42 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,217
Percentile: 41.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: diagram. Source rank: #54. Votes: 2824. Organization: openai. License: Proprietary.

41.4% percentile inside its fair comparison set

1,217Raw benchmark valueCI 1,204 - 1,229

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 #45 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,212
Percentile: 59.6%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: english. Source rank: #58. Votes: 20042. Organization: openai. License: Proprietary.

59.6% percentile inside its fair comparison set

1,212Raw benchmark valueCI 1,203 - 1,221

Vision Arena · Entity Recognition · No Style Control

AR · Vision understanding · Human

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

Rank #24 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,205
Percentile: 28.1%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: entity_recognition. Source rank: #26. Votes: 403. Organization: openai. License: Proprietary.

28.1% percentile inside its fair comparison set

1,205Raw benchmark valueCI 1,175 - 1,235

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-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,246
Percentile: 42.6%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: homework. Source rank: #49. Votes: 1535. Organization: openai. License: Proprietary.

42.6% percentile inside its fair comparison set

1,246Raw benchmark valueCI 1,230 - 1,261

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 #37 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,195
Percentile: 26.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: humor. Source rank: #48. Votes: 1408. Organization: openai. License: Proprietary.

26.5% percentile inside its fair comparison set

1,195Raw benchmark valueCI 1,175 - 1,214

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 #42 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,218
Percentile: 41.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: ocr. Source rank: #53. Votes: 11601. Organization: openai. License: Proprietary.

41.4% percentile inside its fair comparison set

1,218Raw benchmark valueCI 1,209 - 1,227

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 #42 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 72.4%
Percentile: 29.3%
Last updated: recent
Eligibility: historical_model

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

29.3% percentile inside its fair comparison set

72.4%Raw benchmark valueCI 70.3% - 74.5%

Vision Arena · Creative Writing

AR · Vision understanding · Human

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

Rank #10 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,234
Percentile: 71.9%
Last updated: archived
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: creative_writing. Source rank: #11. Votes: 1432. Organization: openai. License: Proprietary.

71.9% percentile inside its fair comparison set

1,234Raw benchmark valueCI 1,217 - 1,250

Vision Arena · Creative Writing · No Style Control

AR · Vision understanding · Human

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

Rank #15 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,223
Percentile: 56.3%
Last updated: archived
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: creative_writing. Source rank: #16. Votes: 1432. Organization: openai. License: Proprietary.

56.3% percentile inside its fair comparison set

1,223Raw benchmark valueCI 1,207 - 1,239

Document understanding1 benchmark61.7%

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 #24 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.9%
Percentile: 61.7%
Last updated: recent
Eligibility: historical_model

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

61.7% percentile inside its fair comparison set

65.9%Raw benchmark valueCI 64.1% - 67.7%

Multilingual16 benchmarks61%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #103 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 65.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: chinese. Source rank: #126. Votes: 2467. Organization: openai. License: Proprietary.

65.4% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,404 - 1,429

Text Arena · French

AR · Multilingual · Human

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

Rank #88 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,421
Percentile: 59.7%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: french. Source rank: #108. Votes: 690. Organization: openai. License: Proprietary.

59.7% percentile inside its fair comparison set

1,421Raw benchmark valueCI 1,398 - 1,444

Text Arena · German

AR · Multilingual · Human

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

Rank #68 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 71.7%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: german. Source rank: #86. Votes: 1235. Organization: openai. License: Proprietary.

71.7% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,392 - 1,427

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #77 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,342
Percentile: 62.6%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: japanese. Source rank: #98. Votes: 1017. Organization: openai. License: Proprietary.

62.6% percentile inside its fair comparison set

1,342Raw benchmark valueCI 1,323 - 1,362

Text Arena · Korean

AR · Multilingual · Human

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

Rank #55 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,380
Percentile: 74%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: korean. Source rank: #69. Votes: 1005. Organization: openai. License: Proprietary.

74% percentile inside its fair comparison set

1,380Raw benchmark valueCI 1,361 - 1,400

Text Arena · Russian

AR · Multilingual · Human

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

Rank #73 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 75.1%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: russian. Source rank: #92. Votes: 3061. Organization: openai. License: Proprietary.

75.1% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,398 - 1,419

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #78 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 64%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: spanish. Source rank: #97. Votes: 986. Organization: openai. License: Proprietary.

64% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,383 - 1,422

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #126 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,374
Percentile: 57.6%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: chinese. Source rank: #152. Votes: 2467. Organization: openai. License: Proprietary.

57.6% percentile inside its fair comparison set

1,374Raw benchmark valueCI 1,362 - 1,386

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #103 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,384
Percentile: 52.8%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: french. Source rank: #123. Votes: 690. Organization: openai. License: Proprietary.

52.8% percentile inside its fair comparison set

1,384Raw benchmark valueCI 1,360 - 1,407

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #88 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,381
Percentile: 63.3%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: german. Source rank: #105. Votes: 1235. Organization: openai. License: Proprietary.

63.3% percentile inside its fair comparison set

1,381Raw benchmark valueCI 1,365 - 1,398

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #86 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,314
Percentile: 58.1%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: japanese. Source rank: #107. Votes: 1017. Organization: openai. License: Proprietary.

58.1% percentile inside its fair comparison set

1,314Raw benchmark valueCI 1,295 - 1,334

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #84 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,349
Percentile: 60.1%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: korean. Source rank: #101. Votes: 1005. Organization: openai. License: Proprietary.

60.1% percentile inside its fair comparison set

1,349Raw benchmark valueCI 1,330 - 1,369

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #100 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,373
Percentile: 65.7%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: russian. Source rank: #122. Votes: 3061. Organization: openai. License: Proprietary.

65.7% percentile inside its fair comparison set

1,373Raw benchmark valueCI 1,363 - 1,384

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #105 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,368
Percentile: 51.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: spanish. Source rank: #126. Votes: 986. Organization: openai. License: Proprietary.

51.4% percentile inside its fair comparison set

1,368Raw benchmark valueCI 1,348 - 1,387

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #39 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,238
Percentile: 50.6%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: chinese. Source rank: #50. Votes: 1380. Organization: openai. License: Proprietary.

50.6% percentile inside its fair comparison set

1,238Raw benchmark valueCI 1,219 - 1,258

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #44 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,228
Percentile: 44.2%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: chinese. Source rank: #56. Votes: 1380. Organization: openai. License: Proprietary.

44.2% percentile inside its fair comparison set

1,228Raw benchmark valueCI 1,209 - 1,247

Source links and registry checks

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Artificial Analysis

Jun 20, 2026

source →

Model profile · OpenAI

GPT-4.1

Closed weightspremium · registry tag 2025 historical workhorse

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 19.2%
Verified coverage: 19.2%
Spread: n/a
Last verified: Jun 20, 2026

textcodevisiondocument4 aliases39 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

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

Chat / text28 benchmarks66.7%

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 #126 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 19
Percentile: 68.4%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

68.4% percentile inside its fair comparison set

19Raw 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 #68 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24.2%
Percentile: 77.5%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

77.5% percentile inside its fair comparison set

24.2%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 #109 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 20.4%
Percentile: 63.8%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

63.8% percentile inside its fair comparison set

20.4%Raw benchmark value

IFBench

AA · Chat / text · Objective

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

Rank #145 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43%
Percentile: 55.2%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

55.2% percentile inside its fair comparison set

43%Raw benchmark value

Blended price

AA · Chat / text · Speed / cost

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

Rank #235 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $3.5 /1M tokens
Percentile: 16.3%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

16.3% percentile inside its fair comparison set

$3.5 /1M tokensRaw benchmark value

Input price

AA · Chat / text · Speed / cost

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

Rank #236 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $2 /1M input tokens
Percentile: 17.8%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

17.8% percentile inside its fair comparison set

$2 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

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

Rank #229 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $8 /1M output tokens
Percentile: 18.5%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

18.5% percentile inside its fair comparison set

$8 /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 #64 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 137.7 tokens/s
Percentile: 70%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

70% percentile inside its fair comparison set

137.7 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

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

Rank #31 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.93s
Percentile: 85.7%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

85.7% percentile inside its fair comparison set

0.93sRaw 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 #19 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.93s
Percentile: 91.4%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

91.4% percentile inside its fair comparison set

0.93sRaw 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 #83 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 74.8%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: overall. Source rank: #102. Votes: 50981. Organization: openai. License: Proprietary.

74.8% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,410 - 1,417

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 #58 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 82.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: creative_writing. Source rank: #72. Votes: 6701. Organization: openai. License: Proprietary.

82.4% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,394 - 1,410

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 #87 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 73.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: english. Source rank: #107. Votes: 25688. Organization: openai. License: Proprietary.

73.5% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,417 - 1,427

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 #81 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 75.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: exclude_ties. Source rank: #100. Votes: 36223. Organization: openai. License: Proprietary.

75.4% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,397 - 1,407

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 #84 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 74.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: hard_prompts. Source rank: #104. Votes: 22164. Organization: openai. License: Proprietary.

74.5% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,426 - 1,436

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 #86 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 73.8%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: hard_prompts_english. Source rank: #105. Votes: 11905. Organization: openai. License: Proprietary.

73.8% percentile inside its fair comparison set

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

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 #80 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,403
Percentile: 75.7%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: instruction_following. Source rank: #99. Votes: 13289. Organization: openai. License: Proprietary.

75.7% percentile inside its fair comparison set

1,403Raw benchmark valueCI 1,397 - 1,408

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 #76 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 75.3%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: longer_query. Source rank: #96. Votes: 9823. Organization: openai. License: Proprietary.

75.3% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,418 - 1,431

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 #62 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 81.1%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: multi_turn. Source rank: #79. Votes: 8958. Organization: openai. License: Proprietary.

81.1% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,423 - 1,437

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 #105 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 68%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: overall. Source rank: #127. Votes: 50981. Organization: openai. License: Proprietary.

68% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,378 - 1,386

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 #91 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,364
Percentile: 72.1%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: creative_writing. Source rank: #112. Votes: 6701. Organization: openai. License: Proprietary.

72.1% percentile inside its fair comparison set

1,364Raw benchmark valueCI 1,356 - 1,371

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 #108 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 67.1%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: english. Source rank: #129. Votes: 25688. Organization: openai. License: Proprietary.

67.1% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,386 - 1,395

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 #105 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,355
Percentile: 68%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: exclude_ties. Source rank: #127. Votes: 36223. Organization: openai. License: Proprietary.

68% percentile inside its fair comparison set

1,355Raw benchmark valueCI 1,350 - 1,360

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 #107 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 67.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: hard_prompts. Source rank: #129. Votes: 22164. Organization: openai. License: Proprietary.

67.4% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,378 - 1,387

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 #107 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 67.3%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: hard_prompts_english. Source rank: #129. Votes: 11905. Organization: openai. License: Proprietary.

67.3% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,384 - 1,396

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 #105 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,366
Percentile: 68%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: instruction_following. Source rank: #128. Votes: 13289. Organization: openai. License: Proprietary.

68% percentile inside its fair comparison set

1,366Raw benchmark valueCI 1,361 - 1,372

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 #103 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,383
Percentile: 66.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: longer_query. Source rank: #126. Votes: 9823. Organization: openai. License: Proprietary.

66.4% percentile inside its fair comparison set

1,383Raw benchmark valueCI 1,376 - 1,389

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 #93 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 71.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: multi_turn. Source rank: #113. Votes: 8958. Organization: openai. License: Proprietary.

71.5% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,390 - 1,404

Coding5 benchmarks58.9%

Terminal-Bench Hard

AA · Coding · Objective

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

Rank #131 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 13.6%
Percentile: 57%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

57% percentile inside its fair comparison set

13.6%Raw benchmark value

SciCode

AA · Coding · Objective

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

Rank #84 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 38.1%
Percentile: 77.4%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `scicode`.

77.4% percentile inside its fair comparison set

38.1%Raw benchmark value

LiveCodeBench

VALS-AI · Coding · Objective

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

Rank #71 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54.7%
Percentile: 22.2%
Last updated: recent
Eligibility: historical_model

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

22.2% percentile inside its fair comparison set

54.7%Raw benchmark valueCI 52.5% - 56.9%

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 #86 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 73.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: coding. Source rank: #106. Votes: 9314. Organization: openai. License: Proprietary.

73.4% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,450 - 1,463

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 #114 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 64.7%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: coding. Source rank: #138. Votes: 9314. Organization: openai. License: Proprietary.

64.7% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,384 - 1,397

Reasoning / math / science7 benchmarks47.7%

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 #265 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 4.6%
Percentile: 28.9%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `hle`.

28.9% percentile inside its fair comparison set

4.6%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

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

Rank #163 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 66.6%
Percentile: 56.7%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

56.7% percentile inside its fair comparison set

66.6%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

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

Rank #237 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

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

Parsed from Artificial Analysis public leaderboard field `critpt`.

65.2% percentile inside its fair comparison set

0%Raw benchmark value

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 #68 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.4%
Percentile: 24.7%
Last updated: recent
Eligibility: historical_model

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

24.7% percentile inside its fair comparison set

65.4%Raw benchmark valueCI 60.7% - 70.1%

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 #56 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 80.5%
Percentile: 38.2%
Last updated: recent
Eligibility: historical_model

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

38.2% percentile inside its fair comparison set

80.5%Raw benchmark valueCI 79.7% - 81.2%

Text Arena · Math

AR · Reasoning / math / science · Human

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

Rank #126 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,373
Percentile: 60.2%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: math. Source rank: #151. Votes: 3226. Organization: openai. License: Proprietary.

60.2% percentile inside its fair comparison set

1,373Raw benchmark valueCI 1,363 - 1,383

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 #127 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,367
Percentile: 59.9%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: math. Source rank: #153. Votes: 3226. Organization: openai. License: Proprietary.

59.9% percentile inside its fair comparison set

1,367Raw benchmark valueCI 1,357 - 1,377

Professional reasoning20 benchmarks69.6%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #35 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.1%
Percentile: 62.2%
Last updated: recent
Eligibility: historical_model

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

62.2% percentile inside its fair comparison set

83.1%Raw benchmark valueCI 82.3% - 83.9%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #12 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 75.1%
Percentile: 87.9%
Last updated: recent
Eligibility: historical_model

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

87.9% percentile inside its fair comparison set

75.1%Raw benchmark valueCI 73.4% - 76.7%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #102 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 63.3%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: expert. Source rank: #125. Votes: 2508. Organization: openai. License: Proprietary.

63.3% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,394 - 1,418

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 #75 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 76.7%
Last updated: recent
Eligibility: historical_model

76.7% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,408 - 1,422

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 #58 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 82.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_entertainment_and_sports_and_media. Source rank: #71. Votes: 9064. Organization: openai. License: Proprietary.

82.4% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,393 - 1,406

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #60 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 80.2%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_legal_and_government. Source rank: #78. Votes: 3276. Organization: openai. License: Proprietary.

80.2% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,427 - 1,448

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 #89 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 72.8%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_life_and_physical_and_social_science. Source rank: #111. Votes: 8544. Organization: openai. License: Proprietary.

72.8% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,417 - 1,431

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #126 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,372
Percentile: 59.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_mathematical. Source rank: #152. Votes: 3056. Organization: openai. License: Proprietary.

59.4% percentile inside its fair comparison set

1,372Raw benchmark valueCI 1,362 - 1,383

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #88 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 70.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_medicine_and_healthcare. Source rank: #108. Votes: 2801. Organization: openai. License: Proprietary.

70.5% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,421 - 1,444

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 #89 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 72.9%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_software_and_it_services. Source rank: #108. Votes: 16826. Organization: openai. License: Proprietary.

72.9% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,437 - 1,448

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 #66 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 79.9%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_writing_and_literature_and_language. Source rank: #84. Votes: 11392. Organization: openai. License: Proprietary.

79.9% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,398 - 1,410

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #114 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,364
Percentile: 58.9%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: expert. Source rank: #139. Votes: 2508. Organization: openai. License: Proprietary.

58.9% percentile inside its fair comparison set

1,364Raw benchmark valueCI 1,352 - 1,376

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 #109 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,368
Percentile: 66%
Last updated: recent
Eligibility: historical_model

66% percentile inside its fair comparison set

1,368Raw benchmark valueCI 1,361 - 1,375

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 #89 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,364
Percentile: 72.8%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_entertainment_and_sports_and_media. Source rank: #109. Votes: 9064. Organization: openai. License: Proprietary.

72.8% percentile inside its fair comparison set

1,364Raw benchmark valueCI 1,357 - 1,370

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 #97 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 67.8%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_legal_and_government. Source rank: #118. Votes: 3276. Organization: openai. License: Proprietary.

67.8% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,389 - 1,410

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 #116 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 64.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_life_and_physical_and_social_science. Source rank: #138. Votes: 8544. Organization: openai. License: Proprietary.

64.4% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,375 - 1,388

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #132 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,358
Percentile: 57.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_mathematical. Source rank: #159. Votes: 3056. Organization: openai. License: Proprietary.

57.5% percentile inside its fair comparison set

1,358Raw benchmark valueCI 1,347 - 1,369

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 #117 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 60.7%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_medicine_and_healthcare. Source rank: #140. Votes: 2801. Organization: openai. License: Proprietary.

60.7% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,367 - 1,391

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 #116 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,391
Percentile: 64.6%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_software_and_it_services. Source rank: #139. Votes: 16826. Organization: openai. License: Proprietary.

64.6% percentile inside its fair comparison set

1,391Raw benchmark valueCI 1,385 - 1,396

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 #97 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,370
Percentile: 70.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: industry_writing_and_literature_and_language. Source rank: #119. Votes: 11392. Organization: openai. License: Proprietary.

70.4% percentile inside its fair comparison set

1,370Raw benchmark valueCI 1,364 - 1,376

Search / tool use1 benchmark57%

Tau2-Bench Telecom

AA · Search / tool use · Objective

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

Rank #134 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.1%
Percentile: 57%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

57% percentile inside its fair comparison set

47.1%Raw benchmark value

Long context2 benchmarks75.7%

Long Context Reasoning

AA · Long context · Objective

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

Rank #45 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61%
Percentile: 86.7%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

86.7% percentile inside its fair comparison set

61%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 #32 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 63.1%
Percentile: 64.8%
Last updated: recent
Eligibility: historical_model

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

64.8% percentile inside its fair comparison set

63.1%Raw benchmark valueCI 61.2% - 64.9%

Vision understanding22 benchmarks45.4%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #74 · Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61.2%
Percentile: 45.9%
Last updated: recent
Eligibility: historical_model

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

45.9% percentile inside its fair comparison set

61.2%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 #41 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,214
Percentile: 63.3%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: overall. Source rank: #51. Votes: 42090. Organization: openai. License: Proprietary.

63.3% percentile inside its fair comparison set

1,214Raw benchmark valueCI 1,208 - 1,221

Vision Arena · Captioning

AR · Vision understanding · Human

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

Rank #10 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,208
Percentile: 65.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: captioning. Source rank: #11. Votes: 440. Organization: openai. License: Proprietary.

65.4% percentile inside its fair comparison set

1,208Raw benchmark valueCI 1,178 - 1,238

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

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

Rank #31 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,227
Percentile: 45.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: creative_writing_vision. Source rank: #38. Votes: 1280. Organization: openai. License: Proprietary.

45.5% percentile inside its fair comparison set

1,227Raw benchmark valueCI 1,208 - 1,246

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 #40 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,233
Percentile: 44.3%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: diagram. Source rank: #52. Votes: 2824. Organization: openai. License: Proprietary.

44.3% percentile inside its fair comparison set

1,233Raw benchmark valueCI 1,220 - 1,246

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 #41 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,211
Percentile: 63.3%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: english. Source rank: #53. Votes: 20042. Organization: openai. License: Proprietary.

63.3% percentile inside its fair comparison set

1,211Raw benchmark valueCI 1,202 - 1,220

Vision Arena · Entity Recognition

AR · Vision understanding · Human

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

Rank #25 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,184
Percentile: 25%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: entity_recognition. Source rank: #27. Votes: 403. Organization: openai. License: Proprietary.

25% percentile inside its fair comparison set

1,184Raw benchmark valueCI 1,154 - 1,214

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 #36 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,248
Percentile: 48.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: homework. Source rank: #47. Votes: 1535. Organization: openai. License: Proprietary.

48.5% percentile inside its fair comparison set

1,248Raw benchmark valueCI 1,232 - 1,263

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 #37 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,181
Percentile: 26.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: humor. Source rank: #49. Votes: 1408. Organization: openai. License: Proprietary.

26.5% percentile inside its fair comparison set

1,181Raw benchmark valueCI 1,161 - 1,200

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 #39 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,226
Percentile: 45.7%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: ocr. Source rank: #50. Votes: 11601. Organization: openai. License: Proprietary.

45.7% percentile inside its fair comparison set

1,226Raw benchmark valueCI 1,217 - 1,235

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 #42 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,210
Percentile: 62.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: overall. Source rank: #54. Votes: 42090. Organization: openai. License: Proprietary.

62.4% percentile inside its fair comparison set

1,210Raw benchmark valueCI 1,204 - 1,217

Vision Arena · Captioning · No Style Control

AR · Vision understanding · Human

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

Rank #18 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,204
Percentile: 34.6%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: captioning. Source rank: #17. Votes: 440. Organization: openai. License: Proprietary.

34.6% percentile inside its fair comparison set

1,204Raw benchmark valueCI 1,175 - 1,233

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 #39 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,222
Percentile: 30.9%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: creative_writing_vision. Source rank: #49. Votes: 1280. Organization: openai. License: Proprietary.

30.9% percentile inside its fair comparison set

1,222Raw benchmark valueCI 1,203 - 1,241

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 #42 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,217
Percentile: 41.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: diagram. Source rank: #54. Votes: 2824. Organization: openai. License: Proprietary.

41.4% percentile inside its fair comparison set

1,217Raw benchmark valueCI 1,204 - 1,229

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 #45 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,212
Percentile: 59.6%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: english. Source rank: #58. Votes: 20042. Organization: openai. License: Proprietary.

59.6% percentile inside its fair comparison set

1,212Raw benchmark valueCI 1,203 - 1,221

Vision Arena · Entity Recognition · No Style Control

AR · Vision understanding · Human

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

Rank #24 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,205
Percentile: 28.1%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: entity_recognition. Source rank: #26. Votes: 403. Organization: openai. License: Proprietary.

28.1% percentile inside its fair comparison set

1,205Raw benchmark valueCI 1,175 - 1,235

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-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,246
Percentile: 42.6%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: homework. Source rank: #49. Votes: 1535. Organization: openai. License: Proprietary.

42.6% percentile inside its fair comparison set

1,246Raw benchmark valueCI 1,230 - 1,261

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 #37 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,195
Percentile: 26.5%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: humor. Source rank: #48. Votes: 1408. Organization: openai. License: Proprietary.

26.5% percentile inside its fair comparison set

1,195Raw benchmark valueCI 1,175 - 1,214

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 #42 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,218
Percentile: 41.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: ocr. Source rank: #53. Votes: 11601. Organization: openai. License: Proprietary.

41.4% percentile inside its fair comparison set

1,218Raw benchmark valueCI 1,209 - 1,227

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 #42 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 72.4%
Percentile: 29.3%
Last updated: recent
Eligibility: historical_model

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

29.3% percentile inside its fair comparison set

72.4%Raw benchmark valueCI 70.3% - 74.5%

Vision Arena · Creative Writing

AR · Vision understanding · Human

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

Rank #10 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,234
Percentile: 71.9%
Last updated: archived
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: creative_writing. Source rank: #11. Votes: 1432. Organization: openai. License: Proprietary.

71.9% percentile inside its fair comparison set

1,234Raw benchmark valueCI 1,217 - 1,250

Vision Arena · Creative Writing · No Style Control

AR · Vision understanding · Human

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

Rank #15 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,223
Percentile: 56.3%
Last updated: archived
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: creative_writing. Source rank: #16. Votes: 1432. Organization: openai. License: Proprietary.

56.3% percentile inside its fair comparison set

1,223Raw benchmark valueCI 1,207 - 1,239

Document understanding1 benchmark61.7%

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 #24 · Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.9%
Percentile: 61.7%
Last updated: recent
Eligibility: historical_model

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

61.7% percentile inside its fair comparison set

65.9%Raw benchmark valueCI 64.1% - 67.7%

Multilingual16 benchmarks61%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #103 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 65.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: chinese. Source rank: #126. Votes: 2467. Organization: openai. License: Proprietary.

65.4% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,404 - 1,429

Text Arena · French

AR · Multilingual · Human

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

Rank #88 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,421
Percentile: 59.7%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: french. Source rank: #108. Votes: 690. Organization: openai. License: Proprietary.

59.7% percentile inside its fair comparison set

1,421Raw benchmark valueCI 1,398 - 1,444

Text Arena · German

AR · Multilingual · Human

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

Rank #68 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 71.7%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: german. Source rank: #86. Votes: 1235. Organization: openai. License: Proprietary.

71.7% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,392 - 1,427

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #77 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,342
Percentile: 62.6%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: japanese. Source rank: #98. Votes: 1017. Organization: openai. License: Proprietary.

62.6% percentile inside its fair comparison set

1,342Raw benchmark valueCI 1,323 - 1,362

Text Arena · Korean

AR · Multilingual · Human

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

Rank #55 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,380
Percentile: 74%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: korean. Source rank: #69. Votes: 1005. Organization: openai. License: Proprietary.

74% percentile inside its fair comparison set

1,380Raw benchmark valueCI 1,361 - 1,400

Text Arena · Russian

AR · Multilingual · Human

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

Rank #73 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 75.1%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: russian. Source rank: #92. Votes: 3061. Organization: openai. License: Proprietary.

75.1% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,398 - 1,419

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #78 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 64%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: spanish. Source rank: #97. Votes: 986. Organization: openai. License: Proprietary.

64% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,383 - 1,422

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #126 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,374
Percentile: 57.6%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: chinese. Source rank: #152. Votes: 2467. Organization: openai. License: Proprietary.

57.6% percentile inside its fair comparison set

1,374Raw benchmark valueCI 1,362 - 1,386

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #103 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,384
Percentile: 52.8%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: french. Source rank: #123. Votes: 690. Organization: openai. License: Proprietary.

52.8% percentile inside its fair comparison set

1,384Raw benchmark valueCI 1,360 - 1,407

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #88 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,381
Percentile: 63.3%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: german. Source rank: #105. Votes: 1235. Organization: openai. License: Proprietary.

63.3% percentile inside its fair comparison set

1,381Raw benchmark valueCI 1,365 - 1,398

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #86 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,314
Percentile: 58.1%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: japanese. Source rank: #107. Votes: 1017. Organization: openai. License: Proprietary.

58.1% percentile inside its fair comparison set

1,314Raw benchmark valueCI 1,295 - 1,334

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #84 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,349
Percentile: 60.1%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: korean. Source rank: #101. Votes: 1005. Organization: openai. License: Proprietary.

60.1% percentile inside its fair comparison set

1,349Raw benchmark valueCI 1,330 - 1,369

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #100 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,373
Percentile: 65.7%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: russian. Source rank: #122. Votes: 3061. Organization: openai. License: Proprietary.

65.7% percentile inside its fair comparison set

1,373Raw benchmark valueCI 1,363 - 1,384

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #105 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,368
Percentile: 51.4%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: spanish. Source rank: #126. Votes: 986. Organization: openai. License: Proprietary.

51.4% percentile inside its fair comparison set

1,368Raw benchmark valueCI 1,348 - 1,387

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #39 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,238
Percentile: 50.6%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: chinese. Source rank: #50. Votes: 1380. Organization: openai. License: Proprietary.

50.6% percentile inside its fair comparison set

1,238Raw benchmark valueCI 1,219 - 1,258

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #44 · Source label: gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,228
Percentile: 44.2%
Last updated: recent
Eligibility: historical_model

Parsed from Arena leaderboard dataset row `gpt-4.1-2025-04-14`. Category: chinese. Source rank: #56. Votes: 1380. Organization: openai. License: Proprietary.

44.2% percentile inside its fair comparison set

1,228Raw benchmark valueCI 1,209 - 1,247