Model profile · Mistral

Mistral Large 3

Open weightsfrontier · registry tag 2026 open flagship

Thin verified coverage

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

Visible coverage: 13.7%
Verified coverage: 13.7%
Spread: 60.5%
Last verified: Oct 3, 2026

41%capability fit

textcodevisiondocument3 aliases42 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

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

Chat / text27 benchmarks52%

Intelligence Index

AA · Chat / text · Combined

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

Rank #312 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 9
Percentile: 44%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

44% percentile inside its fair comparison set

9Raw 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 #161 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 25%
Percentile: 64.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

64.7% percentile inside its fair comparison set

25%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 #283 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 14%
Percentile: 37.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

37.7% percentile inside its fair comparison set

14%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 #233 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 36.2%
Percentile: 33.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

33.3% percentile inside its fair comparison set

36.2%Raw benchmark value

Input price

AA · Chat / text · Speed / cost

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

Rank #181 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.5 /1M input tokens
Percentile: 49.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

49.7% percentile inside its fair comparison set

$0.5 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

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

Rank #155 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.5 /1M output tokens
Percentile: 56.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

56.8% percentile inside its fair comparison set

$1.5 /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 #142 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 79 tokens/s
Percentile: 46.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

46.2% percentile inside its fair comparison set

79 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 #44 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1.13s
Percentile: 83.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

83.7% percentile inside its fair comparison set

1.13sRaw 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 #25 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1.13s
Percentile: 90.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

90.8% percentile inside its fair comparison set

1.13sRaw 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 #126

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 66.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: overall. Source rank: #141. Votes: 79452. Organization: mistral. License: Apache 2.0.

66.8% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,411 - 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 #131

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,374
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: creative_writing. Source rank: #149. Votes: 14058. Organization: mistral. License: Apache 2.0.

65.2% percentile inside its fair comparison set

1,374Raw benchmark valueCI 1,368 - 1,379

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 #122

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 67.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: english. Source rank: #136. Votes: 33043. Organization: mistral. License: Apache 2.0.

67.8% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,423 - 1,431

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 #126

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 66.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: exclude_ties. Source rank: #141. Votes: 58073. Organization: mistral. License: Apache 2.0.

66.8% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,397 - 1,405

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 #130

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 65.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: hard_prompts. Source rank: #145. Votes: 48464. Organization: mistral. License: Apache 2.0.

65.7% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,428 - 1,435

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 #126

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 66.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: hard_prompts_english. Source rank: #141. Votes: 20190. Organization: mistral. License: Apache 2.0.

66.6% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,435 - 1,444

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 #128

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 66.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: instruction_following. Source rank: #143. Votes: 25505. Organization: mistral. License: Apache 2.0.

66.2% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,396 - 1,405

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 #132

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 63.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: longer_query. Source rank: #148. Votes: 29997. Organization: mistral. License: Apache 2.0.

63.1% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,413 - 1,422

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 #118

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 68.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: multi_turn. Source rank: #133. Votes: 13448. Organization: mistral. License: Apache 2.0.

68.7% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,414 - 1,425

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 #90

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 76.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: overall. Source rank: #97. Votes: 79452. Organization: mistral. License: Apache 2.0.

76.3% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,425 - 1,431

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 #115

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 69.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: creative_writing. Source rank: #125. Votes: 14058. Organization: mistral. License: Apache 2.0.

69.5% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,380 - 1,391

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 #89

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 76.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: english. Source rank: #96. Votes: 33043. Organization: mistral. License: Apache 2.0.

76.6% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,436 - 1,444

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 #90

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 76.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: exclude_ties. Source rank: #97. Votes: 58073. Organization: mistral. License: Apache 2.0.

76.3% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,415 - 1,423

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 #100

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 73.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: hard_prompts. Source rank: #109. Votes: 48464. Organization: mistral. License: Apache 2.0.

73.7% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,426 - 1,433

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 #101

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 73.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: hard_prompts_english. Source rank: #108. Votes: 20190. Organization: mistral. License: Apache 2.0.

73.3% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,432 - 1,442

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 #111

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 70.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: instruction_following. Source rank: #121. Votes: 25505. Organization: mistral. License: Apache 2.0.

70.7% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,398 - 1,406

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 #111

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 69%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: longer_query. Source rank: #119. Votes: 29997. Organization: mistral. License: Apache 2.0.

69% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,409 - 1,418

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 #91

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 75.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: multi_turn. Source rank: #101. Votes: 13448. Organization: mistral. License: Apache 2.0.

75.9% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,423 - 1,435

Coding7 benchmarks23.4%

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 #130 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 15.9%
Percentile: 61.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

61.4% percentile inside its fair comparison set

15.9%Raw benchmark value

SciCode

AA · Coding · Objective

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

Rank #160 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 36.6%
Percentile: 19.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

19.7% percentile inside its fair comparison set

36.6%Raw benchmark value

Text Arena · Coding

AR · Coding · Human

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

Rank #112

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 70.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: coding. Source rank: #125. Votes: 20029. Organization: mistral. License: Apache 2.0.

70.1% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,465 - 1,474

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 #97

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 74.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: coding. Source rank: #102. Votes: 20029. Organization: mistral. License: Apache 2.0.

74.1% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,442 - 1,452

WebDev Arena

AR · Coding · Human

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

Rank #120

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,230
Percentile: 6.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: overall. Source rank: #130. Votes: 840. Organization: mistral. License: Apache 2.0.

6.3% percentile inside its fair comparison set

1,230Raw benchmark valueCI 1,204 - 1,255

Code Arena · Webdev Html

AR · Coding · Human

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

Rank #118

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,238
Percentile: 6.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: webdev-html. Source rank: #128. Votes: 840. Organization: mistral. License: Apache 2.0.

6.4% percentile inside its fair comparison set

1,238Raw benchmark valueCI 1,212 - 1,265

Code Arena · Image To Webdev

AR · Coding · Human

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

Rank #43

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,362
Percentile: 4.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: image_to_webdev. Source rank: #47. Votes: 1316. Organization: mistral. License: Apache 2.0.

4.5% percentile inside its fair comparison set

1,362Raw benchmark valueCI 1,344 - 1,380

Reasoning / math / science5 benchmarks39.5%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

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

Rank #438 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 4.2%
Percentile: 17.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

17.6% percentile inside its fair comparison set

4.2%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

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

Rank #243 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 68%
Percentile: 50.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

50.9% percentile inside its fair comparison set

68%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 #321 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 50.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

50.1% percentile inside its fair comparison set

0%Raw benchmark value

Text Arena · Math

AR · Reasoning / math / science · Human

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

Rank #136

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 62.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: math. Source rank: #154. Votes: 4511. Organization: mistral. License: Apache 2.0.

62.4% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,392 - 1,410

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 #120

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 66.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: math. Source rank: #131. Votes: 4511. Organization: mistral. License: Apache 2.0.

66.9% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,406 - 1,424

Professional reasoning18 benchmarksn/a

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #133

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 59.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: expert. Source rank: #147. Votes: 7490. Organization: mistral. License: Apache 2.0.

59.6% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,420 - 1,434

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 #128

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,410
Percentile: 65.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_business_and_management_and_financial_operations. Source rank: #142. Votes: 14889. Organization: mistral. License: Apache 2.0.

65.6% percentile inside its fair comparison set

1,410Raw benchmark valueCI 1,405 - 1,415

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 #135

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,372
Percentile: 64.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_entertainment_and_sports_and_media. Source rank: #152. Votes: 17383. Organization: mistral. License: Apache 2.0.

64.2% percentile inside its fair comparison set

1,372Raw benchmark valueCI 1,367 - 1,377

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #124

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,421
Percentile: 64.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_legal_and_government. Source rank: #140. Votes: 6034. Organization: mistral. License: Apache 2.0.

64.8% percentile inside its fair comparison set

1,421Raw benchmark valueCI 1,413 - 1,429

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 #130

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 65.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_life_and_physical_and_social_science. Source rank: #146. Votes: 12983. Organization: mistral. License: Apache 2.0.

65.5% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,423 - 1,434

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #130

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 63.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_mathematical. Source rank: #143. Votes: 4153. Organization: mistral. License: Apache 2.0.

63.8% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,404 - 1,424

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #134

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 61.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_medicine_and_healthcare. Source rank: #149. Votes: 5582. Organization: mistral. License: Apache 2.0.

61.6% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,422 - 1,439

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 #115

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_software_and_it_services. Source rank: #127. Votes: 29726. Organization: mistral. License: Apache 2.0.

69.7% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,452 - 1,460

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 #126

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,389
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_writing_and_literature_and_language. Source rank: #143. Votes: 19747. Organization: mistral. License: Apache 2.0.

66.7% percentile inside its fair comparison set

1,389Raw benchmark valueCI 1,384 - 1,394

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #118

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,421
Percentile: 64.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: expert. Source rank: #127. Votes: 7490. Organization: mistral. License: Apache 2.0.

64.2% percentile inside its fair comparison set

1,421Raw benchmark valueCI 1,414 - 1,428

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 #97

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 74%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_business_and_management_and_financial_operations. Source rank: #104. Votes: 14889. Organization: mistral. License: Apache 2.0.

74% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,412 - 1,423

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 #110

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 70.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_entertainment_and_sports_and_media. Source rank: #120. Votes: 17383. Organization: mistral. License: Apache 2.0.

70.9% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,381 - 1,391

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 #79

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 77.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_legal_and_government. Source rank: #84. Votes: 6034. Organization: mistral. License: Apache 2.0.

77.7% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,433 - 1,448

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 #84

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 77.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_life_and_physical_and_social_science. Source rank: #89. Votes: 12983. Organization: mistral. License: Apache 2.0.

77.8% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,440 - 1,451

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #113

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 68.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_mathematical. Source rank: #121. Votes: 4153. Organization: mistral. License: Apache 2.0.

68.5% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,414 - 1,434

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 #77

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 78%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_medicine_and_healthcare. Source rank: #82. Votes: 5582. Organization: mistral. License: Apache 2.0.

78% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,438 - 1,454

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 #92

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 75.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_software_and_it_services. Source rank: #98. Votes: 29726. Organization: mistral. License: Apache 2.0.

75.8% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,446 - 1,454

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 #109

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 71.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_writing_and_literature_and_language. Source rank: #118. Votes: 19747. Organization: mistral. License: Apache 2.0.

71.2% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,391 - 1,401

Search / tool use1 benchmark33.9%

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 #226 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24.6%
Percentile: 33.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

33.9% percentile inside its fair comparison set

24.6%Raw benchmark value

Long context1 benchmark38.5%

Long Context Reasoning

AA · Long context · Objective

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

Rank #281 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 36%
Percentile: 38.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

38.5% percentile inside its fair comparison set

36%Raw benchmark value

Vision understanding15 benchmarks35.8%

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 #156 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 55.7%
Percentile: 25.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

25.5% percentile inside its fair comparison set

55.7%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

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

Rank #76

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,201
Percentile: 46%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: overall. Source rank: #85. Votes: 8160. Organization: mistral. License: Apache 2.0.

46% percentile inside its fair comparison set

1,201Raw benchmark valueCI 1,192 - 1,209

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 #64

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,194
Percentile: 23.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: creative_writing_vision. Source rank: #73. Votes: 761. Organization: mistral. License: Apache 2.0.

23.2% percentile inside its fair comparison set

1,194Raw benchmark valueCI 1,171 - 1,218

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 #68

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,234
Percentile: 32.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: diagram. Source rank: #77. Votes: 2057. Organization: mistral. License: Apache 2.0.

32.3% percentile inside its fair comparison set

1,234Raw benchmark valueCI 1,220 - 1,248

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 #70

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,211
Percentile: 50%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: english. Source rank: #80. Votes: 2797. Organization: mistral. License: Apache 2.0.

50% percentile inside its fair comparison set

1,211Raw benchmark valueCI 1,199 - 1,224

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 #78

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,209
Percentile: 19.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: homework. Source rank: #90. Votes: 828. Organization: mistral. License: Apache 2.0.

19.8% percentile inside its fair comparison set

1,209Raw benchmark valueCI 1,187 - 1,230

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 #60

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,182
Percentile: 19.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: humor. Source rank: #71. Votes: 386. Organization: mistral. License: Apache 2.0.

19.2% percentile inside its fair comparison set

1,182Raw benchmark valueCI 1,152 - 1,213

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 #71

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,216
Percentile: 30%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: ocr. Source rank: #81. Votes: 5458. Organization: mistral. License: Apache 2.0.

30% percentile inside its fair comparison set

1,216Raw benchmark valueCI 1,207 - 1,225

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 #69

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,222
Percentile: 51.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: overall. Source rank: #78. Votes: 8160. Organization: mistral. License: Apache 2.0.

51.1% percentile inside its fair comparison set

1,222Raw benchmark valueCI 1,214 - 1,230

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 #62

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,215
Percentile: 25.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: creative_writing_vision. Source rank: #70. Votes: 761. Organization: mistral. License: Apache 2.0.

25.6% percentile inside its fair comparison set

1,215Raw benchmark valueCI 1,192 - 1,238

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 #67

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,241
Percentile: 33.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: diagram. Source rank: #76. Votes: 2057. Organization: mistral. License: Apache 2.0.

33.3% percentile inside its fair comparison set

1,241Raw benchmark valueCI 1,227 - 1,254

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 #65

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,237
Percentile: 53.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: english. Source rank: #72. Votes: 2797. Organization: mistral. License: Apache 2.0.

53.6% percentile inside its fair comparison set

1,237Raw benchmark valueCI 1,224 - 1,249

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 #74

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,218
Percentile: 24%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: homework. Source rank: #84. Votes: 828. Organization: mistral. License: Apache 2.0.

24% percentile inside its fair comparison set

1,218Raw benchmark valueCI 1,196 - 1,239

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 #55

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,213
Percentile: 26%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: humor. Source rank: #63. Votes: 386. Organization: mistral. License: Apache 2.0.

26% percentile inside its fair comparison set

1,213Raw benchmark valueCI 1,182 - 1,244

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 #70

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,231
Percentile: 31%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: ocr. Source rank: #79. Votes: 5458. Organization: mistral. License: Apache 2.0.

31% percentile inside its fair comparison set

1,231Raw benchmark valueCI 1,222 - 1,240

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #134

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 62.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: chinese. Source rank: #151. Votes: 5984. Organization: mistral. License: Apache 2.0.

62.2% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,425 - 1,442

Text Arena · French

AR · Multilingual · Human

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

Rank #107

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 58.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: french. Source rank: #120. Votes: 2224. Organization: mistral. License: Apache 2.0.

58.8% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,418 - 1,447

Text Arena · German

AR · Multilingual · Human

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

Rank #101

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 63.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: german. Source rank: #116. Votes: 1291. Organization: mistral. License: Apache 2.0.

63.2% 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 #88

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,378
Percentile: 64.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: japanese. Source rank: #103. Votes: 859. Organization: mistral. License: Apache 2.0.

64.2% percentile inside its fair comparison set

1,378Raw benchmark valueCI 1,356 - 1,399

Text Arena · Korean

AR · Multilingual · Human

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

Rank #105

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,358
Percentile: 57.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: korean. Source rank: #121. Votes: 1346. Organization: mistral. License: Apache 2.0.

57.4% percentile inside its fair comparison set

1,358Raw benchmark valueCI 1,341 - 1,376

Text Arena · Non English

AR · Multilingual · Human

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

Rank #127

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 66.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: non_english. Source rank: #142. Votes: 46399. Organization: mistral. License: Apache 2.0.

66.5% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,394 - 1,401

Text Arena · Polish

AR · Multilingual · Human

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

Rank #94

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 53.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: polish. Source rank: #108. Votes: 1782. Organization: mistral. License: Apache 2.0.

53.3% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,401 - 1,429

Text Arena · Russian

AR · Multilingual · Human

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

Rank #118

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 65.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: russian. Source rank: #133. Votes: 9545. Organization: mistral. License: Apache 2.0.

65.7% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,402 - 1,415

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #119

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 54.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: spanish. Source rank: #134. Votes: 2351. Organization: mistral. License: Apache 2.0.

54.4% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,393 - 1,419

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #118

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 66.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: chinese. Source rank: #127. Votes: 5984. Organization: mistral. License: Apache 2.0.

66.8% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,440 - 1,456

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #59

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 77.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: french. Source rank: #63. Votes: 2224. Organization: mistral. License: Apache 2.0.

77.4% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,442 - 1,470

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #63

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 77.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: german. Source rank: #71. Votes: 1291. Organization: mistral. License: Apache 2.0.

77.2% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,421 - 1,455

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #70

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,394
Percentile: 71.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: japanese. Source rank: #80. Votes: 859. Organization: mistral. License: Apache 2.0.

71.6% percentile inside its fair comparison set

1,394Raw benchmark valueCI 1,373 - 1,416

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #77

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 68.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: korean. Source rank: #86. Votes: 1346. Organization: mistral. License: Apache 2.0.

68.9% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,367 - 1,402

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #92

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 75.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: non_english. Source rank: #100. Votes: 46399. Organization: mistral. License: Apache 2.0.

75.8% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,409 - 1,416

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #51

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 74.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: polish. Source rank: #57. Votes: 1782. Organization: mistral. License: Apache 2.0.

74.9% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,427 - 1,455

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #101

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 70.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: russian. Source rank: #112. Votes: 9545. Organization: mistral. License: Apache 2.0.

70.7% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,406 - 1,419

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #73

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 72.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: spanish. Source rank: #79. Votes: 2351. Organization: mistral. License: Apache 2.0.

72.2% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,425 - 1,451

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #72

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,205
Percentile: 31.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: chinese. Source rank: #82. Votes: 511. Organization: mistral. License: Apache 2.0.

31.7% percentile inside its fair comparison set

1,205Raw benchmark valueCI 1,177 - 1,233

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #68

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,227
Percentile: 35.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: chinese. Source rank: #78. Votes: 511. Organization: mistral. License: Apache 2.0.

35.6% percentile inside its fair comparison set

1,227Raw benchmark valueCI 1,200 - 1,255

Source links and registry checks

official

Mistral model overview

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

Model profile · Mistral

Mistral Large 3

Open weightsfrontier · registry tag 2026 open flagship

Thin verified coverage

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

Visible coverage: 13.7%
Verified coverage: 13.7%
Spread: 60.5%
Last verified: Oct 3, 2026

41%capability fit

textcodevisiondocument3 aliases42 official source links

Open compare

Data version

Current snapshot.

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

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

Source-linked scores by benchmark

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

Chat / text27 benchmarks52%

Intelligence Index

AA · Chat / text · Combined

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

Rank #312 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 9
Percentile: 44%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

44% percentile inside its fair comparison set

9Raw 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 #161 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 25%
Percentile: 64.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

64.7% percentile inside its fair comparison set

25%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 #283 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 14%
Percentile: 37.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

37.7% percentile inside its fair comparison set

14%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 #233 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 36.2%
Percentile: 33.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

33.3% percentile inside its fair comparison set

36.2%Raw benchmark value

Input price

AA · Chat / text · Speed / cost

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

Rank #181 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.5 /1M input tokens
Percentile: 49.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

49.7% percentile inside its fair comparison set

$0.5 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

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

Rank #155 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.5 /1M output tokens
Percentile: 56.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

56.8% percentile inside its fair comparison set

$1.5 /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 #142 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 79 tokens/s
Percentile: 46.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

46.2% percentile inside its fair comparison set

79 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 #44 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1.13s
Percentile: 83.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

83.7% percentile inside its fair comparison set

1.13sRaw 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 #25 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1.13s
Percentile: 90.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

90.8% percentile inside its fair comparison set

1.13sRaw 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 #126

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 66.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: overall. Source rank: #141. Votes: 79452. Organization: mistral. License: Apache 2.0.

66.8% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,411 - 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 #131

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,374
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: creative_writing. Source rank: #149. Votes: 14058. Organization: mistral. License: Apache 2.0.

65.2% percentile inside its fair comparison set

1,374Raw benchmark valueCI 1,368 - 1,379

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 #122

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 67.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: english. Source rank: #136. Votes: 33043. Organization: mistral. License: Apache 2.0.

67.8% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,423 - 1,431

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 #126

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 66.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: exclude_ties. Source rank: #141. Votes: 58073. Organization: mistral. License: Apache 2.0.

66.8% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,397 - 1,405

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 #130

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 65.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: hard_prompts. Source rank: #145. Votes: 48464. Organization: mistral. License: Apache 2.0.

65.7% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,428 - 1,435

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 #126

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 66.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: hard_prompts_english. Source rank: #141. Votes: 20190. Organization: mistral. License: Apache 2.0.

66.6% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,435 - 1,444

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 #128

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 66.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: instruction_following. Source rank: #143. Votes: 25505. Organization: mistral. License: Apache 2.0.

66.2% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,396 - 1,405

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 #132

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 63.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: longer_query. Source rank: #148. Votes: 29997. Organization: mistral. License: Apache 2.0.

63.1% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,413 - 1,422

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 #118

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 68.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: multi_turn. Source rank: #133. Votes: 13448. Organization: mistral. License: Apache 2.0.

68.7% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,414 - 1,425

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 #90

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 76.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: overall. Source rank: #97. Votes: 79452. Organization: mistral. License: Apache 2.0.

76.3% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,425 - 1,431

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 #115

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 69.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: creative_writing. Source rank: #125. Votes: 14058. Organization: mistral. License: Apache 2.0.

69.5% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,380 - 1,391

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 #89

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 76.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: english. Source rank: #96. Votes: 33043. Organization: mistral. License: Apache 2.0.

76.6% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,436 - 1,444

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 #90

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 76.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: exclude_ties. Source rank: #97. Votes: 58073. Organization: mistral. License: Apache 2.0.

76.3% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,415 - 1,423

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 #100

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 73.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: hard_prompts. Source rank: #109. Votes: 48464. Organization: mistral. License: Apache 2.0.

73.7% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,426 - 1,433

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 #101

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 73.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: hard_prompts_english. Source rank: #108. Votes: 20190. Organization: mistral. License: Apache 2.0.

73.3% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,432 - 1,442

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 #111

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 70.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: instruction_following. Source rank: #121. Votes: 25505. Organization: mistral. License: Apache 2.0.

70.7% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,398 - 1,406

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 #111

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 69%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: longer_query. Source rank: #119. Votes: 29997. Organization: mistral. License: Apache 2.0.

69% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,409 - 1,418

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 #91

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 75.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: multi_turn. Source rank: #101. Votes: 13448. Organization: mistral. License: Apache 2.0.

75.9% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,423 - 1,435

Coding7 benchmarks23.4%

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 #130 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 15.9%
Percentile: 61.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

61.4% percentile inside its fair comparison set

15.9%Raw benchmark value

SciCode

AA · Coding · Objective

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

Rank #160 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 36.6%
Percentile: 19.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

19.7% percentile inside its fair comparison set

36.6%Raw benchmark value

Text Arena · Coding

AR · Coding · Human

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

Rank #112

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 70.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: coding. Source rank: #125. Votes: 20029. Organization: mistral. License: Apache 2.0.

70.1% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,465 - 1,474

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 #97

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,447
Percentile: 74.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: coding. Source rank: #102. Votes: 20029. Organization: mistral. License: Apache 2.0.

74.1% percentile inside its fair comparison set

1,447Raw benchmark valueCI 1,442 - 1,452

WebDev Arena

AR · Coding · Human

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

Rank #120

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,230
Percentile: 6.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: overall. Source rank: #130. Votes: 840. Organization: mistral. License: Apache 2.0.

6.3% percentile inside its fair comparison set

1,230Raw benchmark valueCI 1,204 - 1,255

Code Arena · Webdev Html

AR · Coding · Human

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

Rank #118

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,238
Percentile: 6.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: webdev-html. Source rank: #128. Votes: 840. Organization: mistral. License: Apache 2.0.

6.4% percentile inside its fair comparison set

1,238Raw benchmark valueCI 1,212 - 1,265

Code Arena · Image To Webdev

AR · Coding · Human

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

Rank #43

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,362
Percentile: 4.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: image_to_webdev. Source rank: #47. Votes: 1316. Organization: mistral. License: Apache 2.0.

4.5% percentile inside its fair comparison set

1,362Raw benchmark valueCI 1,344 - 1,380

Reasoning / math / science5 benchmarks39.5%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

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

Rank #438 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 4.2%
Percentile: 17.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

17.6% percentile inside its fair comparison set

4.2%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

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

Rank #243 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 68%
Percentile: 50.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

50.9% percentile inside its fair comparison set

68%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 #321 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 50.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

50.1% percentile inside its fair comparison set

0%Raw benchmark value

Text Arena · Math

AR · Reasoning / math / science · Human

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

Rank #136

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 62.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: math. Source rank: #154. Votes: 4511. Organization: mistral. License: Apache 2.0.

62.4% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,392 - 1,410

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 #120

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 66.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: math. Source rank: #131. Votes: 4511. Organization: mistral. License: Apache 2.0.

66.9% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,406 - 1,424

Professional reasoning18 benchmarksn/a

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #133

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 59.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: expert. Source rank: #147. Votes: 7490. Organization: mistral. License: Apache 2.0.

59.6% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,420 - 1,434

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 #128

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,410
Percentile: 65.6%
Last updated: recent
Eligibility: headline eligible

65.6% percentile inside its fair comparison set

1,410Raw benchmark valueCI 1,405 - 1,415

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 #135

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,372
Percentile: 64.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_entertainment_and_sports_and_media. Source rank: #152. Votes: 17383. Organization: mistral. License: Apache 2.0.

64.2% percentile inside its fair comparison set

1,372Raw benchmark valueCI 1,367 - 1,377

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #124

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,421
Percentile: 64.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_legal_and_government. Source rank: #140. Votes: 6034. Organization: mistral. License: Apache 2.0.

64.8% percentile inside its fair comparison set

1,421Raw benchmark valueCI 1,413 - 1,429

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 #130

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 65.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_life_and_physical_and_social_science. Source rank: #146. Votes: 12983. Organization: mistral. License: Apache 2.0.

65.5% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,423 - 1,434

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #130

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 63.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_mathematical. Source rank: #143. Votes: 4153. Organization: mistral. License: Apache 2.0.

63.8% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,404 - 1,424

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #134

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 61.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_medicine_and_healthcare. Source rank: #149. Votes: 5582. Organization: mistral. License: Apache 2.0.

61.6% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,422 - 1,439

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 #115

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_software_and_it_services. Source rank: #127. Votes: 29726. Organization: mistral. License: Apache 2.0.

69.7% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,452 - 1,460

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 #126

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,389
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_writing_and_literature_and_language. Source rank: #143. Votes: 19747. Organization: mistral. License: Apache 2.0.

66.7% percentile inside its fair comparison set

1,389Raw benchmark valueCI 1,384 - 1,394

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #118

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,421
Percentile: 64.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: expert. Source rank: #127. Votes: 7490. Organization: mistral. License: Apache 2.0.

64.2% percentile inside its fair comparison set

1,421Raw benchmark valueCI 1,414 - 1,428

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 #97

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 74%
Last updated: recent
Eligibility: headline eligible

74% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,412 - 1,423

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 #110

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 70.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_entertainment_and_sports_and_media. Source rank: #120. Votes: 17383. Organization: mistral. License: Apache 2.0.

70.9% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,381 - 1,391

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 #79

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 77.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_legal_and_government. Source rank: #84. Votes: 6034. Organization: mistral. License: Apache 2.0.

77.7% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,433 - 1,448

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 #84

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 77.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_life_and_physical_and_social_science. Source rank: #89. Votes: 12983. Organization: mistral. License: Apache 2.0.

77.8% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,440 - 1,451

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #113

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 68.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_mathematical. Source rank: #121. Votes: 4153. Organization: mistral. License: Apache 2.0.

68.5% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,414 - 1,434

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 #77

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 78%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_medicine_and_healthcare. Source rank: #82. Votes: 5582. Organization: mistral. License: Apache 2.0.

78% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,438 - 1,454

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 #92

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 75.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_software_and_it_services. Source rank: #98. Votes: 29726. Organization: mistral. License: Apache 2.0.

75.8% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,446 - 1,454

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 #109

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 71.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: industry_writing_and_literature_and_language. Source rank: #118. Votes: 19747. Organization: mistral. License: Apache 2.0.

71.2% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,391 - 1,401

Search / tool use1 benchmark33.9%

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 #226 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24.6%
Percentile: 33.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

33.9% percentile inside its fair comparison set

24.6%Raw benchmark value

Long context1 benchmark38.5%

Long Context Reasoning

AA · Long context · Objective

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

Rank #281 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 36%
Percentile: 38.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

38.5% percentile inside its fair comparison set

36%Raw benchmark value

Vision understanding15 benchmarks35.8%

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 #156 · Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 55.7%
Percentile: 25.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

25.5% percentile inside its fair comparison set

55.7%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

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

Rank #76

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,201
Percentile: 46%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: overall. Source rank: #85. Votes: 8160. Organization: mistral. License: Apache 2.0.

46% percentile inside its fair comparison set

1,201Raw benchmark valueCI 1,192 - 1,209

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 #64

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,194
Percentile: 23.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: creative_writing_vision. Source rank: #73. Votes: 761. Organization: mistral. License: Apache 2.0.

23.2% percentile inside its fair comparison set

1,194Raw benchmark valueCI 1,171 - 1,218

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 #68

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,234
Percentile: 32.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: diagram. Source rank: #77. Votes: 2057. Organization: mistral. License: Apache 2.0.

32.3% percentile inside its fair comparison set

1,234Raw benchmark valueCI 1,220 - 1,248

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 #70

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,211
Percentile: 50%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: english. Source rank: #80. Votes: 2797. Organization: mistral. License: Apache 2.0.

50% percentile inside its fair comparison set

1,211Raw benchmark valueCI 1,199 - 1,224

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 #78

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,209
Percentile: 19.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: homework. Source rank: #90. Votes: 828. Organization: mistral. License: Apache 2.0.

19.8% percentile inside its fair comparison set

1,209Raw benchmark valueCI 1,187 - 1,230

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 #60

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,182
Percentile: 19.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: humor. Source rank: #71. Votes: 386. Organization: mistral. License: Apache 2.0.

19.2% percentile inside its fair comparison set

1,182Raw benchmark valueCI 1,152 - 1,213

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 #71

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,216
Percentile: 30%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: ocr. Source rank: #81. Votes: 5458. Organization: mistral. License: Apache 2.0.

30% percentile inside its fair comparison set

1,216Raw benchmark valueCI 1,207 - 1,225

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 #69

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,222
Percentile: 51.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: overall. Source rank: #78. Votes: 8160. Organization: mistral. License: Apache 2.0.

51.1% percentile inside its fair comparison set

1,222Raw benchmark valueCI 1,214 - 1,230

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 #62

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,215
Percentile: 25.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: creative_writing_vision. Source rank: #70. Votes: 761. Organization: mistral. License: Apache 2.0.

25.6% percentile inside its fair comparison set

1,215Raw benchmark valueCI 1,192 - 1,238

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 #67

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,241
Percentile: 33.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: diagram. Source rank: #76. Votes: 2057. Organization: mistral. License: Apache 2.0.

33.3% percentile inside its fair comparison set

1,241Raw benchmark valueCI 1,227 - 1,254

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 #65

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,237
Percentile: 53.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: english. Source rank: #72. Votes: 2797. Organization: mistral. License: Apache 2.0.

53.6% percentile inside its fair comparison set

1,237Raw benchmark valueCI 1,224 - 1,249

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 #74

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,218
Percentile: 24%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: homework. Source rank: #84. Votes: 828. Organization: mistral. License: Apache 2.0.

24% percentile inside its fair comparison set

1,218Raw benchmark valueCI 1,196 - 1,239

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 #55

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,213
Percentile: 26%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: humor. Source rank: #63. Votes: 386. Organization: mistral. License: Apache 2.0.

26% percentile inside its fair comparison set

1,213Raw benchmark valueCI 1,182 - 1,244

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 #70

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,231
Percentile: 31%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: ocr. Source rank: #79. Votes: 5458. Organization: mistral. License: Apache 2.0.

31% percentile inside its fair comparison set

1,231Raw benchmark valueCI 1,222 - 1,240

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #134

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 62.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: chinese. Source rank: #151. Votes: 5984. Organization: mistral. License: Apache 2.0.

62.2% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,425 - 1,442

Text Arena · French

AR · Multilingual · Human

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

Rank #107

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 58.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: french. Source rank: #120. Votes: 2224. Organization: mistral. License: Apache 2.0.

58.8% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,418 - 1,447

Text Arena · German

AR · Multilingual · Human

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

Rank #101

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 63.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: german. Source rank: #116. Votes: 1291. Organization: mistral. License: Apache 2.0.

63.2% 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 #88

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,378
Percentile: 64.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: japanese. Source rank: #103. Votes: 859. Organization: mistral. License: Apache 2.0.

64.2% percentile inside its fair comparison set

1,378Raw benchmark valueCI 1,356 - 1,399

Text Arena · Korean

AR · Multilingual · Human

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

Rank #105

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,358
Percentile: 57.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: korean. Source rank: #121. Votes: 1346. Organization: mistral. License: Apache 2.0.

57.4% percentile inside its fair comparison set

1,358Raw benchmark valueCI 1,341 - 1,376

Text Arena · Non English

AR · Multilingual · Human

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

Rank #127

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 66.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: non_english. Source rank: #142. Votes: 46399. Organization: mistral. License: Apache 2.0.

66.5% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,394 - 1,401

Text Arena · Polish

AR · Multilingual · Human

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

Rank #94

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 53.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: polish. Source rank: #108. Votes: 1782. Organization: mistral. License: Apache 2.0.

53.3% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,401 - 1,429

Text Arena · Russian

AR · Multilingual · Human

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

Rank #118

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 65.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: russian. Source rank: #133. Votes: 9545. Organization: mistral. License: Apache 2.0.

65.7% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,402 - 1,415

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #119

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 54.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: spanish. Source rank: #134. Votes: 2351. Organization: mistral. License: Apache 2.0.

54.4% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,393 - 1,419

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #118

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 66.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: chinese. Source rank: #127. Votes: 5984. Organization: mistral. License: Apache 2.0.

66.8% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,440 - 1,456

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #59

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 77.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: french. Source rank: #63. Votes: 2224. Organization: mistral. License: Apache 2.0.

77.4% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,442 - 1,470

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #63

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 77.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: german. Source rank: #71. Votes: 1291. Organization: mistral. License: Apache 2.0.

77.2% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,421 - 1,455

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #70

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,394
Percentile: 71.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: japanese. Source rank: #80. Votes: 859. Organization: mistral. License: Apache 2.0.

71.6% percentile inside its fair comparison set

1,394Raw benchmark valueCI 1,373 - 1,416

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #77

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 68.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: korean. Source rank: #86. Votes: 1346. Organization: mistral. License: Apache 2.0.

68.9% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,367 - 1,402

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #92

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 75.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: non_english. Source rank: #100. Votes: 46399. Organization: mistral. License: Apache 2.0.

75.8% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,409 - 1,416

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #51

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 74.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: polish. Source rank: #57. Votes: 1782. Organization: mistral. License: Apache 2.0.

74.9% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,427 - 1,455

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #101

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 70.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: russian. Source rank: #112. Votes: 9545. Organization: mistral. License: Apache 2.0.

70.7% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,406 - 1,419

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #73

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 72.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: spanish. Source rank: #79. Votes: 2351. Organization: mistral. License: Apache 2.0.

72.2% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,425 - 1,451

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #72

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,205
Percentile: 31.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: chinese. Source rank: #82. Votes: 511. Organization: mistral. License: Apache 2.0.

31.7% percentile inside its fair comparison set

1,205Raw benchmark valueCI 1,177 - 1,233

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #68

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,227
Percentile: 35.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `mistral-large-3`. Category: chinese. Source rank: #78. Votes: 511. Organization: mistral. License: Apache 2.0.

35.6% percentile inside its fair comparison set

1,227Raw benchmark valueCI 1,200 - 1,255

Source links and registry checks

official

Mistral model overview

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

Mistral Large 3

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

Mistral Large 3

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks