OverviewAll LeaderboardsMethodologyComing soon
New Chat
Agent Arena IndexMistral Large 4
Mistral

Mistral Large 4

Mistral Large 4 is an open source model from Mistral. It ranks #51 of 65 models on the Agent Arena Index with 1,011. Its best signal rank is #47 of 65, on Task Completion.

Agent Arena Index Overview

Rank
#51

Rank spread 45 – 57.

Agent Arena Index
1,011± 26
Pareto frontier

141 points under the frontier

Mistral Large 4
Developer
Mistral
License
Modified MIT
Token price (in / out)
$0.70 / $2.10 per 1M
Sessions
4,433
Ranking updated
Nov 13, 2026

Cost, Time, and Tokens

Cost per task$0.26
GPT-6 Luna (Low)$0.01AnthropicClaude Fable 5.2 (Max)$9.15

The median is $0.54.

Time per task4.8 min
MetaMuse Ember (Max)26 sAnthropicClaude Fable 5.2 (Max)19.5 min

The median is 6.2 min.

Output tokens per task22.3K
GPT-6 Luna (Low)3.7KAnthropicClaude Sonnet 5.5 (Max)149.1K

The median is 31.9K.

Agent Arena Ranking

9001,000
  1. 1,051
    MiniMax-M3.1-Flash#44
  2. 1,047
    GLM-5.3-Flash#45
  3. 1,047
    Stepfun
    Step 5 Preview#46
  4. 1,035
    Qwen3.8-Flash-Next#47
  5. 1,032
    Gemini 3.1 Pro Preview#48
  6. 1,026
    Qwen3.8-27B#49
  7. 1,019
    Reflection AI
    Beam 1.0 501B A23B#50
  8. 1,011
    Mistral Large 4#51
  9. 1,003
    GPT-6 LunaLow#52
  10. 998
    Tencent
    Hy3#53
  11. 996
    Qwen3.7-Max#54
  12. 987
    Qwen3.7-Plus#55
  13. 979
    Meta
    Muse Spark 1.1#56
  14. 979
    Meta
    Muse Spark 1.2xHigh#57
  15. 956
    MiniMax-M3#58

Signal Performance

Mistral Large 4Leader
Rank on the board
  • Task CompletionHow often the model gets users to confirm the task is done.
    Claude Fable 5.2 · 1,314Claude Fable 5.2 · 1,314Mistral Large 4 · 1,060
    #47of 65
  • Praise vs ComplaintHow often the model earns more explicitly positive responses than negative ones.
    Claude Fable 5.2 · 1,852Claude Fable 5.2 · 1,852Mistral Large 4 · 972
    #53of 65
  • SteerabilityHow well the model lands user corrections when they push back.
    Claude Fable 5.2 · 1,338Claude Fable 5.2 · 1,338Mistral Large 4 · 995
    #50of 65
  • Bash ReliabilityHow often the model’s bash commands succeed. Errors outside its control aren’t counted. E.g. network issues, permission denied, etc.
    Claude Sonnet 5 · 1,240Claude Sonnet 5 · 1,240Mistral Large 4 · 1,022
    #55of 65
9001,0001,1001,2001,3001,4001,5001,6001,7001,8001,900

USE CASES

  • Chat with AI
  • Build Apps & Websites
  • Write & Edit Text
  • Search the Web
  • Generate Images
  • Generate Videos
  • Chose any model
  • Compare Models Side by Side

LEADERBOARD RANKINGS

  • Overall
  • Agent
  • Alignment Index
  • Text
  • WebDev
  • Image-to-WebDev
  • Text to Image
  • Image Edit
  • Text to Video
  • Image to Video
  • Video Edit
  • Vision
  • Document
  • Search

COMPANY

  • About Us
  • How It Works
  • Blog
  • Careers
  • Leaderboard Changelog
  • Product Changelog
  • Help Center
  • FAQ

LEGAL

  • Terms
  • Privacy
  • Cookies

FOLLOW

  • X
  • LinkedIn
  • YouTube
  • Discord

© Arena Intelligence