OverviewAll LeaderboardsMethodologyComing soon
New Chat
Chat IndexMistral Large 4
Mistral

Mistral Large 4

Mistral Large 4 is an open source model from Mistral. It ranks #55 of 65 models on the Chat Index with 992. Its best signal rank is #46 of 65, on Steerability.

Chat Index Overview

Rank
#55

Rank spread 37 – 63.

Chat Index
992± 51
Pareto frontier

125 points under the frontier

Mistral Large 4
Developer
Mistral
License
Modified MIT
Token price (in / out)
$0.70 / $2.10 per 1M
Sessions
1,347
Ranking updated
Nov 13, 2026

Cost, Time, and Tokens

Cost per task$0.16
GPT-6 Luna (Low)$0.01AnthropicClaude Fable 5.2 (Max)$5.55

The median is $0.32.

Time per task1.9 min
MetaMuse Ember (Max)18 sAnthropicClaude Sonnet 5.5 (Max)15.2 min

The median is 3.4 min.

Output tokens per task8.1K
GPT-6 Luna (Low)2.1KAnthropicClaude Sonnet 5.5 (Max)135.6K

The median is 14.2K.

Chat Ranking

8009001,000
  1. 1,020
    Qwen3.7-Plus#48
  2. 1,014
    Qwen3.8-Flash-Next#49
  3. 1,013
    MiniMax-M3.1-Flash#50
  4. 1,005
    Qwen3.7-Max#51
  5. 999
    Meta
    Muse Spark 1.2xHigh#52
  6. 999
    Stepfun
    Step 5 Preview#53
  7. 993
    Qwen3.8-27B#54
  8. 992
    Mistral Large 4#55
  9. 969
    Mistral Medium 3.5#56
  10. 961
    GPT-6 LunaLow#57
  11. 941
    Tencent
    Hy3#58
  12. 930
    MiniMax-M3#59
  13. 923
    Synlan
    Spark-X2.6#60
  14. 912
    Thinking Machines
    Inkling#61
  15. 902
    NVIDIA-Nemotron-3.5-Super-VL-120B-A12BNVFP4#62

Signal Performance

Mistral Large 4Leader
Rank on the board
  • Task CompletionHow often the model gets users to confirm the task is done.
    Claude Opus 5.5 (Max) · 1,370Claude Opus 5.5 (Max) · 1,370Mistral Large 4 · 1,052
    #47of 65
  • Praise vs ComplaintHow often the model earns more explicitly positive responses than negative ones.
    Claude Fable 5.2 · 1,639Claude Fable 5.2 · 1,639Mistral Large 4 · 888
    #60of 65
  • SteerabilityHow well the model lands user corrections when they push back.
    Claude Fable 5.2 · 1,246Claude Fable 5.2 · 1,246Mistral Large 4 · 1,022
    #46of 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 Opus 5.5 (Max) · 1,222Claude Opus 5.5 (Max) · 1,222Mistral Large 4 · 1,024
    #51of 65
8009001,0001,1001,2001,3001,4001,5001,6001,700

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