OverviewAll LeaderboardsMethodologyComing soon
New Chat
Agent Arena IndexKimi K3.1 Pro (Max)
Moonshot

Kimi K3.1 Pro (Max)

Kimi K3.1 Pro (Max) is an open source model from Moonshot. It ranks #21 of 65 models on the Agent Arena Index with 1,146. Its best signal rank is #19 of 65, on Praise vs Complaint.

Agent Arena Index Overview

Rank
#21

Rank spread 17 – 25.

Agent Arena Index
1,146± 14
Pareto frontier

101 points under the frontier

Kimi K3.1 Pro
Developer
Moonshot
License
Kimi K3.1 Pro License
Token price (in / out)
$2 / $10 per 1M
Reasoning effort
Max
Sessions
17,859
Ranking updated
Nov 13, 2026

Cost, Time, and Tokens

Cost per task$1.15
GPT-6 Luna (Low)$0.01AnthropicClaude Fable 5.2 (Max)$9.15

The median is $0.54.

Time per task12.2 min
MetaMuse Ember (Max)26 sAnthropicClaude Fable 5.2 (Max)19.5 min

The median is 6.2 min.

Output tokens per task32.8K
GPT-6 Luna (Low)3.7KAnthropicClaude Sonnet 5.5 (Max)149.1K

The median is 31.9K.

Agent Arena Ranking

1,0001,1001,200
  1. 1,191
    Anthropic
    Claude Sonnet 5.5High#14
  2. 1,191
    Qwen4-MaxxHigh#15
  3. 1,176
    Anthropic
    Claude Fable 5High#16
  4. 1,175
    GPT-6 SolMax#17
  5. 1,174
    Anthropic
    Claude Opus 5Max#18
  6. 1,170
    Tencent
    Hy4#19
  7. 1,152
    GPT-6.1 TerraMedium#20
  8. 1,146
    Kimi K3.1 ProMax#21
  9. 1,143
    GPT-5.6 SolxHigh#22
  10. 1,132
    Thinking Machines
    Inkling 2 Small#23
  11. 1,118
    Grok 4.7xHigh#24
  12. 1,117
    MiMo-V2.6-Pro#25
  13. 1,117
    Meta
    Muse EmberMax#26
  14. 1,115
    Gemini 3.8 FlashHigh#27
  15. 1,112
    DeepSeek-V4.1-Flash-20261017Max#28

Signal Performance

Kimi K3.1 ProLeader
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 · 1,314Kimi K3.1 Pro · 1,140
    #30of 65
  • Praise vs ComplaintHow often the model earns more explicitly positive responses than negative ones.
    Claude Fable 5.2 · 1,852Claude Fable 5.2 · 1,852Kimi K3.1 Pro · 1,158
    #19of 65
  • SteerabilityHow well the model lands user corrections when they push back.
    Claude Fable 5.2 · 1,338Claude Fable 5.2 · 1,338Kimi K3.1 Pro · 1,132
    #22of 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 · 1,240Kimi K3.1 Pro · 1,160
    #21of 65
1,0001,1001,2001,3001,4001,5001,6001,7001,8001,900

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