OverviewAll LeaderboardsMethodologyComing soon
New Chat
Agent Arena IndexGPT-6 Luna (Max)
OpenAI

GPT-6 Luna (Max)

GPT-6 Luna (Max) is a proprietary model from OpenAI. It ranks #32 of 65 models on the Agent Arena Index with 1,105. Its best signal rank is #15 of 65, on Bash Reliability.

Agent Arena Index Overview

Rank
#32

Rank spread 24 – 38.

Agent Arena Index
1,105± 6
Pareto frontier

12 points under the frontier

GPT-6 Luna (Max)
Developer
OpenAI
License
Proprietary
Token price (in / out)
$0.05 / $0.25 per 1M
Reasoning effort
Max
Sessions
172,358
Ranking updated
Nov 13, 2026

Cost, Time, and Tokens

Cost per task$0.08
GPT-6 Luna (Low)$0.01AnthropicClaude Fable 5.2 (Max)$9.15

The median is $0.54.

Time per task6.1 min
MetaMuse Ember (Max)26 sAnthropicClaude Fable 5.2 (Max)19.5 min

The median is 6.2 min.

Output tokens per task41.6K
GPT-6 Luna (Low)3.7KAnthropicClaude Sonnet 5.5 (Max)149.1K

The median is 31.9K.

Agent Arena Ranking

1,0001,100
  1. 1,117
    MiMo-V2.6-Pro#25
  2. 1,117
    Meta
    Muse EmberMax#26
  3. 1,115
    Gemini 3.8 FlashHigh#27
  4. 1,112
    DeepSeek-V4.1-Flash-20261017Max#28
  5. 1,111
    Meta
    Muse WonderMax#29
  6. 1,111
    Anthropic
    Claude Sonnet 5High#30
  7. 1,111
    Meta
    Muse Spark 1.3Max#31
  8. 1,105
    GPT-6 LunaMax#32
  9. 1,100
    MiMo-V2.6-Flash#33
  10. 1,098
    Anthropic
    Claude Haiku 5.5High#34
  11. 1,095
    GLM-5.3Max#35
  12. 1,094
    Tencent
    Hy4 preview#36
  13. 1,092
    Kimi K3Max#37
  14. 1,089
    Qwen3.8-Max#38
  15. 1,089
    GLM-5.2Max#39

Signal Performance

GPT-6 Luna (Max)Leader
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 · 1,314GPT-6 Luna (Max) · 1,111
    #39of 65
  • Praise vs ComplaintHow often the model earns more explicitly positive responses than negative ones.
    Claude Fable 5.2 · 1,852Claude Fable 5.2 · 1,852GPT-6 Luna (Max) · 1,059
    #38of 65
  • SteerabilityHow well the model lands user corrections when they push back.
    Claude Fable 5.2 · 1,338Claude Fable 5.2 · 1,338GPT-6 Luna (Max) · 1,106
    #26of 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 · 1,240GPT-6 Luna (Max) · 1,182
    #15of 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