OverviewAll LeaderboardsMethodologyComing soon
New Chat
Coding IndexGPT-6 Luna (Medium)
OpenAI

GPT-6 Luna (Medium)

GPT-6 Luna (Medium) is a proprietary model from OpenAI. It ranks #41 of 65 models on the Coding Index with 1,085. Its best signal rank is #19 of 65, on Bash Reliability.

Coding Index Overview

Rank
#41

Rank spread 34 – 44.

Coding Index
1,085± 8
Pareto frontier

15 points under the frontier

GPT-6 Luna (Medium)
Developer
OpenAI
License
Proprietary
Reasoning effort
Medium
Sessions
26,924
Ranking updated
Nov 13, 2026

Cost, Time, and Tokens

Cost per task$0.04
GPT-6 Luna (Low)$0.01AnthropicClaude Fable 5.2 (Max)$18.90

The median is $1.11.

Time per task3.1 min
MetaMuse Ember (Max)45 sMiMo-V2.6-Flash43.1 min

The median is 11.9 min.

Output tokens per task19.3K
GPT-6 Luna (Low)6.5KAnthropicClaude Sonnet 5.5 (Max)264.8K

The median is 74.8K.

Coding Ranking

9001,0001,100
  1. 1,106
    MiMo-V2.6-Flash#34
  2. 1,104
    GLM-5.3Max#35
  3. 1,100
    Meta
    Muse EmberMax#36
  4. 1,097
    Grok 4.6xHigh#37
  5. 1,090
    Qwen3.8-Max#38
  6. 1,088
    Kimi K3Max#39
  7. 1,087
    MiniMax-M3.1-Flash#40
  8. 1,085
    GPT-6 LunaMedium#41
  9. 1,074
    Gemini 3.8 FlashHigh#42
  10. 1,073
    GPT-5.6 TerraxHigh#43
  11. 1,069
    Stepfun
    Step 5 Preview#44
  12. 1,059
    GLM-5.3-Flash#45
  13. 1,054
    Qwen3.8-Flash-Next#46
  14. 1,038
    Qwen3.8-27B#47
  15. 1,031
    Gemini 3.7 FlashHigh#48

Signal Performance

GPT-6 Luna (Medium)Leader
Rank on the board
  • Task CompletionHow often the model gets users to confirm the task is done.
    Claude Sonnet 5.5 (Max) · 1,356Claude Sonnet 5.5 (Max) · 1,356GPT-6 Luna (Medium) · 1,085
    #45of 65
  • Praise vs ComplaintHow often the model earns more explicitly positive responses than negative ones.
    Claude Fable 5.2 · 2,017Claude Fable 5.2 · 2,017GPT-6 Luna (Medium) · 1,028
    #43of 65
  • SteerabilityHow well the model lands user corrections when they push back.
    Claude Fable 5.2 · 1,454Claude Fable 5.2 · 1,454GPT-6 Luna (Medium) · 1,106
    #34of 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 · 1,234Claude Sonnet 5 · 1,234GPT-6 Luna (Medium) · 1,160
    #19of 65
9001,0001,1001,2001,3001,4001,5001,6001,7001,8001,9002,0002,100

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