OverviewAll LeaderboardsMethodology
New Chat
Agent Arena IndexGPT-6.2 Sol (Max)
OpenAI

GPT-6.2 Sol (Max)

GPT-6.2 Sol (Max) is a proprietary model from OpenAI. It ranks #11 of 68 models on the Agent Arena Index with 1,241. Its best signal rank is #11 of 68, on Steerability.

Agent Arena Index Overview

Rank
#11

Rank spread 5 – 17.

Agent Arena Index
1,241± 31
Pareto frontier
GPT-6.2 Sol
Developer
OpenAI
License
Proprietary
Token price (in / out)
$2 / $10 per 1M
Reasoning effort
Max
Sessions
3,764
Ranking updated
Nov 18, 2026

Cost, Time, and Tokens

Cost per task$0.96
Gemini 4 Argon (High)$0.66AnthropicClaude Fable 5.2 (Max)$9.15

The median is $2.29.

Time per task—
Output tokens per task37.3K
Gemini 4 Argon (High)21.7KAnthropicClaude Sonnet 5.5 (Max)144.3K

The median is 45.4K.

Agent Arena Ranking

1,1001,2001,300
  1. 1,303
    Gemini 4 CarbonHigh#4
  2. 1,296
    Anthropic
    Claude Sonnet 5.5Max#5
  3. 1,291
    GPT-6.2 AstraMax#6
  4. 1,282
    GPT-6 AstraMax#7
  5. 1,273
    Anthropic
    Claude Opus 5.5High#8
  6. 1,272
    Anthropic
    Claude Fable 5.1Max#9
  7. 1,271
    Gemini 4 HydrogenHigh#10
  8. 1,241
    GPT-6.2 SolMax#11
  9. 1,241
    GPT-6.1 SolMax#12
  10. 1,230
    GPT-6.1 TerraMax#13
  11. 1,229
    Gemini 4 ArgonHigh#14
  12. 1,201
    Meta
    Muse Wonder FullMax#15
  13. 1,201
    GPT-6.1 SolMedium#16
  14. 1,196
    Anthropic
    Claude Sonnet 5.5High#17
  15. 1,189
    Qwen4-MaxxHigh#18

Signal Performance

GPT-6.2 SolLeader
Rank on the board
  • Task CompletionHow often the model gets users to confirm the task is done.
    Claude Fable 5.2 · 1,343Claude Fable 5.2 · 1,343GPT-6.2 Sol · 1,228
    #13of 68
  • Praise vs ComplaintHow often the model earns more explicitly positive responses than negative ones.
    Claude Fable 5.2 · 1,779Claude Fable 5.2 · 1,779GPT-6.2 Sol · 1,324
    #13of 68
  • SteerabilityHow well the model lands user corrections when they push back.
    Claude Fable 5.2 · 1,331Claude Fable 5.2 · 1,331GPT-6.2 Sol · 1,220
    #11of 68
  • 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-6.2 Sol · 1,141
    #29of 68
1,0001,1001,2001,3001,4001,5001,6001,7001,800

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