OverviewAll LeaderboardsMethodologyComing soon
New Chat
Agent Arena IndexClaude Opus 5 (Max)
AnthropicAnthropic

Claude Opus 5 (Max)

Claude Opus 5 (Max) is a proprietary model from Anthropic. It ranks #18 of 65 models on the Agent Arena Index with 1,174. Its best signal rank is #12 of 65, on Task Completion.

Agent Arena Index Overview

Rank
#18

Rank spread 12 – 21.

Agent Arena Index
1,174± 17
Pareto frontier

133 points under the frontier

Claude Opus 5
Developer
AnthropicAnthropic
License
Proprietary
Token price (in / out)
$5 / $25 per 1M
Reasoning effort
Max
Sessions
18,015
Ranking updated
Nov 13, 2026

Cost, Time, and Tokens

Cost per task$4.50
GPT-6 Luna (Low)$0.01AnthropicClaude Fable 5.2 (Max)$9.15

The median is $0.54.

Time per task9.9 min
MetaMuse Ember (Max)26 sAnthropicClaude Fable 5.2 (Max)19.5 min

The median is 6.2 min.

Output tokens per task60.3K
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. 1,225
    Gemini 4 ArgonHigh#11
  2. 1,200
    Meta
    Muse Wonder FullMax#12
  3. 1,198
    GPT-6.1 SolMedium#13
  4. 1,191
    Anthropic
    Claude Sonnet 5.5High#14
  5. 1,191
    Qwen4-MaxxHigh#15
  6. 1,176
    Anthropic
    Claude Fable 5High#16
  7. 1,175
    GPT-6 SolMax#17
  8. 1,174
    Anthropic
    Claude Opus 5Max#18
  9. 1,170
    Tencent
    Hy4#19
  10. 1,152
    GPT-6.1 TerraMedium#20
  11. 1,146
    Kimi K3.1 ProMax#21
  12. 1,143
    GPT-5.6 SolxHigh#22
  13. 1,132
    Thinking Machines
    Inkling 2 Small#23
  14. 1,118
    Grok 4.7xHigh#24
  15. 1,117
    MiMo-V2.6-Pro#25

Signal Performance

Claude Opus 5Leader
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 · 1,314Claude Opus 5 · 1,214
    #12of 65
  • Praise vs ComplaintHow often the model earns more explicitly positive responses than negative ones.
    Claude Fable 5.2 · 1,852Claude Fable 5.2 · 1,852Claude Opus 5 · 1,194
    #17of 65
  • SteerabilityHow well the model lands user corrections when they push back.
    Claude Fable 5.2 · 1,338Claude Fable 5.2 · 1,338Claude Opus 5 · 1,110
    #25of 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 · 1,240Claude Opus 5 · 1,185
    #14of 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