OverviewAll LeaderboardsMethodologyComing soon
New Chat
Agent Arena IndexQwen4-Max (xHigh)
Alibaba

Qwen4-Max (xHigh)

Qwen4-Max (xHigh) is a proprietary model from Alibaba. It ranks #15 of 65 models on the Agent Arena Index with 1,191. Its best signal rank is #13 of 65, on Task Completion.

Agent Arena Index Overview

Rank
#15

Rank spread 12 – 19.

Agent Arena Index
1,191± 17
Pareto frontier

117 points under the frontier

Qwen4-Max
Developer
Alibaba
License
Proprietary
Token price (in / out)
$1.50 / $4.50 per 1M
Reasoning effort
xHigh
Sessions
10,731
Ranking updated
Nov 13, 2026

Cost, Time, and Tokens

Cost per task$1.44
GPT-6.1 Sol (Medium)$0.40AnthropicClaude Fable 5.2 (Max)$9.15

The median is $1.47.

Time per task16.4 min
AnthropicClaude Sonnet 5.5 (High)2.4 minAnthropicClaude Fable 5.2 (Max)19.5 min

The median is 9.4 min.

Output tokens per task46.2K
GPT-6.1 Sol (Medium)9.4KAnthropicClaude Sonnet 5.5 (Max)149.1K

The median is 44.5K.

Agent Arena Ranking

1,0001,1001,200
  1. 1,268
    Anthropic
    Claude Opus 5.5High#8
  2. 1,246
    GPT-6.1 SolMax#9
  3. 1,241
    GPT-6.1 TerraMax#10
  4. 1,225
    Gemini 4 ArgonHigh#11
  5. 1,200
    Meta
    Muse Wonder FullMax#12
  6. 1,198
    GPT-6.1 SolMedium#13
  7. 1,191
    Anthropic
    Claude Sonnet 5.5High#14
  8. 1,191
    Qwen4-MaxxHigh#15
  9. 1,176
    Anthropic
    Claude Fable 5High#16
  10. 1,175
    GPT-6 SolMax#17
  11. 1,174
    Anthropic
    Claude Opus 5Max#18
  12. 1,170
    Tencent
    Hy4#19
  13. 1,152
    GPT-6.1 TerraMedium#20
  14. 1,146
    Kimi K3.1 ProMax#21
  15. 1,143
    GPT-5.6 SolxHigh#22

Signal Performance

Qwen4-MaxLeader
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 · 1,314Qwen4-Max · 1,211
    #13of 65
  • Praise vs ComplaintHow often the model earns more explicitly positive responses than negative ones.
    Claude Fable 5.2 · 1,852Claude Fable 5.2 · 1,852Qwen4-Max · 1,224
    #15of 65
  • SteerabilityHow well the model lands user corrections when they push back.
    Claude Fable 5.2 · 1,338Claude Fable 5.2 · 1,338Qwen4-Max · 1,167
    #19of 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 · 1,240Qwen4-Max · 1,130
    #29of 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