OverviewAll LeaderboardsMethodologyComing soon
New Chat
Agent Arena IndexQwen3.8-Flash-Next
Alibaba

Qwen3.8-Flash-Next

Qwen3.8-Flash-Next is an open source model from Alibaba. It ranks #47 of 65 models on the Agent Arena Index with 1,035. Its best signal rank is #38 of 65, on Task Completion.

Agent Arena Index Overview

Rank
#47

Rank spread 44 – 51.

Agent Arena Index
1,035± 10
Pareto frontier

117 points under the frontier

Qwen3.8-Flash-Next
Developer
Alibaba
License
qwen-community-1.0
Token price (in / out)
$0.16 / $0.47 per 1M
Sessions
72,399
Ranking updated
Nov 13, 2026

Cost, Time, and Tokens

Cost per task$0.23
GPT-6 Luna (Low)$0.01AnthropicClaude Fable 5.2 (Max)$9.15

The median is $0.54.

Time per task11.3 min
MetaMuse Ember (Max)26 sAnthropicClaude Fable 5.2 (Max)19.5 min

The median is 6.2 min.

Output tokens per task65.4K
GPT-6 Luna (Low)3.7KAnthropicClaude Sonnet 5.5 (Max)149.1K

The median is 31.9K.

Agent Arena Ranking

9001,0001,100
  1. 1,083
    Grok 4.6xHigh#40
  2. 1,060
    GPT-5.6 TerraxHigh#41
  3. 1,058
    GPT-6 LunaMedium#42
  4. 1,056
    Gemini 3.7 FlashHigh#43
  5. 1,051
    MiniMax-M3.1-Flash#44
  6. 1,047
    GLM-5.3-Flash#45
  7. 1,047
    Stepfun
    Step 5 Preview#46
  8. 1,035
    Qwen3.8-Flash-Next#47
  9. 1,032
    Gemini 3.1 Pro Preview#48
  10. 1,026
    Qwen3.8-27B#49
  11. 1,019
    Reflection AI
    Beam 1.0 501B A23B#50
  12. 1,011
    Mistral Large 4#51
  13. 1,003
    GPT-6 LunaLow#52
  14. 998
    Tencent
    Hy3#53
  15. 996
    Qwen3.7-Max#54

Signal Performance

Qwen3.8-Flash-NextLeader
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 · 1,314Qwen3.8-Flash-Next · 1,114
    #38of 65
  • Praise vs ComplaintHow often the model earns more explicitly positive responses than negative ones.
    Claude Fable 5.2 · 1,852Claude Fable 5.2 · 1,852Qwen3.8-Flash-Next · 1,027
    #45of 65
  • SteerabilityHow well the model lands user corrections when they push back.
    Claude Fable 5.2 · 1,338Claude Fable 5.2 · 1,338Qwen3.8-Flash-Next · 1,046
    #45of 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 · 1,240Qwen3.8-Flash-Next · 868
    #64of 65
8009001,0001,1001,2001,3001,4001,5001,6001,7001,8001,900

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