Qwen 3.8 Max
Alibaba open 2026-08-03
SOTA
Qwen 3.8 Max outscores the executioner, Claude Haiku 5.5 (43.4): it is SOTA, the top tier right now.
- Score
- 45.4
- Artificial Analysis Intelligence Index
- Best rank
- #2
- Arena — Vision
- Price
- $3.00
- Blended Price, USD per 1M tokens (3:1 input:output)
Every score this model has on the boards we track, one board at a time. Nothing is averaged across boards.
Scores on each board Each rank is the board’s own: the rank it publishes, or the model’s place in the board’s own order where it publishes none. The bar shows how much of that board the model ranks ahead of. Scores from different boards cannot be compared.
- Artificial Analysis LLM LeaderboardArtificial Analysis Intelligence Index45.4No. 14 of 375
- Arena — AgentOverall0.023No. 23 of 52
- Artificial Analysis Coding AgentsArtificial Analysis Coding Agent Index0.433No. 18 of 24
- Epoch AI Benchmarking HubFrontierMath Tiers 1–374.7%No. 19 of 82
- Terminal-Bench 4.0Terminal-Bench 4.027.0%No. 25 of 35
- Arena — CodeOverall1674No. 10 of 142
- Arena — TextOverall (style control)1483No. 22 of 414
- Arena — VisionOverall (style control)1301No. 2 of 165
Scores at each effort setting The same model at each effort setting. A bar runs from zero to that board’s best score, so read each board on its own and never across boards.
Tested at one setting only
- Epoch AI Benchmarking Hubxhigh74.7%
- Terminal-Bench 4.0 · Claude Codemax27.0%
Value: where it sits on the kill line Each dot is a model: further right costs more, higher up scores more. Where the dashed lines cross stands the executioner. Above it is SOTA, the top tier; below and to the left is cheaper and weaker, the low-cost picks.
The executioner is the best value on the board: every model that costs more and scores no higher is killed.
Compare on the home page chart → How the kill line is drawn →
Providers
Where to run it: the developer's own page first, then the clouds that serve it.
- Alibaba Official qwencloud.com ↗
- Alibaba Cloud Model Studio alibabacloud.com ↗
- OpenRouter openrouter.ai ↗
Other Qwen 3.8 models
Price, and the Artificial Analysis Intelligence Index score from Artificial Analysis LLM Leaderboard.
- Qwen 3.8 Flash Next Killed $0.23 39.8
- Qwen 3.8 $1.13 33.7
Compare with another SOTA model
- Qwen 3.8 Max vs Claude Fable 5
- Qwen 3.8 Max vs Claude Fable 5.1
- Qwen 3.8 Max vs Claude Haiku 5.5
- Qwen 3.8 Max vs Claude Opus 5.5
- Qwen 3.8 Max vs Claude Sonnet 5.5
- Qwen 3.8 Max vs Gemini 4 Argon
- Qwen 3.8 Max vs Kimi K3
- Qwen 3.8 Max vs Muse Spark 1.3
- Qwen 3.8 Max vs GPT 6.1 Sol
- Qwen 3.8 Max vs GPT 6 Astra
- Qwen 3.8 Max vs Step 5
- Qwen 3.8 Max vs Grok 4.7
- Qwen 3.8 Max vs MiMo V2.6 Pro
- Qwen 3.8 Max vs GLM 5.3
Details
- Family
- Qwen → Qwen 3.8
- Blended Price, USD per 1M tokens (3:1 input:output)
- $3.00
- Sources
- 8 boards ·12 scores ·7 settings
- Also written as
-
Qwen3.8 Maxqwen3-8-maxqwen3.8-maxQwen3.8 2.4T A95Bqwen3-8-2-4t-a95bQwen/Qwen3.8-2.4T-A95BQwen 3.8 Max