Back to models
Intelligence Index
Reasoning setting
45.4#12 of 83measured models
Measured · Artificial Analysis v4.3.2- API price from
- $2.00 in / $6.00 out / 1M tokOpenRouter · Alibaba
- Context window
- 983.62K tok
Performance profile
ReasoningRank #9 of 107
92.8%
GPQA DiamondCodingRank #25 of 94
52.1%
SciCodeCost efficiencyRank #66 of 67
8.4pts / $
Intelligence ÷ eval costCapabilities
Context window
Modalities
Measured setting
Integration
Reasoning trade-offs
Source (opens in a new tab)Qwen3.8 Max (0902)
Cost per task (USD)
Qwen3.8 Max (0902)0902
- Intelligence Index
- 45.4
- Cost / task
- $5.41
- Evaluation time
- 35.9m
Pricing & access
USD per 1M tokens
- Input
- $2.00
- Output
- $6.00
- Cached input
- $0.25
Benchmarks
Full leaderboardSource (opens in a new tab)43.1%, rank 19 of 12652.1%, rank 25 of 9438.9%, rank 10 of 8780.3%, rank 28 of 1251,666 Elo, rank 9 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 16Muse Spark OpenExtra high43.9%
- 17JT-4.1 Flash 236B A21BReasoning43.6%
- 18Grok 4.7Extra high43.1%
- 19Qwen3.8 Max (0902)Reasoning43.1%
- 20GPT-5.6 TerraMax42.9%
- 21GPT-5.3-CodexExtra high42.5%
- 22Qwen3.8 2.4T A95BReasoning42.4%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherMiMo-V2.6-ProReasoning
- Intelligence Index
- 46.3+0.9
- Cost / task
- $0.133−98%
- Higher score, lower costPublic API and app accessGemini 4 ArgonHigh
- Intelligence Index
- 52.6+7.1
- Cost / task
- $1.99−63%
- More from AlibabaQwen3.8 2.4T A95BReasoning
- Intelligence Index
- 39.9−5.5
- Cost / task
- $2.16−60%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.