Back to models
Intelligence Index
Reasoning setting
25.2#44 of 83measured models
Measured · Artificial Analysis v4.3.2- API price from
- $0.32 in / $1.28 out / 1M tokOpenRouter · Alibaba
- Context window
- 1M tok
Performance profile
ReasoningRank #20 of 107
90.0%
GPQA DiamondCodingRank #45 of 94
46.1%
SciCodeCost efficiencyRank #25 of 67
115.9pts / $
Intelligence ÷ eval costCapabilities
Context window
Modalities
Measured setting
Integration
Reasoning trade-offs
Source (opens in a new tab)Qwen3.7 Plus
Cost per task (USD) · log scale
Qwen3.7 PlusReasoning
- Intelligence Index
- 25.2
- Cost / task
- $0.217
- Evaluation time
- 9.7m
Pricing & access
USD per 1M tokens
- Input
- $0.32
- Output
- $1.28
- Cached input
- $0.064
Benchmarks
Full leaderboardSource (opens in a new tab)35.6%, rank 34 of 12646.1%, rank 45 of 941.0%, rank 39 of 8773.0%, rank 57 of 125768 Elo, rank 63 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 31Qwen3.8-Flash-NextReasoning38.0%
- 32Agnes 2.5 Pro BetaReasoning37.5%
- 33Motif 3Reasoning37.0%
- 34Qwen3.7 PlusReasoning35.6%
- 35MiMo-V2.6-FlashReasoning35.1%
- 36Mistral Large 4Reasoning35.0%
- 36Kimi K2.7 CodeReasoning35.0%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherHy3Reasoning
- Intelligence Index
- 25.3+0.1
- Cost / task
- $0.072−67%
- Higher score, lower costGPT-6 LunaMax
- Intelligence Index
- 38.1+13.0
- Cost / task
- $0.068−69%
- More from AlibabaQwen3.5 397B A17BReasoning
- Intelligence Index
- 18.4−6.7
- Cost / task
- $0.475+119%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.