readable AI benchmarks (simplified)
Alibaba
Qwen3.7 Plus
Qwen3.7 Plus has a Quality Score of 44.6, ranking 153rd among 571 scored models. Per 1M tokens, pricing is $0.400 input, $1.60 output, and $0.080 cached input. It accepts text, image, and video input, outputs text, and has a 1M token context window. Its Reliability Score is 50.5, ranking 119th among 573 scored models, above average (total average: 36.5). Its Value Score is 36.1, around average compared with the total Value average of 31.4.
Quality Score44.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score36.1
Factual reliability50.5
Cache Discount80%
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image, video
- Output modalities
- text
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $0.400
- Output
- $1.60
- Cached Input
- $0.080
- Cache write
- not available
- Cost per task
- $0.217
Capability
- Intelligence
- 25.2
- Coding
- not available
- Agentic
- not available
- Omniscience
- 1.1
- Correct
- 22.5%
- Blended price
- $0.296
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 44.0%
Correct 22.5%Incorrect 21.4%Partial / not attempted 56.0%
Artificial Analysis benchmarks
- GDPval-AA v2
- 14%
- τ³-Banking
- 18%
- SciCode
- 46%
- Humanity’s Last Exam
- 36%
- GPQA Diamond
- 90%
- CritPt
- 9%
- AA-Omniscience
- 51%
- AA-LCR
- 73%
Similar models
- Qwen3.6 PlusAlibabaQuality Score 46.0Value Score 35.6
- Qwen3.6 Max PreviewAlibabaQuality Score 49.1Value Score 33.9
- Qwen3.8 27B (Low)AlibabaQuality Score 38.5Value Score 29.5
- Qwen3.8 27B (Medium)AlibabaQuality Score 37.2Value Score 28.5
- Qwen3.8 27B (Xhigh)AlibabaQuality Score 48.4Value Score 37.1
- Qwen3.7 MaxAlibabaQuality Score 51.0Value Score 33.7