readable AI benchmarks (simplified)
Alibaba
Qwen3.8 Max
Qwen3.8 Max has a Quality Score of 46.5, ranking 53rd among 296 scored models. Per 1M tokens, pricing is $2.00 input, $6.00 output, and $0.250 cached input. It has a 1M token context window. Its Reliability Score is 51.7, ranking 54th among 296 scored models, above average (total average: 35.7). Its Value Score is 33.4, around average compared with the total Value average of 29.1.
Quality Score46.5coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1
Value Score33.4
Reliability51.7
Cache Discount88%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $2.00
- Output
- $6.00
- Cached Input
- $0.250
- Cache write
- not available
- Cost per task
- $2.67
Capability
- Intelligence
- 40.3
- Coding
- not available
- Agentic
- not available
- Omniscience
- 3.4
- Correct
- 31.9%
- Blended price
- $1.18
Answer outcomes
Attempt rate: 60.3%
Correct 31.9%Incorrect 28.4%Abstained 39.7%
Artificial Analysis benchmarks
- GDPval-AA v2
- 57%
- τ³-Banking
- 51%
- SciCode
- 53%
- Humanity’s Last Exam
- 43%
- GPQA Diamond
- 93%
- CritPt
- 20%
- AA-Omniscience
- 52%
- AA-LCR
- 78%
Similar models
- Qwen3.8 2.4T A95BAlibabaQuality Score 46.3Value Score 33.1
- Qwen3.8 Max (0902)AlibabaQuality Score 51.2Value Score 36.9
- Qwen3.8-Flash-NextAlibabaQuality Score 38.3Value Score 41.2
- Qwen3.8 27B (xhigh)AlibabaQuality Score 31.1Value Score 28.6
- Qwen3.7 PlusAlibabaQuality Score 35.6Value Score 26.3
- Qwen3.8 27B (medium)AlibabaQuality Score 23.2Value Score 24.4