readable AI benchmarks (simplified)
Alibaba
Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B has a Quality Score of 56.8, ranking 72nd among 571 scored models. Per 1M tokens, pricing is $2.00 input, $6.00 output, and $0.250 cached input. It accepts text input, outputs text, and has a 262k token context window. Its Reliability Score is 52.2, ranking 105th among 573 scored models, above average (total average: 36.5). Its Value Score is 38.9, high compared with the total Value average of 31.4.
Quality Score56.8coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score38.9
Factual reliability52.2
Cache Discount88%
Model specification
- Reasoning
- reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 262k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $2.00
- Output
- $6.00
- Cached Input
- $0.250
- Cache write
- not available
- Cost per task
- $2.16
Capability
- Intelligence
- 39.9
- Coding
- not available
- Agentic
- not available
- Omniscience
- 4.3
- Correct
- 31.3%
- Blended price
- $1.18
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 58.2%
Correct 31.3%Incorrect 26.9%Partial / not attempted 41.8%
Artificial Analysis benchmarks
- GDPval-AA v2
- 56%
- τ³-Banking
- 49%
- SciCode
- 54%
- Humanity’s Last Exam
- 42%
- GPQA Diamond
- 94%
- CritPt
- 20%
- AA-Omniscience
- 52%
- AA-LCR
- 80%
Similar models
- Qwen3.8 MaxAlibabaQuality Score 56.7Value Score 38.9
- Qwen3.8-Flash-NextAlibabaQuality Score 53.2Value Score 48.2
- Qwen3.8 Max (0902)AlibabaQuality Score 62.9Value Score 43.2
- Qwen3.7 MaxAlibabaQuality Score 51.0Value Score 33.7
- Qwen3.8 27B (Xhigh)AlibabaQuality Score 48.4Value Score 37.1
- Qwen3.6 Max PreviewAlibabaQuality Score 49.1Value Score 33.9