readable AI benchmarks (simplified)
Alibaba
Qwen3 Max Thinking
Qwen3 Max Thinking has a Quality Score of 32.2, ranking 235th among 551 scored models. It has a 256k token context window. Its Reliability Score is 31.7, ranking 290th among 553 scored models, below average (total average: 35.6).
Quality Score32.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability31.7
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 256k tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- not available
- Output
- not available
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 21.3
- Coding
- not available
- Agentic
- not available
- Omniscience
- -36.6
- Correct
- 29.8%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 96.3%
Correct 29.8%Incorrect 66.4%Partial / not attempted 3.7%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 28%
- GPQA Diamond
- 86%
- CritPt
- 2%
- AA-Omniscience
- 32%
- AA-LCR
- 74%
Similar models
- Qwen3.5 27B (Reasoning)AlibabaQuality Score 31.6Value Score not available
- Qwen3.5 397B A17B (Reasoning)AlibabaQuality Score 31.5Value Score not available
- Qwen3.6 35B A3B (Reasoning)AlibabaQuality Score 33.5Value Score not available
- Qwen3.6 27B (Reasoning)AlibabaQuality Score 36.5Value Score not available
- Qwen3.5 35B A3B (Reasoning)AlibabaQuality Score 27.8Value Score not available
- Qwen3 Max Thinking (Preview)AlibabaQuality Score 27.8Value Score 19.4