readable AI benchmarks (simplified)
Mistral
Mistral Medium 3.1
Mistral Medium 3.1 has a Quality Score of 20.5, ranking 373rd among 551 scored models. It has a 128k token context window. Its Reliability Score is 26.9, ranking 346th among 553 scored models, below average (total average: 35.6).
Quality Score20.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability26.9
Cache Discountnot available
Model specification
- Reasoning
- non-reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 128k 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
- 9.2
- Coding
- not available
- Agentic
- not available
- Omniscience
- -46.3
- Correct
- 20.8%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 87.8%
Correct 20.8%Incorrect 67.0%Partial / not attempted 12.2%
Artificial Analysis benchmarks
- GDPval-AA v2
- 0%
- τ³-Banking
- 8%
- SciCode
- 32%
- Humanity’s Last Exam
- 5%
- GPQA Diamond
- 59%
- CritPt
- 0%
- AA-Omniscience
- 27%
- AA-LCR
- 43%
Similar models
- Mistral Small 4 (Non-reasoning)MistralQuality Score 19.8Value Score 17.7
- Devstral 2MistralQuality Score 20.0Value Score not available
- Mistral Large 3MistralQuality Score 22.2Value Score 18.0
- Mistral Small 3.2MistralQuality Score 18.7Value Score not available
- Mistral Large 2 (Nov '24)MistralQuality Score 22.2Value Score not available
- Devstral Small (May '25)MistralQuality Score 17.5Value Score not available