readable AI benchmarks (simplified)
Mistral
Devstral 2
Devstral 2 has a Quality Score of 20.0, ranking 406th among 571 scored models. It accepts text input, outputs text, and has a 256k token context window. Its Reliability Score is 26.6, ranking 371st among 573 scored models, below average (total average: 36.5).
Quality Score20.0coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability26.6
Cache Discountnot available
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 256k tokens
- Weights
- open 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
- 8.6
- Coding
- not available
- Agentic
- not available
- Omniscience
- -46.7
- Correct
- 20.8%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 88.3%
Correct 20.8%Incorrect 67.5%Partial / not attempted 11.7%
Artificial Analysis benchmarks
- GDPval-AA v2
- 2%
- τ³-Banking
- 11%
- SciCode
- 33%
- Humanity’s Last Exam
- 4%
- GPQA Diamond
- 59%
- CritPt
- 0%
- AA-Omniscience
- 27%
- AA-LCR
- 32%
Similar models
- Mistral Small 4 (Non-reasoning)MistralQuality Score 19.8Value Score 17.7
- Mistral Medium 3.1MistralQuality Score 20.5Value Score not available
- Mistral Small 3.2MistralQuality Score 18.7Value Score not available
- Devstral Small (Jul '25)MistralQuality Score 18.1Value Score not available
- Devstral Small (May '25)MistralQuality Score 17.5Value Score not available
- Mistral Large 3MistralQuality Score 22.2Value Score 18.0