readable AI benchmarks (simplified)
Mistral
Devstral Small (Jul '25)
Devstral Small (Jul '25) has a Quality Score of 18.1, ranking 426th among 551 scored models. It accepts text input, outputs text, and has a 256k token context window. Its Reliability Score is 24.6, ranking 385th among 553 scored models, below average (total average: 35.6).
Quality Score18.1coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability24.6
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
- 7.6
- Coding
- not available
- Agentic
- not available
- Omniscience
- -50.8
- Correct
- 14.7%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 80.3%
Correct 14.7%Incorrect 65.6%Partial / not attempted 19.7%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 4%
- GPQA Diamond
- 41%
- CritPt
- 0%
- AA-Omniscience
- 25%
- AA-LCR
- 19%
Similar models
- Mistral Small 3.1MistralQuality Score 17.8Value Score not available
- Mistral Small 3.2MistralQuality Score 18.7Value Score not available
- Devstral Small (May '25)MistralQuality Score 17.5Value Score not available
- Devstral Small 2MistralQuality Score 16.4Value Score not available
- Devstral 2MistralQuality Score 20.0Value Score not available
- Mistral Small 4 (Non-reasoning)MistralQuality Score 19.8Value Score 17.7