readable AI benchmarks (simplified)
Mistral
Mistral Small 4 (Non-reasoning)
Mistral Small 4 (Non-reasoning) has a Quality Score of 19.8, ranking 408th among 571 scored models. Per 1M tokens, pricing is $0.150 input, $0.600 output, and $0.015 cached input. It has a 256k token context window. Its Reliability Score is 25.7, ranking 384th among 573 scored models, below average (total average: 36.5). Its Value Score is 17.7, low compared with the total Value average of 31.4.
Quality Score19.8coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score17.7
Factual reliability25.7
Cache Discount90%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 256k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.150
- Output
- $0.600
- Cached Input
- $0.015
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 9.0
- Coding
- not available
- Agentic
- not available
- Omniscience
- -48.5
- Correct
- 16.6%
- Blended price
- $0.100
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 81.6%
Correct 16.6%Incorrect 65.1%Partial / not attempted 18.4%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 4%
- GPQA Diamond
- 57%
- CritPt
- 0%
- AA-Omniscience
- 26%
- AA-LCR
- 28%
Similar models
- Devstral 2MistralQuality Score 20.0Value Score not available
- Mistral Medium 3.1MistralQuality Score 20.5Value 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 (Jul '25)MistralQuality Score 18.1Value Score not available
- Mistral Large 3MistralQuality Score 22.2Value Score 18.0