readable AI benchmarks (simplified)
Mistral
Magistral Small 1
Magistral Small 1 has a Quality Score of 20.2, ranking 383rd among 551 scored models. It accepts text input, outputs text, and has a 40k token context window. Its Reliability Score is 27.8, ranking 336th among 553 scored models, below average (total average: 35.6).
Quality Score20.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability27.8
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 40k 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
- 8.2
- Coding
- not available
- Agentic
- not available
- Omniscience
- -44.4
- Correct
- 18.0%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 80.4%
Correct 18.0%Incorrect 62.4%Partial / not attempted 19.6%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 8%
- GPQA Diamond
- 64%
- CritPt
- 0%
- AA-Omniscience
- 28%
- AA-LCR
- 0%
Similar models
- Magistral Small 1.2MistralQuality Score 15.3Value Score not available
- Magistral Medium 1MistralQuality Score 25.2Value Score not available
- Mistral Small 4 (Reasoning)MistralQuality Score 26.1Value Score 23.4
- Magistral Medium 1.2MistralQuality Score 27.4Value Score not available
- Mistral Medium 3.5MistralQuality Score 26.7Value Score 18.4
- Devstral 2MistralQuality Score 20.0Value Score not available