Mistral
Mistral Small 4 (Reasoning)
Quality Score22.0
Value Score21.4
Reliability34.8
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image
- Output modalities
- text
- Context window
- 256k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.150
- Output
- $0.600
- Cached Input
- not available
- Cached Output
- not available
- Cost per task
- $0.100
Capability
- Intelligence
- 19.7
- Coding
- 26.6
- Agentic
- 4.6
- Omniscience
- -30.4
- Correct
- 21.7%
- Blended price
- $0.195
Answer outcomes
Correct 21.7%Incorrect 52.1%Abstained 26.2%
Artificial Analysis benchmarks
- GDPval-AA v2
- 4%
- τ³-Banking
- 5%
- Terminal-Bench v2.1
- 21%
- SciCode
- 38%
- Humanity’s Last Exam
- 10%
- GPQA Diamond
- 77%
- CritPt
- 0%
- AA-Omniscience
- 35%
- AA-LCR
- 47%
Similar models
- Magistral Medium 1.2MistralQuality Score 20.7Value Score not available
- Mistral Medium 3.5MistralQuality Score 30.2Value Score 24.6
- Magistral Small 1.2MistralQuality Score 10.2Value Score 10.8
- Devstral 2MistralQuality Score 20.4Value Score 24.1
- Mistral Large 3MistralQuality Score 19.6Value Score 16.7
- Devstral Small 2MistralQuality Score 16.8Value Score 21.0