readable AI benchmarks (simplified)
Mistral
Ministral 3 3B
Ministral 3 3B has a Quality Score of 12.7, ranking 526th among 571 scored models. Per 1M tokens, pricing is $0.100 input, $0.100 output, and $0.010 cached input. It accepts text and image input, outputs text, and has a 256k token context window. Its Reliability Score is 18.0, ranking 506th among 573 scored models, below average (total average: 36.5). Its Value Score is 12.1, low compared with the total Value average of 31.4.
Quality Score12.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score12.1
Factual reliability18.0
Cache Discount90%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text, image
- Output modalities
- text
- Context window
- 256k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.100
- Output
- $0.100
- Cached Input
- $0.010
- Cache write
- not available
- Cost per task
- $0.0078
Capability
- Intelligence
- 4.8
- Coding
- not available
- Agentic
- not available
- Omniscience
- -64.0
- Correct
- 9.0%
- Blended price
- $0.037
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 82.0%
Correct 9.0%Incorrect 73.0%Partial / not attempted 18.0%
Artificial Analysis benchmarks
- GDPval-AA v2
- 0%
- τ³-Banking
- 5%
- SciCode
- 15%
- Humanity’s Last Exam
- 5%
- GPQA Diamond
- 36%
- CritPt
- 0%
- AA-Omniscience
- 18%
- AA-LCR
- 17%
Similar models
- Mistral 7B InstructMistralQuality Score 12.6Value Score not available
- Ministral 3 14BMistralQuality Score 13.1Value Score 12.0
- Ministral 3 8BMistralQuality Score 12.0Value Score 11.2
- Devstral Small 2MistralQuality Score 16.4Value Score not available
- Mistral Small 3.1MistralQuality Score 17.8Value Score not available
- Devstral Small (Jul '25)MistralQuality Score 18.1Value Score not available