readable AI benchmarks (simplified)
Mistral
Mistral Medium 3.5
Mistral Medium 3.5 has a Quality Score of 26.7, ranking 312th among 577 scored models. Per 1M tokens, pricing is $1.50 input, $7.50 output, and $0.150 cached input. It accepts text and image input, outputs text, and has a 256k token context window. Its Reliability Score is 31.6, ranking 316th among 579 scored models, below average (total average: 36.6). Its Value Score is 18.4, low compared with the total Value average of 31.8.
Quality Score26.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score18.4
Factual reliability31.6
Cache Discount90%
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
- $1.50
- Output
- $7.50
- Cached Input
- $0.150
- Cache write
- not available
- Cost per task
- $0.502
Capability
- Intelligence
- 14.2
- Coding
- not available
- Agentic
- not available
- Omniscience
- -36.8
- Correct
- 24.7%
- Blended price
- $1.16
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 86.1%
Correct 24.7%Incorrect 61.5%Partial / not attempted 13.9%
Artificial Analysis benchmarks
- GDPval-AA v2
- 13%
- τ³-Banking
- 15%
- SciCode
- 40%
- Humanity’s Last Exam
- 14%
- GPQA Diamond
- 75%
- CritPt
- 0%
- AA-Omniscience
- 32%
- AA-LCR
- 69%
Similar models
- Magistral Medium 1.2MistralQuality Score 27.4Value Score not available
- Mistral Small 4 (Reasoning)MistralQuality Score 26.1Value Score 23.4
- Magistral Medium 1MistralQuality Score 25.2Value Score not available
- Magistral Small 1MistralQuality Score 20.2Value Score not available
- Magistral Small 1.2MistralQuality Score 15.3Value Score not available
- Mistral Medium 3MistralQuality Score 24.1Value Score not available