readable AI benchmarks (simplified)
Mistral
Mistral Large 4 Preview
Mistral Large 4 Preview has a Quality Score of 53.2, ranking 90th among 572 scored models. Per 1M tokens, pricing is $1.36 input, $4.18 output, $0.140 cached input, and $1.36 cache write. It has a 524,288 token context window. Its Reliability Score is 47.4, ranking 158th among 574 scored models, above average (total average: 36.5). Its Value Score is 38.3, high compared with the total Value average of 31.5.
Quality Score53.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score38.3
Factual reliability47.4
Cache Discount90%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 524,288 tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $1.36
- Output
- $4.18
- Cached Input
- $0.140
- Cache write
- $1.36
- Cost per task
- $1.13
Capability
- Intelligence
- 38.4
- Coding
- not available
- Agentic
- not available
- Omniscience
- -5.3
- Correct
- 25.8%
- Blended price
- $0.788
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 56.9%
Correct 25.8%Incorrect 31.1%Partial / not attempted 43.1%
Artificial Analysis benchmarks
- GDPval-AA v2
- 46%
- SciCode
- 54%
- Humanity’s Last Exam
- 35%
- CritPt
- 11%
- AA-Omniscience
- 47%
- AA-LCR
- 81%
Similar models
- Mistral Medium 3.5MistralQuality Score 26.7Value Score 18.4
- 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