readable AI benchmarks (simplified)
Mistral
Mistral Large 4 Preview
Mistral Large 4 Preview has a Quality Score of 42.6, ranking 108th among 217 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 46.3, ranking 122nd among 229 scored models, above average (total average: 46.1). Its Value Score is 30.7, around average compared with the total Value average of 33.8.
Quality Score42.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score30.7
Factual reliability46.3
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
- $5.54
Capability
- Intelligence
- 25.3
- Coding
- not available
- Agentic
- not available
- Omniscience
- -7.5
- Correct
- 23.9%
- Blended price
- $0.788
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 55.4%
Correct 23.9%Incorrect 31.4%Partial / not attempted 44.6%
Artificial Analysis benchmarks
- SciCode
- 54%
- Humanity’s Last Exam
- 35%
- CritPt
- 11%
- AA-Omniscience
- 46%
- AA-LCR
- 81%
Similar models
- Mistral Large 4 PreviewMistralQuality Score 42.6Value Score 30.7
- Magistral Medium 1.2MistralQuality Score not availableValue Score not available
- Magistral Small 1MistralQuality Score not availableValue Score not available
- Magistral Small 1.2MistralQuality Score not availableValue Score not available
- Mistral Medium 3.5MistralQuality Score not availableValue Score not available
- Mistral Small 4 (Reasoning)MistralQuality Score not availableValue Score not available