readable AI benchmarks (simplified)
Mistral
Mistral Large 3
Mistral Large 3 has a Quality Score of 22.2, ranking 359th among 572 scored models. Per 1M tokens, pricing is $0.500 input, $1.50 output, and $0.050 cached input. It accepts text and image input, outputs text, and has a 256k token context window. Its Reliability Score is 30.2, ranking 323rd among 574 scored models, below average (total average: 36.5). Its Value Score is 18.0, low compared with the total Value average of 31.5.
Quality Score22.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score18.0
Factual reliability30.2
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
- $0.500
- Output
- $1.50
- Cached Input
- $0.050
- Cache write
- not available
- Cost per task
- $0.031
Capability
- Intelligence
- 9.3
- Coding
- not available
- Agentic
- not available
- Omniscience
- -39.6
- Correct
- 24.9%
- Blended price
- $0.285
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 89.5%
Correct 24.9%Incorrect 64.5%Partial / not attempted 10.5%
Artificial Analysis benchmarks
- GDPval-AA v2
- 0%
- τ³-Banking
- 6%
- SciCode
- 37%
- Humanity’s Last Exam
- 4%
- GPQA Diamond
- 68%
- CritPt
- 0%
- AA-Omniscience
- 30%
- AA-LCR
- 36%
Similar models
- Mistral Large 2 (Nov '24)MistralQuality Score 22.2Value Score not available
- Mistral Medium 3.1MistralQuality Score 20.5Value Score not available
- Devstral MediumMistralQuality Score 24.0Value Score not available
- Mistral Medium 3MistralQuality Score 24.1Value Score not available
- Mistral Small 4 (Non-reasoning)MistralQuality Score 19.8Value Score 17.7
- Devstral 2MistralQuality Score 20.0Value Score not available