Compare AI models
| Specifications | ||
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 40k | 32k |
| These models have no shared benchmark scores. | ||
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 59.35% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 72.03% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 60.99% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 71.46% | — |
| Overview | ||
| Company | Mistral | Mistral |
| Release date | Jul 24 2025 | Feb 26 2024 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Magistral Medium 1.1vsClaude Fable 5.2Mistral SmallvsClaude Fable 5.2Magistral Medium 1.1vsGPT-6.2 AstraMistral SmallvsGPT-6.2 AstraMagistral Medium 1.1vsGemini 4 HydrogenMistral SmallvsGemini 4 HydrogenMagistral Medium 1.1vsMuse EmberMistral SmallvsMuse EmberMagistral Medium 1.1vsGrok 4.7Mistral SmallvsGrok 4.7Magistral Medium 1.1vsDeepSeek-V4.1-Flash-1017Mistral SmallvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Magistral Medium 1.1 and Mistral Small don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Mistral Small shipped 514 days before Magistral Medium 1.1, so benchmark comparisons should account for the intervening progress.
Context windows are 40k (Magistral Medium 1.1) vs 32k (Mistral Small).
Direct benchmark comparisons are unavailable — Magistral Medium 1.1 and Mistral Small don't publish scores on any of the same benchmarks.