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 | 128k |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $0.40Mistral |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $2.00Mistral |
| — | $180Mistral · zdr | |
| Benchmarks | ||
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% | 30.3% |
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% | 57.1% |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | — | 92.1% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 89.4% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | — | 91% |
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% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 77.2% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 66.1% |
| Overview | ||
| Company | Mistral | Mistral |
| Release date | Jul 24 2025 | May 7 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Magistral Medium 1.1vsClaude Fable 5.2Mistral Medium 3vsClaude Fable 5.2Magistral Medium 1.1vsGPT-6.2 AstraMistral Medium 3vsGPT-6.2 AstraMagistral Medium 1.1vsGemini 4 HydrogenMistral Medium 3vsGemini 4 HydrogenMagistral Medium 1.1vsMuse EmberMistral Medium 3vsMuse EmberMagistral Medium 1.1vsGrok 4.7Mistral Medium 3vsGrok 4.7Magistral Medium 1.1vsDeepSeek-V4.1-Flash-1017Mistral Medium 3vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Magistral Medium 1.1 leads Mistral Medium 3 on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Mistral Medium 3 shipped 78 days before Magistral Medium 1.1, so benchmark comparisons should account for the intervening progress.
Context windows are 40k (Magistral Medium 1.1) vs 128k (Mistral Medium 3).
On LiveCodeBench, Magistral Medium 1.1 leads at 59.35% vs Mistral Medium 3 at 30.3%. On GPQA Diamond, Magistral Medium 1.1 leads at 71.46% vs Mistral Medium 3 at 57.1%.