Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 1.8B/3.25B | — |
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. | 32k | 40k |
| 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% |
MATHReasoning — accuracy on the original competition mathematics test set | 22.8% | — |
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% |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 55.8% | — |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | 30.6% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 32.6% | — |
| Overview | ||
| Company | Mistral | |
| Release date | Dec 6 2023 | Jul 24 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Gemini 1.0 NanovsClaude Fable 5.2Magistral Medium 1.1vsClaude Fable 5.2Gemini 1.0 NanovsGPT-6.2 AstraMagistral Medium 1.1vsGPT-6.2 AstraGemini 1.0 NanovsMuse EmberMagistral Medium 1.1vsMuse EmberGemini 1.0 NanovsGrok 4.7Magistral Medium 1.1vsGrok 4.7Gemini 1.0 NanovsDeepSeek-V4.1-Flash-1017Magistral Medium 1.1vsDeepSeek-V4.1-Flash-1017Gemini 1.0 NanovsKimi K3.1 ProMagistral Medium 1.1vsKimi K3.1 ProFrequently asked questions
Gemini 1.0 Nano and Magistral Medium 1.1 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Gemini 1.0 Nano shipped 596 days before Magistral Medium 1.1, so benchmark comparisons should account for the intervening progress.
Context windows are 32k (Gemini 1.0 Nano) vs 40k (Magistral Medium 1.1).
Direct benchmark comparisons are unavailable — Gemini 1.0 Nano and Magistral Medium 1.1 don't publish scores on any of the same benchmarks.