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. | 1B/3B/11B/90B | 24B |
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. | 128k | 40k |
| 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. | $0.027Cloudflare | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.201Cloudflare | — |
| $15.45Cloudflare | — | |
| 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. | — | 59.17% |
MATHReasoning — accuracy on the original competition mathematics test set | 68% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | — | 70.52% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 62.03% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 65.78% |
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. | 86% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 86.9% | — |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | 57.3% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 60.3% | — |
| Overview | ||
| Company | Meta | Mistral |
| Release date | Sep 25 2024 | Jul 24 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
LLaMA 3.2vsClaude Fable 5.2Magistral Small 1.1vsClaude Fable 5.2LLaMA 3.2vsGPT-6.2 AstraMagistral Small 1.1vsGPT-6.2 AstraLLaMA 3.2vsGemini 4 HydrogenMagistral Small 1.1vsGemini 4 HydrogenLLaMA 3.2vsGrok 4.7Magistral Small 1.1vsGrok 4.7LLaMA 3.2vsDeepSeek-V4.1-Flash-1017Magistral Small 1.1vsDeepSeek-V4.1-Flash-1017LLaMA 3.2vsKimi K3.1 ProMagistral Small 1.1vsKimi K3.1 ProFrequently asked questions
LLaMA 3.2 and Magistral Small 1.1 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. LLaMA 3.2 shipped 302 days before Magistral Small 1.1, so benchmark comparisons should account for the intervening progress.
LLaMA 3.2 has 1B/3B/11B/90B parameters, while Magistral Small 1.1 has 24B. Context windows are 128k (LLaMA 3.2) vs 40k (Magistral Small 1.1).
Direct benchmark comparisons are unavailable — LLaMA 3.2 and Magistral Small 1.1 don't publish scores on any of the same benchmarks.