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. | 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 | — |
| 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. | $0.06DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.16DeepInfra | — |
| $25.00DeepInfra · fp8 | — | |
| Benchmarks | ||
MATHReasoning — accuracy on the original competition mathematics test set | 69.42% | 73% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 69.06% | 72% |
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. | 80.5% | 86.2% |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | 67.09% | 68.1% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 62.5% | 63.2% |
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. | — | 85.7% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 46.13% | — |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | 12.1% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 49.1% | — |
| Overview | ||
| Company | Mistral | SpaceXSI |
| Release date | Jun 20 2025 | Aug 13 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Mistral Small 3.2vsClaude Fable 5.2Grok‑2 minivsClaude Fable 5.2Mistral Small 3.2vsGPT-6.2 AstraGrok‑2 minivsGPT-6.2 AstraMistral Small 3.2vsGemini 4 HydrogenGrok‑2 minivsGemini 4 HydrogenMistral Small 3.2vsMuse EmberGrok‑2 minivsMuse EmberMistral Small 3.2vsDeepSeek-V4.1-Flash-1017Grok‑2 minivsDeepSeek-V4.1-Flash-1017Mistral Small 3.2vsKimi K3.1 ProGrok‑2 minivsKimi K3.1 ProFrequently asked questions
Grok‑2 mini leads Mistral Small 3.2 on 5 of the 5 benchmarks they both report. Grok‑2 mini shipped 311 days before Mistral Small 3.2, so benchmark comparisons should account for the intervening progress.
Mistral Small 3.2 is open weight, while Grok‑2 mini is closed.
On MATH, Grok‑2 mini leads at 73% vs Mistral Small 3.2 at 69.42%. On MMLU-Pro, Grok‑2 mini leads at 72% vs Mistral Small 3.2 at 69.06%. On MMLU, Grok‑2 mini leads at 86.2% vs Mistral Small 3.2 at 80.5%. On MathVista, Grok‑2 mini leads at 68.1% vs Mistral Small 3.2 at 67.09%. On MMMU, Grok‑2 mini leads at 63.2% vs Mistral Small 3.2 at 62.5%.