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. | 22B | — |
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 | 200k |
| These models have no shared benchmark scores. | ||
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | — | 49.3% |
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. | — | 97.6% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | — | 97.9% |
DROPReasoning — three-shot token F1 on questions requiring reasoning over paragraphs | — | 80.6 |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 77.2% |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | — | 13.8% |
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. | — | 86.9% |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | — | 92% |
| Overview | ||
| Company | Mistral | OpenAI |
| Release date | Sep 17 2024 | Jan 31 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Mistral Small 2vsClaude Fable 5.2o3-mini-highvsClaude Fable 5.2Mistral Small 2vsGemini 4 Hydrogeno3-mini-highvsGemini 4 HydrogenMistral Small 2vsMuse Embero3-mini-highvsMuse EmberMistral Small 2vsGrok 4.7o3-mini-highvsGrok 4.7Mistral Small 2vsDeepSeek-V4.1-Flash-1017o3-mini-highvsDeepSeek-V4.1-Flash-1017Mistral Small 2vsKimi K3.1 Proo3-mini-highvsKimi K3.1 ProFrequently asked questions
Mistral Small 2 and o3-mini-high don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Mistral Small 2 shipped 136 days before o3-mini-high, so benchmark comparisons should account for the intervening progress.
Context windows are 32k (Mistral Small 2) vs 200k (o3-mini-high). Mistral Small 2 is open weight, while o3-mini-high is closed.
Direct benchmark comparisons are unavailable — Mistral Small 2 and o3-mini-high don't publish scores on any of the same benchmarks.