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. | 7B | — |
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 |
| Benchmarks | ||
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. | 38.4% | 99.3% |
MATHReasoning — accuracy on the original competition mathematics test set | 13.2% | — |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | — | 98.2% |
DROPReasoning — three-shot token F1 on questions requiring reasoning over paragraphs | — | 78.1 |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 81.3% |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | — | 19.3% |
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. | — | 90.3% |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | — | 93.5% |
| Overview | ||
| Company | Mistral | OpenAI |
| Release date | May 22 2024 | Apr 16 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Mistral 7B v0.3vsClaude Fable 5.2o4-mini-highvsClaude Fable 5.2Mistral 7B v0.3vsGemini 4 Hydrogeno4-mini-highvsGemini 4 HydrogenMistral 7B v0.3vsMuse Embero4-mini-highvsMuse EmberMistral 7B v0.3vsGrok 4.7o4-mini-highvsGrok 4.7Mistral 7B v0.3vsDeepSeek-V4.1-Flash-1017o4-mini-highvsDeepSeek-V4.1-Flash-1017Mistral 7B v0.3vsKimi K3.1 Proo4-mini-highvsKimi K3.1 ProFrequently asked questions
o4-mini-high leads Mistral 7B v0.3 on 1 of the 1 benchmark they both report (HumanEval). Mistral 7B v0.3 shipped 329 days before o4-mini-high, so benchmark comparisons should account for the intervening progress.
Context windows are 32k (Mistral 7B v0.3) vs 200k (o4-mini-high). Mistral 7B v0.3 is open weight, while o4-mini-high is closed.
On HumanEval, o4-mini-high leads at 99.3% vs Mistral 7B v0.3 at 38.4%.