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. | 1M | 32k |
| Benchmarks | ||
MATHReasoning — accuracy on the original competition mathematics test set | 77.9% | 13.2% |
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. | 30% | — |
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% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 51% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 67.3% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 62.3% | — |
| Overview | ||
| Company | Mistral | |
| Release date | Sep 24 2024 | May 22 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 1.5 Flash-002vsClaude Fable 5.2Mistral 7B v0.3vsClaude Fable 5.2Gemini 1.5 Flash-002vsGPT-6.2 AstraMistral 7B v0.3vsGPT-6.2 AstraGemini 1.5 Flash-002vsMuse EmberMistral 7B v0.3vsMuse EmberGemini 1.5 Flash-002vsGrok 4.7Mistral 7B v0.3vsGrok 4.7Gemini 1.5 Flash-002vsDeepSeek-V4.1-Flash-1017Mistral 7B v0.3vsDeepSeek-V4.1-Flash-1017Gemini 1.5 Flash-002vsKimi K3.1 ProMistral 7B v0.3vsKimi K3.1 ProFrequently asked questions
Gemini 1.5 Flash-002 leads Mistral 7B v0.3 on 1 of the 1 benchmark they both report (MATH). Mistral 7B v0.3 shipped 125 days before Gemini 1.5 Flash-002, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Gemini 1.5 Flash-002) vs 32k (Mistral 7B v0.3). Gemini 1.5 Flash-002 is closed, while Mistral 7B v0.3 is open weight.
On MATH, Gemini 1.5 Flash-002 leads at 77.9% vs Mistral 7B v0.3 at 13.2%.