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. | — | 9B |
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 | 128k |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 65.7% | 64% |
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 5% |
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. | — | 71.1% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | 40.8% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 76.8% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 43.8% | — |
| Overview | ||
| Company | Mistral | NVIDIA |
| Release date | Aug 12 2025 | Aug 18 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Mistral Medium 3.1vsClaude Fable 5.2Nemotron Nano 2vsClaude Fable 5.2Mistral Medium 3.1vsGPT-6.2 AstraNemotron Nano 2vsGPT-6.2 AstraMistral Medium 3.1vsGemini 4 HydrogenNemotron Nano 2vsGemini 4 HydrogenMistral Medium 3.1vsMuse EmberNemotron Nano 2vsMuse EmberMistral Medium 3.1vsGrok 4.7Nemotron Nano 2vsGrok 4.7Mistral Medium 3.1vsDeepSeek-V4.1-Flash-1017Nemotron Nano 2vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Mistral Medium 3.1 leads Nemotron Nano 2 on 1 of the 1 benchmark they both report (GPQA Diamond). Mistral Medium 3.1 shipped 6 days before Nemotron Nano 2, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Mistral Medium 3.1) vs 128k (Nemotron Nano 2). Mistral Medium 3.1 is closed, while Nemotron Nano 2 is open weight.
On GPQA Diamond, Mistral Medium 3.1 leads at 65.7% vs Nemotron Nano 2 at 64%.