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 | 49B |
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 |
| 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. | $0.351Cloudflare | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.555Cloudflare | — |
| $97.95Cloudflare | — | |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 45.96% | 71.97% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 66.76% | 79.53% |
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. | — | 73.58% |
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. | 88.41% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | — | 7.64% |
MATHReasoning — accuracy on the original competition mathematics test set | 69.3% | — |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | — | 97.4% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | — | 87.5% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 82.71% |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | 10.43% | — |
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. | 80.62% | — |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | 68.91% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 49.25% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 64% | — |
| Overview | ||
| Company | Mistral | NVIDIA |
| Release date | Mar 17 2025 | Jul 25 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Mistral Small 3.1vsClaude Fable 5.2Llama Nemotron Super 49B v1.5vsClaude Fable 5.2Mistral Small 3.1vsGPT-6.2 AstraLlama Nemotron Super 49B v1.5vsGPT-6.2 AstraMistral Small 3.1vsGemini 4 NeonLlama Nemotron Super 49B v1.5vsGemini 4 NeonMistral Small 3.1vsMuse EmberLlama Nemotron Super 49B v1.5vsMuse EmberMistral Small 3.1vsGrok 4.7Llama Nemotron Super 49B v1.5vsGrok 4.7Mistral Small 3.1vsDeepSeek-V4.1-Flash-1017Llama Nemotron Super 49B v1.5vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Llama Nemotron Super 49B v1.5 leads Mistral Small 3.1 on 2 of the 2 benchmarks they both report (GPQA Diamond, MMLU-Pro). Mistral Small 3.1 shipped 130 days before Llama Nemotron Super 49B v1.5, so benchmark comparisons should account for the intervening progress.
Mistral Small 3.1 has 24B parameters, while Llama Nemotron Super 49B v1.5 has 49B. Context windows are 128k (Mistral Small 3.1) vs 128k (Llama Nemotron Super 49B v1.5).
On GPQA Diamond, Llama Nemotron Super 49B v1.5 leads at 71.97% vs Mistral Small 3.1 at 45.96%. On MMLU-Pro, Llama Nemotron Super 49B v1.5 leads at 79.53% vs Mistral Small 3.1 at 66.76%.