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 | 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. | 32k | 128k |
| These models have no shared benchmark scores. | ||
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% |
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 | 56.6% | — |
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% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 71.97% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 79.53% |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | 77.1% | — |
| Overview | ||
| Company | Mistral | NVIDIA |
| Release date | Jul 16 2024 | Jul 25 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Mathstral 7BvsClaude Fable 5.2Llama Nemotron Super 49B v1.5vsClaude Fable 5.2Mathstral 7BvsGPT-6.2 AstraLlama Nemotron Super 49B v1.5vsGPT-6.2 AstraMathstral 7BvsGemini 4 NeonLlama Nemotron Super 49B v1.5vsGemini 4 NeonMathstral 7BvsMuse EmberLlama Nemotron Super 49B v1.5vsMuse EmberMathstral 7BvsGrok 4.7Llama Nemotron Super 49B v1.5vsGrok 4.7Mathstral 7BvsDeepSeek-V4.1-Flash-1017Llama Nemotron Super 49B v1.5vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Mathstral 7B and Llama Nemotron Super 49B v1.5 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Mathstral 7B shipped 374 days before Llama Nemotron Super 49B v1.5, so benchmark comparisons should account for the intervening progress.
Mathstral 7B has 7B parameters, while Llama Nemotron Super 49B v1.5 has 49B. Context windows are 32k (Mathstral 7B) vs 128k (Llama Nemotron Super 49B v1.5).
Direct benchmark comparisons are unavailable — Mathstral 7B and Llama Nemotron Super 49B v1.5 don't publish scores on any of the same benchmarks.