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 | 4B |
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 | 256k |
| 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. | $0.04DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.064DeepInfra | — |
| $14.00DeepInfra · fp8 | — | |
| These models have no shared benchmark scores. | ||
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. | 84.8% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 82.9% | — |
τ²-bench · retailAgentic tasks — task success in the retail domain of the second-generation customer-service evaluation | — | 39.8% |
τ²-bench · airlineAgentic tasks — task success in the airline domain of the second-generation customer-service evaluation | — | 33.3% |
τ²-bench · telecomAgentic tasks — task success in the telecom domain of the second-generation customer-service evaluation | — | 33% |
MATHReasoning — accuracy on the original competition mathematics test set | 70.6% | — |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | — | 95.4% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 78.5% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 53.2% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 66.3% | — |
| Overview | ||
| Company | Mistral | NVIDIA |
| Release date | Jan 30 2025 | Mar 16 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Mistral Small 3vsClaude Fable 5.2Nemotron 3 Nano 4BvsClaude Fable 5.2Mistral Small 3vsGPT-6.2 AstraNemotron 3 Nano 4BvsGPT-6.2 AstraMistral Small 3vsGemini 4 NeonNemotron 3 Nano 4BvsGemini 4 NeonMistral Small 3vsMuse EmberNemotron 3 Nano 4BvsMuse EmberMistral Small 3vsGrok 4.7Nemotron 3 Nano 4BvsGrok 4.7Mistral Small 3vsDeepSeek-V4.1-Flash-1017Nemotron 3 Nano 4BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Mistral Small 3 and Nemotron 3 Nano 4B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Mistral Small 3 shipped 410 days before Nemotron 3 Nano 4B, so benchmark comparisons should account for the intervening progress.
Mistral Small 3 has 24B parameters, while Nemotron 3 Nano 4B has 4B. Context windows are 32k (Mistral Small 3) vs 256k (Nemotron 3 Nano 4B).
Direct benchmark comparisons are unavailable — Mistral Small 3 and Nemotron 3 Nano 4B don't publish scores on any of the same benchmarks.