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. | 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. | 256k | 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. | 53.2% | 42.5% |
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. | — | 83.7% |
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 | — | 64.3% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 95.4% | — |
DROPReasoning — three-shot token F1 on questions requiring reasoning over paragraphs | — | 83.2 |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 78.5% | — |
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. | — | 84.7% |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | — | 87.1% |
| Overview | ||
| Company | NVIDIA | OpenAI |
| Release date | Mar 16 2026 | Nov 6 2023 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Nemotron 3 Nano 4BvsClaude Fable 5.2GPT-4 TurbovsClaude Fable 5.2Nemotron 3 Nano 4BvsGemini 4 NeonGPT-4 TurbovsGemini 4 NeonNemotron 3 Nano 4BvsMuse EmberGPT-4 TurbovsMuse EmberNemotron 3 Nano 4BvsGrok 4.7GPT-4 TurbovsGrok 4.7Nemotron 3 Nano 4BvsDeepSeek-V4.1-Flash-1017GPT-4 TurbovsDeepSeek-V4.1-Flash-1017Nemotron 3 Nano 4BvsMistral Large 4GPT-4 TurbovsMistral Large 4Frequently asked questions
Nemotron 3 Nano 4B leads GPT-4 Turbo on 1 of the 1 benchmark they both report (GPQA Diamond). GPT-4 Turbo shipped 861 days before Nemotron 3 Nano 4B, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Nemotron 3 Nano 4B) vs 128k (GPT-4 Turbo). Nemotron 3 Nano 4B is open weight, while GPT-4 Turbo is closed.
On GPQA Diamond, Nemotron 3 Nano 4B leads at 53.2% vs GPT-4 Turbo at 42.5%.