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. | 253B | 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. | 128k | 256k |
| Benchmarks | ||
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 97% | 95.4% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 72.5% | 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. | 76.01% | 53.2% |
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. | 66.31% | — |
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% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 80.8% | — |
| Overview | ||
| Company | NVIDIA | NVIDIA |
| Release date | Apr 7 2025 | Mar 16 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Llama Nemotron Ultra 253BvsClaude Fable 5.2Nemotron 3 Nano 4BvsClaude Fable 5.2Llama Nemotron Ultra 253BvsGPT-6.2 AstraNemotron 3 Nano 4BvsGPT-6.2 AstraLlama Nemotron Ultra 253BvsGemini 4 NeonNemotron 3 Nano 4BvsGemini 4 NeonLlama Nemotron Ultra 253BvsMuse EmberNemotron 3 Nano 4BvsMuse EmberLlama Nemotron Ultra 253BvsGrok 4.7Nemotron 3 Nano 4BvsGrok 4.7Llama Nemotron Ultra 253BvsDeepSeek-V4.1-Flash-1017Nemotron 3 Nano 4BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Llama Nemotron Ultra 253B leads Nemotron 3 Nano 4B on 2 of the 3 benchmarks they both report (MATH-500, AIME 2025, GPQA Diamond). Llama Nemotron Ultra 253B shipped 343 days before Nemotron 3 Nano 4B, so benchmark comparisons should account for the intervening progress.
Llama Nemotron Ultra 253B has 253B parameters, while Nemotron 3 Nano 4B has 4B. Context windows are 128k (Llama Nemotron Ultra 253B) vs 256k (Nemotron 3 Nano 4B).
On MATH-500, Llama Nemotron Ultra 253B leads at 97% vs Nemotron 3 Nano 4B at 95.4%. On AIME 2025, Nemotron 3 Nano 4B leads at 78.5% vs Llama Nemotron Ultra 253B at 72.5%. On GPQA Diamond, Llama Nemotron Ultra 253B leads at 76.01% vs Nemotron 3 Nano 4B at 53.2%.