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. | 8B/49B | 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 |
| Benchmarks | ||
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 96.6% | 97.4% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 58.4% | 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. | 66.67% | 71.97% |
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% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | — | 87.5% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 79.53% |
| Overview | ||
| Company | NVIDIA | NVIDIA |
| Release date | Mar 18 2025 | Jul 25 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Llama Nemotron (Nano/Super)vsClaude Fable 5.2Llama Nemotron Super 49B v1.5vsClaude Fable 5.2Llama Nemotron (Nano/Super)vsGPT-6.2 AstraLlama Nemotron Super 49B v1.5vsGPT-6.2 AstraLlama Nemotron (Nano/Super)vsGemini 4 NeonLlama Nemotron Super 49B v1.5vsGemini 4 NeonLlama Nemotron (Nano/Super)vsMuse EmberLlama Nemotron Super 49B v1.5vsMuse EmberLlama Nemotron (Nano/Super)vsGrok 4.7Llama Nemotron Super 49B v1.5vsGrok 4.7Llama Nemotron (Nano/Super)vsDeepSeek-V4.1-Flash-1017Llama Nemotron Super 49B v1.5vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Llama Nemotron Super 49B v1.5 leads Llama Nemotron (Nano/Super) on 3 of the 3 benchmarks they both report (MATH-500, AIME 2025, GPQA Diamond). Llama Nemotron (Nano/Super) shipped 129 days before Llama Nemotron Super 49B v1.5, so benchmark comparisons should account for the intervening progress.
Llama Nemotron (Nano/Super) has 8B/49B parameters, while Llama Nemotron Super 49B v1.5 has 49B. Context windows are 128k (Llama Nemotron (Nano/Super)) vs 128k (Llama Nemotron Super 49B v1.5).
On MATH-500, Llama Nemotron Super 49B v1.5 leads at 97.4% vs Llama Nemotron (Nano/Super) at 96.6%. On AIME 2025, Llama Nemotron Super 49B v1.5 leads at 82.71% vs Llama Nemotron (Nano/Super) at 58.4%. On GPQA Diamond, Llama Nemotron Super 49B v1.5 leads at 71.97% vs Llama Nemotron (Nano/Super) at 66.67%.