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. | 49B | 32B |
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 | ||
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% | 63.4% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 97.4% | 98% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 87.5% | 79.5% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 82.71% | 69.5% |
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% | 65.6% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 83.9% |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 7.64% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 79.53% | — |
| Overview | ||
| Company | NVIDIA | Qwen |
| Release date | Jul 25 2025 | Mar 6 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Llama Nemotron Super 49B v1.5vsClaude Fable 5.2QwQ-32BvsClaude Fable 5.2Llama Nemotron Super 49B v1.5vsGPT-6.2 AstraQwQ-32BvsGPT-6.2 AstraLlama Nemotron Super 49B v1.5vsGemini 4 NeonQwQ-32BvsGemini 4 NeonLlama Nemotron Super 49B v1.5vsMuse EmberQwQ-32BvsMuse EmberLlama Nemotron Super 49B v1.5vsGrok 4.7QwQ-32BvsGrok 4.7Llama Nemotron Super 49B v1.5vsDeepSeek-V4.1-Flash-1017QwQ-32BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Llama Nemotron Super 49B v1.5 leads QwQ-32B on 4 of the 5 benchmarks they both report. QwQ-32B shipped 141 days before Llama Nemotron Super 49B v1.5, so benchmark comparisons should account for the intervening progress.
Llama Nemotron Super 49B v1.5 has 49B parameters, while QwQ-32B has 32B. Context windows are 128k (Llama Nemotron Super 49B v1.5) vs 128k (QwQ-32B).
On LiveCodeBench, Llama Nemotron Super 49B v1.5 leads at 73.58% vs QwQ-32B at 63.4%. On MATH-500, QwQ-32B leads at 98% vs Llama Nemotron Super 49B v1.5 at 97.4%. On AIME 2024, Llama Nemotron Super 49B v1.5 leads at 87.5% vs QwQ-32B at 79.5%. On AIME 2025, Llama Nemotron Super 49B v1.5 leads at 82.71% vs QwQ-32B at 69.5%. On GPQA Diamond, Llama Nemotron Super 49B v1.5 leads at 71.97% vs QwQ-32B at 65.6%.