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 | — |
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 | 1M |
| 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% | 37.8% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 79.53% | 64.5% |
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. | — | 86.6% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 76.3% |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 7.64% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 81.1% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 97.4% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 87.5% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 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. | 71.97% | — |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | — | 93.8% |
| Overview | ||
| Company | NVIDIA | Qwen |
| Release date | Jul 25 2025 | Nov 15 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Llama Nemotron Super 49B v1.5vsClaude Fable 5.2Qwen2.5-Turbo (1M)vsClaude Fable 5.2Llama Nemotron Super 49B v1.5vsGPT-6.2 AstraQwen2.5-Turbo (1M)vsGPT-6.2 AstraLlama Nemotron Super 49B v1.5vsGemini 4 NeonQwen2.5-Turbo (1M)vsGemini 4 NeonLlama Nemotron Super 49B v1.5vsMuse EmberQwen2.5-Turbo (1M)vsMuse EmberLlama Nemotron Super 49B v1.5vsGrok 4.7Qwen2.5-Turbo (1M)vsGrok 4.7Llama Nemotron Super 49B v1.5vsDeepSeek-V4.1-Flash-1017Qwen2.5-Turbo (1M)vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Llama Nemotron Super 49B v1.5 leads Qwen2.5-Turbo (1M) on 2 of the 2 benchmarks they both report (LiveCodeBench, MMLU-Pro). Qwen2.5-Turbo (1M) shipped 252 days before Llama Nemotron Super 49B v1.5, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Llama Nemotron Super 49B v1.5) vs 1M (Qwen2.5-Turbo (1M)). Llama Nemotron Super 49B v1.5 is open weight, while Qwen2.5-Turbo (1M) is closed.
On LiveCodeBench, Llama Nemotron Super 49B v1.5 leads at 73.58% vs Qwen2.5-Turbo (1M) at 37.8%. On MMLU-Pro, Llama Nemotron Super 49B v1.5 leads at 79.53% vs Qwen2.5-Turbo (1M) at 64.5%.