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 | 14.3B |
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 | 32k |
| These models have no shared benchmark scores. | ||
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% | — |
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. | — | 34.2% |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 7.64% | — |
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% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 79.53% | — |
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. | — | 62.5% |
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. | — | 61.5% |
| Overview | ||
| Company | NVIDIA | Qwen |
| Release date | Jul 25 2025 | Mar 28 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Llama Nemotron Super 49B v1.5vsClaude Fable 5.2Qwen1.5-MoEvsClaude Fable 5.2Llama Nemotron Super 49B v1.5vsGPT-6.2 AstraQwen1.5-MoEvsGPT-6.2 AstraLlama Nemotron Super 49B v1.5vsGemini 4 NeonQwen1.5-MoEvsGemini 4 NeonLlama Nemotron Super 49B v1.5vsMuse EmberQwen1.5-MoEvsMuse EmberLlama Nemotron Super 49B v1.5vsGrok 4.7Qwen1.5-MoEvsGrok 4.7Llama Nemotron Super 49B v1.5vsDeepSeek-V4.1-Flash-1017Qwen1.5-MoEvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Llama Nemotron Super 49B v1.5 and Qwen1.5-MoE don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen1.5-MoE shipped 484 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 Qwen1.5-MoE has 14.3B. Context windows are 128k (Llama Nemotron Super 49B v1.5) vs 32k (Qwen1.5-MoE).
Direct benchmark comparisons are unavailable — Llama Nemotron Super 49B v1.5 and Qwen1.5-MoE don't publish scores on any of the same benchmarks.