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. | 4B | 0.5B/1.5B/3B/7B/14B/32B/72B |
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 |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $0.288DeepInfra |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.32DeepInfra |
| — | $92.00DeepInfra · fp8 | |
| Benchmarks | ||
IFEvalAgentic tasks — following verifiable instructions in generated responses | 75.5% | 84.1% |
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. | — | 55.5% |
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% |
MATHReasoning — accuracy on the original competition mathematics test set | — | 83.1% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 96.2% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 46.3% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 55.1% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 71.1% |
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. | — | 95.8% |
| Overview | ||
| Company | NVIDIA | Qwen |
| Release date | May 20 2025 | Sep 19 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Llama Nemotron Nano 4B v1.1vsClaude Fable 5.2Qwen2.5vsClaude Fable 5.2Llama Nemotron Nano 4B v1.1vsGPT-6.2 AstraQwen2.5vsGPT-6.2 AstraLlama Nemotron Nano 4B v1.1vsGemini 4 NeonQwen2.5vsGemini 4 NeonLlama Nemotron Nano 4B v1.1vsMuse EmberQwen2.5vsMuse EmberLlama Nemotron Nano 4B v1.1vsGrok 4.7Qwen2.5vsGrok 4.7Llama Nemotron Nano 4B v1.1vsDeepSeek-V4.1-Flash-1017Qwen2.5vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen2.5 leads Llama Nemotron Nano 4B v1.1 on 1 of the 1 benchmark they both report (IFEval). Qwen2.5 shipped 243 days before Llama Nemotron Nano 4B v1.1, so benchmark comparisons should account for the intervening progress.
Llama Nemotron Nano 4B v1.1 has 4B parameters, while Qwen2.5 has 0.5B/1.5B/3B/7B/14B/32B/72B. Context windows are 128k (Llama Nemotron Nano 4B v1.1) vs 128k (Qwen2.5).
On IFEval, Qwen2.5 leads at 84.1% vs Llama Nemotron Nano 4B v1.1 at 75.5%.