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 | 80B |
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 | 256k |
| 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. | — | $0.072DeepInfra |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.88DeepInfra |
| — | $73.00DeepInfra · fp8 | |
| Benchmarks | ||
IFEvalAgentic tasks — following verifiable instructions in generated responses | 75.5% | 87.6% |
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% | 72.9% |
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. | — | 56.6% |
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% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 80.6% |
| Overview | ||
| Company | NVIDIA | Qwen |
| Release date | May 20 2025 | Sep 11 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Llama Nemotron Nano 4B v1.1vsClaude Fable 5.2Qwen3-NextvsClaude Fable 5.2Llama Nemotron Nano 4B v1.1vsGPT-6.2 AstraQwen3-NextvsGPT-6.2 AstraLlama Nemotron Nano 4B v1.1vsGemini 4 NeonQwen3-NextvsGemini 4 NeonLlama Nemotron Nano 4B v1.1vsMuse EmberQwen3-NextvsMuse EmberLlama Nemotron Nano 4B v1.1vsGrok 4.7Qwen3-NextvsGrok 4.7Llama Nemotron Nano 4B v1.1vsDeepSeek-V4.1-Flash-1017Qwen3-NextvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen3-Next leads Llama Nemotron Nano 4B v1.1 on 2 of the 2 benchmarks they both report (IFEval, GPQA Diamond). Llama Nemotron Nano 4B v1.1 shipped 114 days before Qwen3-Next, so benchmark comparisons should account for the intervening progress.
Llama Nemotron Nano 4B v1.1 has 4B parameters, while Qwen3-Next has 80B. Context windows are 128k (Llama Nemotron Nano 4B v1.1) vs 256k (Qwen3-Next).
On IFEval, Qwen3-Next leads at 87.6% vs Llama Nemotron Nano 4B v1.1 at 75.5%. On GPQA Diamond, Qwen3-Next leads at 72.9% vs Llama Nemotron Nano 4B v1.1 at 55.1%.