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 |
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. | 1M | 128k |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 51.5% | 55.1% |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 12.5% | — |
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. | 28.9% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 75.5% |
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% |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | 21.7% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 71.6% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 68% | — |
| Overview | ||
| Company | NVIDIA | |
| Release date | Feb 5 2025 | May 20 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 2.0 Flash-LitevsClaude Fable 5.2Llama Nemotron Nano 4B v1.1vsClaude Fable 5.2Gemini 2.0 Flash-LitevsGPT-6.2 AstraLlama Nemotron Nano 4B v1.1vsGPT-6.2 AstraGemini 2.0 Flash-LitevsMuse EmberLlama Nemotron Nano 4B v1.1vsMuse EmberGemini 2.0 Flash-LitevsGrok 4.7Llama Nemotron Nano 4B v1.1vsGrok 4.7Gemini 2.0 Flash-LitevsDeepSeek-V4.1-Flash-1017Llama Nemotron Nano 4B v1.1vsDeepSeek-V4.1-Flash-1017Gemini 2.0 Flash-LitevsMistral Large 4Llama Nemotron Nano 4B v1.1vsMistral Large 4Frequently asked questions
Llama Nemotron Nano 4B v1.1 leads Gemini 2.0 Flash-Lite on 1 of the 1 benchmark they both report (GPQA Diamond). Gemini 2.0 Flash-Lite shipped 104 days before Llama Nemotron Nano 4B v1.1, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Gemini 2.0 Flash-Lite) vs 128k (Llama Nemotron Nano 4B v1.1). Gemini 2.0 Flash-Lite is closed, while Llama Nemotron Nano 4B v1.1 is open weight.
On GPQA Diamond, Llama Nemotron Nano 4B v1.1 leads at 55.1% vs Gemini 2.0 Flash-Lite at 51.5%.