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. | 62.1% | 55.1% |
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 15% | — |
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. | 21.4% | — |
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. | 35.1% | — |
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% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 76.4% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 70.7% | — |
| Overview | ||
| Company | NVIDIA | |
| Release date | Dec 11 2024 | May 20 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 2.0 FlashvsClaude Fable 5.2Llama Nemotron Nano 4B v1.1vsClaude Fable 5.2Gemini 2.0 FlashvsGPT-6.2 AstraLlama Nemotron Nano 4B v1.1vsGPT-6.2 AstraGemini 2.0 FlashvsMuse EmberLlama Nemotron Nano 4B v1.1vsMuse EmberGemini 2.0 FlashvsGrok 4.7Llama Nemotron Nano 4B v1.1vsGrok 4.7Gemini 2.0 FlashvsDeepSeek-V4.1-Flash-1017Llama Nemotron Nano 4B v1.1vsDeepSeek-V4.1-Flash-1017Gemini 2.0 FlashvsMistral Large 4Llama Nemotron Nano 4B v1.1vsMistral Large 4Frequently asked questions
Gemini 2.0 Flash leads Llama Nemotron Nano 4B v1.1 on 1 of the 1 benchmark they both report (GPQA Diamond). Gemini 2.0 Flash shipped 160 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) vs 128k (Llama Nemotron Nano 4B v1.1). Gemini 2.0 Flash is closed, while Llama Nemotron Nano 4B v1.1 is open weight.
On GPQA Diamond, Gemini 2.0 Flash leads at 62.1% vs Llama Nemotron Nano 4B v1.1 at 55.1%.