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. | 109B | 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. | 10M | 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. | $0.08DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.24DeepInfra | — |
| $35.00DeepInfra · fp8 | — | |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 57.2% | 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. | 20% | — |
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. | 32.8% | — |
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 | 74.3% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 90.6% | — |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | 70.7% | — |
MMMU-Pro · standard and vision meanMultimodal reasoning — average across the standard and vision sets | 52.2% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 69.4% | — |
| Overview | ||
| Company | Meta | NVIDIA |
| Release date | Apr 5 2025 | May 20 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
LLaMA 4 ScoutvsClaude Fable 5.2Llama Nemotron Nano 4B v1.1vsClaude Fable 5.2LLaMA 4 ScoutvsGPT-6.2 AstraLlama Nemotron Nano 4B v1.1vsGPT-6.2 AstraLLaMA 4 ScoutvsGemini 4 NeonLlama Nemotron Nano 4B v1.1vsGemini 4 NeonLLaMA 4 ScoutvsGrok 4.7Llama Nemotron Nano 4B v1.1vsGrok 4.7LLaMA 4 ScoutvsDeepSeek-V4.1-Flash-1017Llama Nemotron Nano 4B v1.1vsDeepSeek-V4.1-Flash-1017LLaMA 4 ScoutvsMistral Large 4Llama Nemotron Nano 4B v1.1vsMistral Large 4Frequently asked questions
LLaMA 4 Scout leads Llama Nemotron Nano 4B v1.1 on 1 of the 1 benchmark they both report (GPQA Diamond). LLaMA 4 Scout shipped 45 days before Llama Nemotron Nano 4B v1.1, so benchmark comparisons should account for the intervening progress.
LLaMA 4 Scout has 109B parameters, while Llama Nemotron Nano 4B v1.1 has 4B. Context windows are 10M (LLaMA 4 Scout) vs 128k (Llama Nemotron Nano 4B v1.1).
On GPQA Diamond, LLaMA 4 Scout leads at 57.2% vs Llama Nemotron Nano 4B v1.1 at 55.1%.