Compare AI models

Specifications
Parameters
109B4B
Context window
10M256k
API pricing
Cheapest input
$0.08DeepInfra—
Cheapest output
$0.24DeepInfra—
$35.00DeepInfra · fp8—
Benchmarks
GPQA Diamond
57.2%53.2%
Overview
CompanyMetaNVIDIA
Release dateApr 5 2025Mar 16 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 4 Scout leads Nemotron 3 Nano 4B on 1 of the 1 benchmark they both report (GPQA Diamond). LLaMA 4 Scout shipped 345 days before Nemotron 3 Nano 4B, so benchmark comparisons should account for the intervening progress.

LLaMA 4 Scout has 109B parameters, while Nemotron 3 Nano 4B has 4B. Context windows are 10M (LLaMA 4 Scout) vs 256k (Nemotron 3 Nano 4B).

On GPQA Diamond, LLaMA 4 Scout leads at 57.2% vs Nemotron 3 Nano 4B at 53.2%.