Compare AI models

Specifications
Parameters
1B/4B/12B/27B51B
Context window
—128k
API pricing
Cheapest input
$0.04DeepInfra—
Cheapest output
$0.05Parasail—
$10.50Parasail · bf16—
Benchmarks
MMLU
76.9%80.2%
GSM8K
95.9%91.43%
Overview
CompanyGoogleNVIDIA
Release dateMar 12 2025Sep 23 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemma 3 and Llama 3.1 Nemotron 51B are evenly matched across the 2 benchmarks they both report (MMLU, GSM8K). Llama 3.1 Nemotron 51B shipped 170 days before Gemma 3, so benchmark comparisons should account for the intervening progress.

Gemma 3 has 1B/4B/12B/27B parameters, while Llama 3.1 Nemotron 51B has 51B.

On MMLU, Llama 3.1 Nemotron 51B leads at 80.2% vs Gemma 3 at 76.9%. On GSM8K, Gemma 3 leads at 95.9% vs Llama 3.1 Nemotron 51B at 91.43%.