Compare AI models

Specifications
Parameters
1B/4B/12B/27B8B
Context window
—8k
API pricing
Cheapest input
$0.04DeepInfra—
Cheapest output
$0.05Parasail—
$10.50Parasail · bf16—
Benchmarks
HumanEval
87.8%36.22%
MMLU
76.9%69.51%
GSM8K
95.9%58.45%
Overview
CompanyGoogleNVIDIA
Release dateMar 12 2025Aug 21 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemma 3 leads Mistral NeMo Minitron 8B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Mistral NeMo Minitron 8B shipped 203 days before Gemma 3, so benchmark comparisons should account for the intervening progress.

Gemma 3 has 1B/4B/12B/27B parameters, while Mistral NeMo Minitron 8B has 8B.

On HumanEval, Gemma 3 leads at 87.8% vs Mistral NeMo Minitron 8B at 36.22%. On MMLU, Gemma 3 leads at 76.9% vs Mistral NeMo Minitron 8B at 69.51%. On GSM8K, Gemma 3 leads at 95.9% vs Mistral NeMo Minitron 8B at 58.45%.