Compare AI models

Specifications
Parameters
1B/4B/12B/27B7B
Context window
—32k
API pricing
Cheapest input
$0.04DeepInfra—
Cheapest output
$0.08DeepInfra—
$15.00DeepInfra · bf16—
Benchmarks
HumanEval
87.8%38.4%
MATH
89%13.2%
Overview
CompanyGoogleMistral
Release dateMar 12 2025May 22 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemma 3 leads Mistral 7B v0.3 on 2 of the 2 benchmarks they both report (HumanEval, MATH). Mistral 7B v0.3 shipped 294 days before Gemma 3, so benchmark comparisons should account for the intervening progress.

Gemma 3 has 1B/4B/12B/27B parameters, while Mistral 7B v0.3 has 7B.

On HumanEval, Gemma 3 leads at 87.8% vs Mistral 7B v0.3 at 38.4%. On MATH, Gemma 3 leads at 89% vs Mistral 7B v0.3 at 13.2%.