Compare AI models

Specifications
Parameters
1B/4B/12B/27B1.5B/4B
Context window
—8k
API pricing
Cheapest input
$0.04DeepInfra—
Cheapest output
$0.08DeepInfra—
$15.00DeepInfra · bf16—
Benchmarks
MMLU
76.9%54.84%
GSM8K
95.9%54.89%
Overview
CompanyGoogleZ.ai
Release dateMar 12 2025Nov 29 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemma 3 leads GLM-Edge on 2 of the 2 benchmarks they both report (MMLU, GSM8K). GLM-Edge shipped 103 days before Gemma 3, so benchmark comparisons should account for the intervening progress.

Gemma 3 has 1B/4B/12B/27B parameters, while GLM-Edge has 1.5B/4B.

On MMLU, Gemma 3 leads at 76.9% vs GLM-Edge at 54.84%. On GSM8K, Gemma 3 leads at 95.9% vs GLM-Edge at 54.89%.