Compare AI models

Specifications
Parameters
1B/4B/12B/27B—
Context window
—128k
API pricing
Cheapest input
$0.04DeepInfra—
Cheapest output
$0.08DeepInfra—
$15.00DeepInfra · bf16—
Benchmarks
HumanEval
87.8%75.7%
IFEval
90.4%75.2%
MATH
89%57.9%
MMLU
76.9%81.9%
GSM8K
95.9%90.9%
Overview
CompanyGoogleZ.ai
Release dateMar 12 2025Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Gemma 3 leads GLM-4-Air on 4 of the 5 benchmarks they both report. GLM-4-Air shipped 280 days before Gemma 3, so benchmark comparisons should account for the intervening progress.

Gemma 3 is open weight, while GLM-4-Air is closed.

On HumanEval, Gemma 3 leads at 87.8% vs GLM-4-Air at 75.7%. On IFEval, Gemma 3 leads at 90.4% vs GLM-4-Air at 75.2%. On MATH, Gemma 3 leads at 89% vs GLM-4-Air at 57.9%. On MMLU, GLM-4-Air leads at 81.9% vs Gemma 3 at 76.9%. On GSM8K, Gemma 3 leads at 95.9% vs GLM-4-Air at 90.9%.