Compare AI models

Specifications
Parameters
1B/4B/12B/27B6B
Context window
—8k
API pricing
Cheapest input
$0.04DeepInfra—
Cheapest output
$0.08DeepInfra—
$15.00DeepInfra · bf16—
Benchmarks
HumanEval
87.8%58.5%
MATH
89%25.7%
MMLU
76.9%61.4%
GSM8K
95.9%72.3%
Overview
CompanyGoogleZ.ai
Release dateMar 12 2025Oct 27 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemma 3 leads ChatGLM3-6B on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). ChatGLM3-6B shipped 502 days before Gemma 3, so benchmark comparisons should account for the intervening progress.

Gemma 3 has 1B/4B/12B/27B parameters, while ChatGLM3-6B has 6B.

On HumanEval, Gemma 3 leads at 87.8% vs ChatGLM3-6B at 58.5%. On MATH, Gemma 3 leads at 89% vs ChatGLM3-6B at 25.7%. On MMLU, Gemma 3 leads at 76.9% vs ChatGLM3-6B at 61.4%. On GSM8K, Gemma 3 leads at 95.9% vs ChatGLM3-6B at 72.3%.