Compare AI models

Specifications
Parameters
1B/4B/12B/27B9B
Context window
—128k
API pricing
Cheapest input
$0.04DeepInfra—
Cheapest output
$0.08DeepInfra—
$15.00DeepInfra · bf16—
Benchmarks
LiveCodeBench
29.7%28.5%
HumanEval
87.8%82.3%
Overview
CompanyGoogleZ.ai
Release dateMar 12 2025Jul 5 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemma 3 leads CodeGeeX4-ALL-9B on 2 of the 2 benchmarks they both report (LiveCodeBench, HumanEval). CodeGeeX4-ALL-9B shipped 250 days before Gemma 3, so benchmark comparisons should account for the intervening progress.

Gemma 3 has 1B/4B/12B/27B parameters, while CodeGeeX4-ALL-9B has 9B.

On LiveCodeBench, Gemma 3 leads at 29.7% vs CodeGeeX4-ALL-9B at 28.5%. On HumanEval, Gemma 3 leads at 87.8% vs CodeGeeX4-ALL-9B at 82.3%.