Compare AI models

Specifications
Parameters
5.1B/8B/26B/31B16B
Context window
—8k
API pricing
Cheapest input
$0.04Darkbloom—
Cheapest output
$0.10Modal—
$15.50Darkbloom—
Benchmarks
LiveCodeBench
80%14.3%
GPQA Diamond
84.3%35.2%
MMLU-Pro
85.2%42.4%
Overview
CompanyGoogleMoonshot AI
Release dateApr 2 2026Feb 22 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemma 4 leads Moonlight on 3 of the 3 benchmarks they both report (LiveCodeBench, GPQA Diamond, MMLU-Pro). Moonlight shipped 404 days before Gemma 4, so benchmark comparisons should account for the intervening progress.

Gemma 4 has 5.1B/8B/26B/31B parameters, while Moonlight has 16B.

On LiveCodeBench, Gemma 4 leads at 80% vs Moonlight at 14.3%. On GPQA Diamond, Gemma 4 leads at 84.3% vs Moonlight at 35.2%. On MMLU-Pro, Gemma 4 leads at 85.2% vs Moonlight at 42.4%.