Compare AI models

Specifications
Parameters
5.1B/8B/26B/31B27B
Context window
—256k
API pricing
Cheapest input
$0.04Darkbloom—
Cheapest output
$0.10Modal—
$15.50Darkbloom—
Benchmarks
LiveCodeBench
80%83.9%
Humanity's Last Exam · no tools
19.5%24%
AIME 2026
89.2%94.1%
GPQA Diamond
84.3%87.8%
MMLU-Pro
85.2%86.2%
MMMU-Pro
76.9%75.8%
Overview
CompanyGoogleQwen
Release dateApr 2 2026Apr 22 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.6-27B leads Gemma 4 on 5 of the 6 benchmarks they both report. Gemma 4 shipped 20 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.

Gemma 4 has 5.1B/8B/26B/31B parameters, while Qwen3.6-27B has 27B.

On LiveCodeBench, Qwen3.6-27B leads at 83.9% vs Gemma 4 at 80%. On Humanity's Last Exam · no tools, Qwen3.6-27B leads at 24% vs Gemma 4 at 19.5%. On AIME 2026, Qwen3.6-27B leads at 94.1% vs Gemma 4 at 89.2%. On GPQA Diamond, Qwen3.6-27B leads at 87.8% vs Gemma 4 at 84.3%. On MMLU-Pro, Qwen3.6-27B leads at 86.2% vs Gemma 4 at 85.2%. On MMMU-Pro, Gemma 4 leads at 76.9% vs Qwen3.6-27B at 75.8%.