Compare AI models

Specifications
Parameters
5.1B/8B/26B/31B>1T
Context window
—256k
API pricing
Cheapest input
$0.04Darkbloom—
Cheapest output
$0.10Modal—
$15.50Darkbloom—
Benchmarks
LiveCodeBench
80%85.9%
Humanity's Last Exam · with tools
26.5%49.8%
GPQA Diamond
84.3%87.4%
MMLU-Pro
85.2%85.7%
Overview
CompanyGoogleQwen
Release dateApr 2 2026Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen3-Max-Thinking leads Gemma 4 on 4 of the 4 benchmarks they both report (LiveCodeBench, Humanity's Last Exam, GPQA Diamond, MMLU-Pro). Qwen3-Max-Thinking shipped 66 days before Gemma 4, so benchmark comparisons should account for the intervening progress.

Gemma 4 has 5.1B/8B/26B/31B parameters, while Qwen3-Max-Thinking has >1T. Gemma 4 is open weight, while Qwen3-Max-Thinking is closed.

On LiveCodeBench, Qwen3-Max-Thinking leads at 85.9% vs Gemma 4 at 80%. On Humanity's Last Exam · with tools, Qwen3-Max-Thinking leads at 49.8% vs Gemma 4 at 26.5%. On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs Gemma 4 at 84.3%. On MMLU-Pro, Qwen3-Max-Thinking leads at 85.7% vs Gemma 4 at 85.2%.