Compare AI models

Specifications
Parameters
—>1T
Context window
—256k
Benchmarks
SWE-Bench Verified
77.4%75.3%
Humanity's Last Exam · with tools
50.4%49.8%
GPQA Diamond
89.5%87.4%
Overview
CompanyMetaQwen
Release dateApr 8 2026Jan 26 2026
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Muse Spark leads Qwen3-Max-Thinking on 3 of the 3 benchmarks they both report (SWE-Bench Verified, Humanity's Last Exam, GPQA Diamond). Qwen3-Max-Thinking shipped 72 days before Muse Spark, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On SWE-Bench Verified, Muse Spark leads at 77.4% vs Qwen3-Max-Thinking at 75.3%. On Humanity's Last Exam · with tools, Muse Spark leads at 50.4% vs Qwen3-Max-Thinking at 49.8%. On GPQA Diamond, Muse Spark leads at 89.5% vs Qwen3-Max-Thinking at 87.4%.