Compare AI models

Specifications
Parameters
—27B
Context window
—256k
Benchmarks
SWE-Bench Verified
77.4%77.2%
GPQA Diamond
89.5%87.8%
CharXiv Reasoning
88.9%78.4%
MMMU-Pro
80.4%75.8%
Overview
CompanyMetaQwen
Release dateApr 8 2026Apr 22 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Muse Spark leads Qwen3.6-27B on 4 of the 4 benchmarks they both report (SWE-Bench Verified, GPQA Diamond, CharXiv Reasoning, MMMU-Pro). Muse Spark shipped 14 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.

Muse Spark is closed, while Qwen3.6-27B is open weight.

On SWE-Bench Verified, Muse Spark leads at 77.4% vs Qwen3.6-27B at 77.2%. On GPQA Diamond, Muse Spark leads at 89.5% vs Qwen3.6-27B at 87.8%. On CharXiv Reasoning, Muse Spark leads at 88.9% vs Qwen3.6-27B at 78.4%. On MMMU-Pro, Muse Spark leads at 80.4% vs Qwen3.6-27B at 75.8%.