Compare AI models

Specifications
Parameters
—0.8B/2B/4B/9B
Context window
—256k
Benchmarks
GPQA Diamond
89.5%81.7%
OSWorld-Verified
53.3%41.8%
CharXiv Reasoning
88.9%73%
MMMU-Pro
80.4%70.1%
Overview
CompanyMetaQwen
Release dateApr 8 2026Mar 2 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Muse Spark leads Qwen3.5 Small on 4 of the 4 benchmarks they both report (GPQA Diamond, OSWorld-Verified, CharXiv Reasoning, MMMU-Pro). Qwen3.5 Small shipped 37 days before Muse Spark, so benchmark comparisons should account for the intervening progress.

Muse Spark is closed, while Qwen3.5 Small is open weight.

On GPQA Diamond, Muse Spark leads at 89.5% vs Qwen3.5 Small at 81.7%. On OSWorld-Verified, Muse Spark leads at 53.3% vs Qwen3.5 Small at 41.8%. On CharXiv Reasoning, Muse Spark leads at 88.9% vs Qwen3.5 Small at 73%. On MMMU-Pro, Muse Spark leads at 80.4% vs Qwen3.5 Small at 70.1%.