Compare AI models

Specifications
Parameters
—27B/35B/122B
Context window
—256k
Benchmarks
SWE-Bench Verified
77.4%72%
Humanity's Last Exam · with tools
50.4%47.5%
GPQA Diamond
89.5%86.6%
OSWorld-Verified
53.3%58%
CharXiv Reasoning
88.9%77.2%
MMMU-Pro
80.4%76.9%
Overview
CompanyMetaQwen
Release dateApr 8 2026Feb 24 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Muse Spark leads Qwen3.5 Medium on 5 of the 6 benchmarks they both report. Qwen3.5 Medium shipped 43 days before Muse Spark, so benchmark comparisons should account for the intervening progress.

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

On SWE-Bench Verified, Muse Spark leads at 77.4% vs Qwen3.5 Medium at 72%. On Humanity's Last Exam · with tools, Muse Spark leads at 50.4% vs Qwen3.5 Medium at 47.5%. On GPQA Diamond, Muse Spark leads at 89.5% vs Qwen3.5 Medium at 86.6%. On OSWorld-Verified, Qwen3.5 Medium leads at 58% vs Muse Spark at 53.3%. On CharXiv Reasoning, Muse Spark leads at 88.9% vs Qwen3.5 Medium at 77.2%. On MMMU-Pro, Muse Spark leads at 80.4% vs Qwen3.5 Medium at 76.9%.