RankingOSWorld partial · 2.0 08.08

OSWorld partial · 2.0 08.08

Data updated 22 Nov 2026

OSWorld partial · 2.0 08.08 is published here as its own result table, version 2.0 08.08. Scores use percent, and higher values rank better. The display harness is Muse Spark1.3 evaluation methodology. Data updated 22 Nov 2026.

Bucket
Agentic
Unit
percent
Direction
Higher is better
Version
2.0 08.08
Display harness
Muse Spark1.3 evaluation methodology
Board
https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology

Compare published benchmark results with category weights →

Models

Published configurations retain their source and harness labels. Missing results remain unknown.

1–4 of 4 entries

ModelScoreHarnessEvidenceSource-recorded date
Claude Opus 5Anthropic68.3%
Reported settings & source

108tasks; common internal GUI framework; execution-based checkers; partial metric; reasoning max

Muse1.2 uses older06.24tasks; all others08.08. Do not compare these versions as identical.

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Muse Spark1.3 evaluation methodologylab self-report2026-09-06
Muse Spark 1.3Meta66.9%
Reported settings & source

108tasks; common internal GUI framework; execution-based checkers; partial metric; reasoning max

Muse1.2 uses older06.24tasks; all others08.08. Do not compare these versions as identical.

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Muse Spark1.3 evaluation methodologylab self-report2026-09-06
GPT-5.6 SolOpenAI62.7%
Reported settings & source

108tasks; common internal GUI framework; execution-based checkers; partial metric; reasoning max

Muse1.2 uses older06.24tasks; all others08.08. Do not compare these versions as identical.

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Muse Spark1.3 evaluation methodologylab self-report2026-09-06
Muse Spark 1.3Meta59%
Reported settings & source

108tasks; common internal GUI framework; execution-based checkers; partial metric; reasoning xhigh

Muse1.2 uses older06.24tasks; all others08.08. Do not compare these versions as identical.

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Muse Spark1.3 evaluation methodologylab self-report2026-09-06