SkillsBench

AI benchmark results and model performance

Type: percentageAgents

49.73%

44.30% - 59.20%

44.30% - Muse Glimmer 30B

Scores Over Time

Individual benchmark scores plotted by date.

Models Using This Benchmark

Organisation	Model	Reported	Top Score	Info	Self Reported	Source
Meta	Muse Glimmer 30B	10 Aug 2026	44.30%	With skills; high reasoning	Yes	Source
Qwen	Qwen 3.6 Plus	01 Apr 2026	45.70%	-	Yes	Source
Qwen	Qwen 3.7 Max	21 May 2026	59.20%	Evaluated via OpenCode on 78 tasks; avg of 5 runs	Yes	Source