Skillsbench
SkillsBench is an evaluation framework that measures how skills work, and the first dataset that measures how powerful models are at using skills on expert-curated tasks across high-GDP-value, diverse domains.
- Domain
- rl-env
- License
- unknown
- Published
- Feb 2026
- Canonical
- openreward.ai/benchflow/skillsbench
Cite
Notes
Only stored in your browser.
Top score 45.3 by Claude Opus 4.5 - 2 models reporting (2 frontier)
Score history
2Top models
2
FAQ
- What is Skillsbench?
- SkillsBench is an evaluation framework that measures how skills work, and the first dataset that measures how powerful models are at using skills on expert-curated tasks across high-GDP-value, diverse domains.
- What is the current top score on Skillsbench?
- The top reported score is 45.3 by Claude Opus 4.5, across 2 models reporting (2 from frontier labs).
- What license is Skillsbench under?
- Skillsbench is available under unknown.