TUA-Bench
Explore score history ↗Evaluates terminal-use agents on 120 real-world tasks across five families (document editing, email, web info, scientific/engineering workflows) using execution-based scoring.
- Released
- 2026-06-26
- Institutions
- Duke University · Stanford University
- Evaluates
- Code & Software, General AI, cs.SE
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
TUA-Bench paper and code
No reported scores are on record for this benchmark yet.