Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Mike A. Merrill, Alexander G Shaw, Nicholas Carlini, Boxuan Li +81 more
2026arXiv.org638 citations
Semantic Scholar
Researcher profile · Semantic Scholar
Mike A. Merrill, Alexander G Shaw, Nicholas Carlini, Boxuan Li +81 more
Jeseth Delgado Vela, Sarah E. Philo, Joe Brown, M. Taniuchi +17 more
B. Bellekom, C. Troman, Shannon Fitz, J. Akello +2 more