Terminal-Bench
Year: 2026
Type: software
Abstract: A benchmark for AI agents in terminal environments.
Authors: Marten, Ryan, Shaw, Alex, Bercovich, Ivan, Droste, Benedikt, Cerruti, Tommaso, Dillmann, Steven, Wang, Ruiyang, Wahdany, Dariush, Hart, Allen, Krauth, Karl, ScaleAI, Snorkel AI, Turing, gNucleus AI, Boolean AI, Carlini, Nicholas, Lyu, Shengrui, Wei, Anjiang, Khatua, Arpandeep, Plüster, Björn, Dwivedi, Chaitanya, Sutcliffe, Christine, Yuming, Tivris, David, Wang, Di, Goh, Hui Wen, Xing, Hanwen, Lin, Haowei, Salia, Irakli, Seol, Jaejung, Bao, Jiajun, Ouyang, Jialin, Park, Junha, Walsh, Liam, Kong, Luyang, Ivanov, Maksim, Ubl, Malte, Liamets, Mikhail, Menis, Orfeas, Migdal, Piotr, Bao, Qingquan, Movva, Raj, Ben Chaim, Roey, Srinath, Namburi, Bogdanik, Sergey, Yadav, Shubham, Benjamin, Stephen, Kung, Tony, Hughes, Walker, Lan, Xin, Gupta, Himanshu, Mishra, Swaroop, Wang, Chenguang, He, Hao, Tu, Jianhong, Montgomery, Kyle, Tu, Zengji, Naik, Atharva, Mortensen, David, Zhang, Ivan, Mathur, Yash, Liu, Emmy, Singh, Karanpartap, Yu, Michael, Feng, Steven, Gangal, Varun, Tao, Zhuofu, Ruan, Sherry, Mueller, Jonas, Cabezas, Joan, Bauer, Justin, Li, Kevin Xiang, Zhang, Robert, Feller, Aaron, Madayan, Alec, Chen, Leon, Feuer, Ben, Li, Xiangyi, Li, Boxuan, Raj, Harsh, Galler, Samuel, Shi, Lin, Segal, Ivgeni, Buchanan, Kelly, P., Shreyas, Desai, Rishi, Schneider, Aaron, Settles, Chris, Lin, Xiangning, Nezhurina, Marianna, Wang, Andrew, Kowalczyk, Michał, Zhao, Jin-Xiang, Satia, Sanyam, Hu, Jessie, Atef, Sherif, Chen, Kobe, Vance, Sam, Segato, Gian, Jitsev, Jenia, Dimakis, Alex, Merrill, Mike, Konwinski, Andy, Schmidt, Ludwig
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7204277217