arXiv AI
Sep 1

Terminal-Bench-LILT: Multilingual Agentic Coding Benchmark Grounded in Language, Region, and Culture

arXiv:2608.28641v1 Announce Type: cross Abstract: Most evaluations for coding agents are conducted exclusively in English, which does not reflect real-world multilingual deployment. We present Termin...

By Yunsu Kim, Kaden Uhlig, Ashwin Purohit, Milind Agarwal, Patrick Simianer, Anil Arslan, Kiarash Mokhtari, Thomas Zenkel, Johannes Mosig, Gabriel Bretschner, Shamik Bose, Joern Wuebker, John DeNero