ONEBench to test them all: Sample-level benchmarking over open-ended capabilities
A Ghosh and S Dziadzio and A Prabhu and V Udandarao and S Albanie and M Bethge, arXiv preprint arXiv:2412.06745, 2024
@article{Ghosh2024onebench, author = "Ghosh, A and Dziadzio, S and Prabhu, A and Udandarao, V and Albanie, S and Bethge, M", title = "ONEBench to test them all: Sample-level benchmarking over open-ended capabilities", year = "2024", month = "December", journal = "arXiv preprint arXiv:2412.06745" }