notesum.ai

Published at December 9

ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities

cs.LG
cs.CL
cs.CV

Released Date: December 9, 2024

Authors: Adhiraj Ghosh1, Sebastian Dziadzio, Ameya Prabhu, Vishaal Udandarao, Samuel Albanie, Matthias Bethge

Aff.: 1Tübingen AI Center, University of Tübingen

Arxiv: http://arxiv.org/pdf/2412.06745v1