This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
José A. Alonso
jalonso.bsky.social
did:plc:nogtf77xcyjilq52agusqrjx
UGMathBench: A diverse and dynamic benchmark for undergraduate-level mathematical reasoning with large language models. ~ Xin Xu et als. arxiv.org/abs/2501.13766 #LLMs #Math
https://arxiv.org/abs/2501.13766
2025-02-26T11:05:39.158Z