From 006a70748f626a2dc90f8f2d21664a0e3880fa8d Mon Sep 17 00:00:00 2001 From: liushz Date: Fri, 28 Mar 2025 11:25:52 +0000 Subject: [PATCH] Add olymmath dataset --- opencompass/configs/datasets/OlymMATH/README.md | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/opencompass/configs/datasets/OlymMATH/README.md b/opencompass/configs/datasets/OlymMATH/README.md index 14caadc5..53c9b7a0 100644 --- a/opencompass/configs/datasets/OlymMATH/README.md +++ b/opencompass/configs/datasets/OlymMATH/README.md @@ -1,9 +1,8 @@ # OlymMATH [GitHub Link](https://github.com/RUCAIBox/OlymMATH) -This is a implementation of HLE dataset, which evaluates 2370 text-based questions without images. The default setting is to use LLM as a judge. - -Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models +Dataset OlymMATH, please refer to the paper: +Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models by Haoxiang Sun, Yingqian Min, Zhipeng Chen, Wayne Xin Zhao, Zheng Liu, Zhongyuan Wang, Lei Fang, and Ji-Rong Wen. ## How to eval OlymMATH with model judge