OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: He, Chaoqun, Luo, Renjie, Bai, Yuzhuo, Hu, Shengding, Thai, Zhen Leng, Shen, Junhao, Hu, Jinyi, Han, Xu, Huang, Yujie, Zhang, Yuxiang, Liu, Jie, Qi, Lei, Liu, Zhiyuan, Sun, Maosong
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914826447486976
author He, Chaoqun
Luo, Renjie
Bai, Yuzhuo
Hu, Shengding
Thai, Zhen Leng
Shen, Junhao
Hu, Jinyi
Han, Xu
Huang, Yujie
Zhang, Yuxiang
Liu, Jie
Qi, Lei
Liu, Zhiyuan
Sun, Maosong
author_facet He, Chaoqun
Luo, Renjie
Bai, Yuzhuo
Hu, Shengding
Thai, Zhen Leng
Shen, Junhao
Hu, Jinyi
Han, Xu
Huang, Yujie
Zhang, Yuxiang
Liu, Jie
Qi, Lei
Liu, Zhiyuan
Sun, Maosong
contents Recent advancements have seen Large Language Models (LLMs) and Large Multimodal Models (LMMs) surpassing general human capabilities in various tasks, approaching the proficiency level of human experts across multiple domains. With traditional benchmarks becoming less challenging for these models, new rigorous challenges are essential to gauge their advanced abilities. In this work, we present OlympiadBench, an Olympiad-level bilingual multimodal scientific benchmark, featuring 8,476 problems from Olympiad-level mathematics and physics competitions, including the Chinese college entrance exam. Each problem is detailed with expert-level annotations for step-by-step reasoning. Evaluating top-tier models on OlympiadBench, we implement a comprehensive assessment methodology to accurately evaluate model responses. Notably, the best-performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning. Our analysis orienting GPT-4V points out prevalent issues with hallucinations, knowledge omissions, and logical fallacies. We hope that our challenging benchmark can serve as a valuable resource for helping future AGI research endeavors. The data and evaluation code are available at \url{https://github.com/OpenBMB/OlympiadBench}
format Preprint
id arxiv_https___arxiv_org_abs_2402_14008
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
He, Chaoqun
Luo, Renjie
Bai, Yuzhuo
Hu, Shengding
Thai, Zhen Leng
Shen, Junhao
Hu, Jinyi
Han, Xu
Huang, Yujie
Zhang, Yuxiang
Liu, Jie
Qi, Lei
Liu, Zhiyuan
Sun, Maosong
Computation and Language
Recent advancements have seen Large Language Models (LLMs) and Large Multimodal Models (LMMs) surpassing general human capabilities in various tasks, approaching the proficiency level of human experts across multiple domains. With traditional benchmarks becoming less challenging for these models, new rigorous challenges are essential to gauge their advanced abilities. In this work, we present OlympiadBench, an Olympiad-level bilingual multimodal scientific benchmark, featuring 8,476 problems from Olympiad-level mathematics and physics competitions, including the Chinese college entrance exam. Each problem is detailed with expert-level annotations for step-by-step reasoning. Evaluating top-tier models on OlympiadBench, we implement a comprehensive assessment methodology to accurately evaluate model responses. Notably, the best-performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning. Our analysis orienting GPT-4V points out prevalent issues with hallucinations, knowledge omissions, and logical fallacies. We hope that our challenging benchmark can serve as a valuable resource for helping future AGI research endeavors. The data and evaluation code are available at \url{https://github.com/OpenBMB/OlympiadBench}
title OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
topic Computation and Language
url https://arxiv.org/abs/2402.14008