Jinyi Hu, Maosong Sun, Zhiyuan Liu, Xu Han, Jie Liu, Yuzhuo Bai, Yuxiang Zhang, Shengding Hu, Chaoqun He, Renjie Luo, Zhen Thai, Junhao Shen, and 2 more
We lifted 6 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| OpenBMB/OlympiadBench | canonical | 5 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| extract_answer | Ran | OpenBMB/OlympiadBench/inference/judge.py code served (permissive licence) · get_code("5328984c0ec57f93") |
| get_answer_type_text | Ran | OpenBMB/OlympiadBench/inference/code/evaluators/evaluator.py code served (permissive licence) · get_code("974ffb3038c7a520") |
| get_single_answer_type_text | Ran | OpenBMB/OlympiadBench/inference/code/evaluators/evaluator.py code served (permissive licence) · get_code("492ce033452181fb") |
| judge_answer | Ran | OpenBMB/OlympiadBench/inference/code/evaluators/text_only_gpt_4.py code served (permissive licence) · get_code("f76fefaa9a78d45f") |
| make_input | Ran | OpenBMB/OlympiadBench/inference/code/evaluators/text_only_gpt_4.py code served (permissive licence) · get_code("ed614f73c91d4dfd") |
| call_openai | Not yet run | OpenBMB/OlympiadBench/inference/code/evaluators/text_only_gpt_4.py code served (permissive licence) · get_code("04240f6bffe2447e") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 https: //github.com/OpenBMB/OlympiadBench
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.14008")
get_code_for_paper("2402.14008")
have("2402.14008")
Connect an agent — have() is free.