TheoremQA Benchmark

What is TheoremQA?

TheoremQA is the first theorem-driven question-answering dataset designed to evaluate AI models’ capabilities to apply theorems to solve challenging science…

Released

2023-12-06

Evaluates

推理, Reasoning, 大语言模型, LLM, 数理能力, Math, 逻辑推理, 开源收录, Open-Source, 不支持, Unsupported

Openness

open

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/TheoremQA

TheoremQA paper, code and dataset

• Paper https://arxiv.org/pdf/2305.12524
• Code https://github.com/TIGER-AI-Lab/TheoremQA
• Dataset https://huggingface.co/datasets/TIGER-Lab/TheoremQA

Which sources cite TheoremQA?

• TheoremQA

Related 推理, Reasoning, 大语言模型, LLM, 数理能力, Math, 逻辑推理, 开源收录, Open-Source, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• ActiveFly-Bench
• Ada-LEval
• AdvancedMathBench
• AECBench