PaperBench

What is PaperBench?

PaperBench is a benchmark evaluating the ability of AI agents to replicate state-of-the-art AI research. Benchmark Radar tracks PaperBench, cited by 1 source…

Released

2025-04-07

Evaluates

理解, Understanding, 智能体, Agent, 任务执行, Task Execution, 语言理解, Comprehension, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

PaperBench paper and code

• Paper https://arxiv.org/abs/2504.01848
• Code https://github.com/openai/preparedness

Which sources cite PaperBench?

• PaperBench

Related 理解, Understanding, 智能体, Agent, 任务执行, Task Execution, 语言理解, Comprehension, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• Ada-LEval
• AECBench
• AFQMC
• AgentBoard