PaperBench

PaperBench: Evaluating AI's Ability to Replicate AI Research Paper: arXiv:2504.01848GitHub: openai/preparedness 📋 Dataset Description PaperBench is a benchmark dataset for evaluating the ability of AI agents to replicate state-of-the-art AI research from scratch. The dataset contains 20 ICML 2024 Spotlight and Oral pa

Papers using PaperBench (1)

Multi-agent Collaboration with State Management2026