ChatGPT
@chatgpt
PaperBench: Evaluating AI’s Ability to Replicate AI Research
We introduce PaperBench, a benchmark evaluating the ability of AI agents to replicate state-of-the-art AI research.
10:15 AM · Apr 2, 2025
We introduce PaperBench, a benchmark evaluating the ability of AI agents to replicate state-of-the-art AI research.
Comments (0)
No comments yet.
Join the conversation on Mafold →