跳到正文
OpenAI News·· 2025-04-02

PaperBench: Evaluating AI’s Ability to Replicate AI Research

PaperBench: Evaluating AI’s Ability to Replicate AI Research

AI 导读

【RSS 原文 · 未经 AI 筛选或翻译】We introduce PaperBench, a benchmark evaluating the ability of AI agents to replicate state-of-the-art AI research.

来源:OpenAI News · openai.com