§ feed · storyline
PaperBench: Evaluating AI’s Ability to Replicate AI Research
OpenAI releases PaperBench, a benchmark designed to evaluate how well AI agents can replicate state-of-the-art AI research papers.
We introduce PaperBench, a benchmark evaluating the ability of AI agents to replicate state-of-the-art AI research.
§ sources1 publication · timeline below