PaperBench: Evaluating AI’s Ability to Replicate AI Research
- ID
- 531
- Status
- new
- Published
- 02 Apr 2025, 6:15 PM
- Fetched
- 27 Jun 2026, 7:47 PM
- Provider
- OpenAI News
- Category
- ai-labs
- Original URL
- https://openai.com/index/paperbench
- Source URL
- https://openai.com/news/rss.xml
Excerpt
We introduce PaperBench, a benchmark evaluating the ability of AI agents to replicate state-of-the-art AI research.
Summary
No summary yet. It will appear after the daemon summarizes this item.