Lead story
Models & availability
Latest
← Feed
Copy✕ Close copy menu
PaperBench: Evaluating AI’s Ability to Replicate AI Research
OpenAI introduces PaperBench, a benchmark to evaluate AI agents' ability to replicate state-of-the-art AI research.
From the source
We introduce PaperBench, a benchmark evaluating the ability of AI agents to replicate state-of-the-art AI research.
openai.com
Visit source ↗openai.com
- Announced
- 02 Apr 2025 10:15 UTC
- Detected
- 03 Aug 2026 21:11 UTC (+488d after)