[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![OpenAI Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::4398626122.png) OpenAI [@OpenAI](/creator/twitter/OpenAI) on x 4.2M followers
Created: 2025-04-02 17:13:21 UTC

We’re releasing PaperBench, a benchmark evaluating the ability of AI agents to replicate state-of-the-art AI research, as part of our Preparedness Framework.

Agents must replicate top ICML 2024 papers, including understanding the paper, writing code, and executing experiments.

![](https://pbs.twimg.com/media/Gni4aIbakAAXHTd.jpg)

XXXXXXXXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1907481490457506235/c:line.svg)

**Related Topics**
[coins ai agents](/topic/coins-ai-agents)
[coins ai](/topic/coins-ai)
[open ai](/topic/open-ai)

[Post Link](https://x.com/OpenAI/status/1907481490457506235)