[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.]

![rohanpaul_ai Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::2588345408.png) Rohan Paul [@rohanpaul_ai](/creator/twitter/rohanpaul_ai) on x 73.7K followers
Created: 2025-07-17 18:29:45 UTC

🖥️ OpenAI rolled out “agent mode,” in ChatGPT.

Lets the model click around a virtual computer, run code, and finish multistep jobs on its own, hitting XXXX% on Humanity’s Last Exam while handling chores like building slide decks or buying groceries. 

It reaches XXXX% accuracy on Humanity’s Last Exam (HLE), while older baselines like OpenAI o3 without tools sit at XXXX% and deep-research with browsing reaches 26.6%.

The HLE exam spans XXXXX expert-level questions across 100+ subjects that were crowdsourced specifically to stump modern language models.

So coubling the previous best pass@1 score signals a jump in broad reasoning skill, not just memorization.

The leap comes from giving the model its own virtual computer with a browser, terminal, and API hooks so it can fetch data, run code, and decide which tool to use on the fly.

OpenAI also says that the agent ran up to X attempts in parallel and picked the answer the model felt most confident about, got the score pushed to XXXX%

So overall, agents that can act as well as reason are starting to close the gap with human experts.

![](https://pbs.twimg.com/media/GwFGRFtXYAASyYk.png)

XXXXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1945913831370453072/c:line.svg)

**Related Topics**
[groceries](/topic/groceries)
[virtual](/topic/virtual)
[open ai](/topic/open-ai)

[Post Link](https://x.com/rohanpaul_ai/status/1945913831370453072)