[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.]

![scaling01 Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::1825243643529027584.png) Lisan al Gaib [@scaling01](/creator/twitter/scaling01) on x 16K followers
Created: 2025-07-10 04:59:00 UTC

ARC-AGI-2 score is extremely impressive and math scores look also very promising. Good job xAI!

However, we haven't seen anything on coding, long-context or instruction-following.

Looks to be a math-benchmaxxed model. But the math-benchmaxxing might enhance general reasoning capabilities as evident by ARC-AGI-2 scores.


XXXXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1943173082996261292/c:line.svg)

**Related Topics**
[capabilities](/topic/capabilities)
[xai](/topic/xai)
[gaib](/topic/gaib)

[Post Link](https://x.com/scaling01/status/1943173082996261292)