logoalt Hacker News

thomasahle • today at 9:49 PM • 1 reply • view on HN

• 98.6% on ARC-AGI-3

• 97.6% on frontier math

• 95.9% on CAD

• 100% on ExploitBench

Nothing modest about it

Replies

nater5000 • today at 10:27 PM

Except the release announcement. You know, the thing the OP you're responding to is specifically pointing out?

➕ show 1 reply