Re:Sam Altman's response to Molotov cocktail incident
by ctolsen on Saturday April 11, 2026 @02:21AM
(#47727971)
I mean, I could say the same about Gemini. 3.1 Pro tops a bunch of benchmarks out there but any practical use I've put it to it's underperforming both other proprietary and open weight models. Benchmarks are suspicious in general.
Gets 5% on ARC-AGI2 private set.
Chinese models are suspiciously good a benchmarks.