X · @teortaxesTex
· X / Twitter
Grok 4.5 does as well as DeepSeek-V4-Pro WeirdML is hard, requires respect of constraints, and it seems you need to specifically train for something l…
Grok 4.5 does as well as DeepSeek-V4-ProWeirdML is hard, requires respect of constraints, and it seems you need to specifically train for something like itHåvard Ihle: Grok 4.5 (high) scores 46.4% on WeirdML, down from 49.9% for Grok 4.3. It seems generally smarter than earlier grok models, but it's problem is that it'