T
TBPN @tbpn
Tuesday, November 18, 2025 import
Tweet
Gemini 3 blew past every other model on ARC-AGI-2. But how does it perform on the Shrimp Fried Rice benchmark? We put it to the test today: https://t.co/aPMjaVh4Oo
Gemini 3 blew past every other model on ARC-AGI-2. But how does it perform on the Shrimp Fried Rice benchmark? We put it to the test today: https://t.co/aPMjaVh4Oo