Tagged: post-training

3 articles

Latest

Z.ai's GLM-5.3 jumps from 4.6 to 28.3 on Terminal-Bench without a new base model

Grok 4.6 lands in Cursor with 500K context and a $6 output price

Hugging Face trains a 2.2B model to see GUIs, hitting 65% on ScreenSpot