PhD student at Vector Institute & University of British Columbia · Research on AI Agents, LLM, RL

ClawBench — Can AI Agents Complete Everyday Online Tasks?

153 tasks · 144 live websites · 8 categories · Best model: 33.3%

Paper · Dashboard · Dataset · PyPI

VidGround — Watch Before You Answer

Visually grounded post-training for video LLMs.

Paper · HF Paper

• 2026.04 — New paper: ClawBench: Can AI Agents Complete Everyday Online Tasks? — 153 real-world tasks, 144 live websites, 7 frontier models. Best model: 33.3%.
  • 
• 2026.04 — New paper: VidGround: Watch Before You Answer — Visually grounded post-training for video LLMs.
  • 

 yuxuan.zhang(at)ubc.ca      Google Scholar      GitHub      Twitter      Website