Benchmark
CUA-World
A benchmark environment for evaluating the performance of computer-use agents (CUAs), with emphasis on long-horizon tasks and real-time interactive scenarios.
Timeline (last 90 days)
Nov 5
VTR requires only 2000 training steps to achieve performance comparable to full-resolution models on OSWorld, CUA-World and video game action prediction tasks, while using 2.5 to 5.8 times fewer visual tokens.
Unverified50%