CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
Open paper
Benchmark
Model
Rank
Results
computer-use-agents-on-webarena
CUA-GYM-A17B
#3
Success Rate: 56.0
computer-use-agents-on-osworld-verified
CUA-GYM-A17B
#8
Success Rate: 72.6
Rank counts only results with a code link.