OS-Copilot/OSReward download history
OS-Copilot/OSReward is a visual question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 812 times (262 in the last 7 days), and 2,656 times in total. It ranks #22,612 among datasets by monthly downloads.
OSReward Benchmark OSReward evaluates whether a multimodal judge can determine if a computer-use agent completed a user's task. This release contains binary outcome labels only: SUCCESS and FAIL. The benchmark has two evaluation configurations: Configuration Trajectories Unique