ResearchDatasetsExeVR-BenchExeVR-BenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsReward ModelingExeVR-Bench Overall84.7Accuracy11Reward ModelingExeVR-Bench Android83.5Accuracy11Reward ModelingExeVR-Bench Mac/Win90Accuracy11Reward ModelingExeVR-Bench Ubuntu Human84Accuracy11Reward ModelingExeVR-Bench Ubuntu Agent85.1Accuracy11