ResearchTasksMulti-task Surgical Reasoning and RecognitionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSurgCoTBench (test)SurgRAW-Qwen3VL-8B64.03Overall Score12Feb 26, 2026