ResearchTasksAmbiguous Question AnsweringFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAmbigQA (test)HERA (Qwen-3-14B)54.43Accuracy13Apr 2, 2026Museum Artifact Dataset Amb. 1.0 (test)Qwen3-VL-8B (Direct)65Answer Accuracy4Jul 8, 2026