ResearchTasksArtifact ExplanationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedArtiBench (test)Qwen2.5-VL-7B + ArtiAgent23.3ROUGE8Feb 26, 2026SynthScars (test)LEGION24.7ROUGE Score8Feb 26, 2026LOKI (test)Qwen2.5-VL-7B + ArtiAgent0.169ROUGE8Feb 26, 2026