ResearchTasksProcedural reasoningProcedural reasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedRecipeQAGPT-4o46.6BertScore10May 15, 2026ProcedureVQAGPT-4o61.4BertScore10May 15, 2026Procedural-skill v1.0 (test)pre-SFT Haiku-4-595.5Performance Score (BL)7May 13, 2026