ResearchTasksWorkflow ExecutionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedT3 Payment8 models (Gemma4:e4b/26b/31b, GPT-OSS:20b/120b, MSmall3.2:24b, GPT-5.2)100TSR11May 8, 20267,680 workflows Financial synthetic benchmarkInKH81.5Quality6Jun 2, 2026