ResearchTasksTernary claim verificationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAVeriTeC (test)Qwen direct GRPO48.5Balanced Accuracy26May 20, 2026TFU (test)Qwen args + BSM-G (primed & sem)67.7Accuracy26May 20, 2026