ResearchTasksGeneral Domain ReasoningGeneral Domain ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedSuperGPQA, MMLU-Pro, BBEHR-Diverse40.75Overall Avg Score28Feb 26, 2026HalluBenchPAPO-7B71Accuracy13Jun 16, 2026General Domain Reasoning benchmarks ARC-c, MMLU-ProTRAPO83.7ARC-c12Feb 26, 2026GPQARFT40.4Accuracy11May 18, 2026