ResearchTasksCommon Sense Reasoning and Question AnsweringFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedReasoning Benchmarks Zero-shot (PIQA, ARC, HellaSwag, WinoGrande)FlatQuant82.75PIQA Accuracy31Mar 27, 2026Task Suite Zero-shot (ARC-e, ARC-c, HellaSwag, OBQA, WinoGrande, MathQA, PIQA)Dense83.54ARC-e17Feb 26, 2026
Reasoning Benchmarks Zero-shot (PIQA, ARC, HellaSwag, WinoGrande)FlatQuant82.75PIQA Accuracy31Mar 27, 2026
Task Suite Zero-shot (ARC-e, ARC-c, HellaSwag, OBQA, WinoGrande, MathQA, PIQA)Dense83.54ARC-e17Feb 26, 2026