ResearchTasksZero-shot Question Answering and ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAccuracy Tasks Zero-shot (AC, AE, WI, QA)FP1662AC Score52Feb 26, 2026LM-Eval-Harness Suite (PIQA, HellaSwag, LAMBADA, ARC-e, ARC-c, SciQ, Race, MMLU) zero-shotLlama3 8B80.7PIQA32Feb 26, 2026Evaluation Suite Zero-shot (ARC, LogiQA, Wino, CSQA, BoolQ, PIQA, MMLU)Avg-DeUS83.88ARC21Feb 26, 2026Downstream Suite Zero-shot (PIQA, HS, ARC, WG, RTE, OQA, BoolQ)Meta-Llama-3-8B Dense80.79PIQA Accuracy12Mar 4, 2026
LM-Eval-Harness Suite (PIQA, HellaSwag, LAMBADA, ARC-e, ARC-c, SciQ, Race, MMLU) zero-shotLlama3 8B80.7PIQA32Feb 26, 2026
Evaluation Suite Zero-shot (ARC, LogiQA, Wino, CSQA, BoolQ, PIQA, MMLU)Avg-DeUS83.88ARC21Feb 26, 2026
Downstream Suite Zero-shot (PIQA, HS, ARC, WG, RTE, OQA, BoolQ)Meta-Llama-3-8B Dense80.79PIQA Accuracy12Mar 4, 2026