ResearchTasksMultiple Choice Question Answering and ReasoningMultiple Choice Question Answering and ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedShort Context Benchmarks MMLU, SciQ, OQA, CQA, SIQA, PIQA, HellaSwag, WinoGrande, ARC-c, ARC-eQwen2.5-7B74.25MMLU Accuracy10May 26, 2026EleutherAI lm-eval-harness ARC-C, ARC-E, HellaSwag, PIQA, WinoGrande standard (test val)Q-MQA22.7ARC-Challenge Accuracy6Jun 4, 2026
Short Context Benchmarks MMLU, SciQ, OQA, CQA, SIQA, PIQA, HellaSwag, WinoGrande, ARC-c, ARC-eQwen2.5-7B74.25MMLU Accuracy10May 26, 2026
EleutherAI lm-eval-harness ARC-C, ARC-E, HellaSwag, PIQA, WinoGrande standard (test val)Q-MQA22.7ARC-Challenge Accuracy6Jun 4, 2026