ResearchDatasetsDownstream Reasoning BenchmarksDownstream Reasoning BenchmarksFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsReasoningDownstream Reasoning Benchmarks (MATH, GSM8K, AQUA, AIME, AMC, MMLU, GPQA)82.15Average Accuracy18
ReasoningDownstream Reasoning Benchmarks (MATH, GSM8K, AQUA, AIME, AMC, MMLU, GPQA)82.15Average Accuracy18