ResearchDatasetsCombined BenchmarksFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsGeneral Reasoning and Code GenerationCombined Benchmarks Avg33.75Average Score14Mathematical ReasoningCombined Benchmarks AVG52.03Average Accuracy8