ResearchTasksReasoning and Code GenerationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedReasoning Evaluation Suite (GSM8K, MATH500, AIME24, HumanEval) (test)SafeChain94.7GSM8K Accuracy36Apr 23, 2026Reasoning and Code Generation Suite (MATH, GSM8K, MBPP, TheoremQA, BBH) (test)FlexSwitch54.38MATH Accuracy6May 1, 2026
Reasoning Evaluation Suite (GSM8K, MATH500, AIME24, HumanEval) (test)SafeChain94.7GSM8K Accuracy36Apr 23, 2026
Reasoning and Code Generation Suite (MATH, GSM8K, MBPP, TheoremQA, BBH) (test)FlexSwitch54.38MATH Accuracy6May 1, 2026