ResearchTasksAggregate EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAggregated Benchmarks GSM8K MBPP HumanEval ARC-E ARC-CFull61.16Average Score26Jun 11, 2026Multi-domain Aggregate SuiteBase57.1General Average7May 7, 2026DCLM CORE (val)Bank of Values (BoV)27.2CORE5Jun 4, 2026