ResearchDatasetsOverall Evaluation SuiteOverall Evaluation SuiteFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsGeneral Benchmark AggregationOverall Evaluation Suite59.8Math Average21Aggregated Programming Capability EvaluationOverall Evaluation Suite64.2Macro Average Score10General Language ModelingOverall Evaluation Suite73.6Average Score4