ResearchTasksAggregate performance evaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAggregate 10-Benchmark SuiteFineRouter79.9Average Score29Apr 14, 2026Overall Performance across 12 DatasetsDeep Lasso1.42Rank29Feb 26, 2026MMLU, GSM, HellaSwag, TruthfulQA, ARC-C, CodeXMADS8B5.32Improvement18Jun 1, 2026Average SST2, AGNEWS, GSM8KSFT26.47HS Score11Mar 4, 2026