ResearchTasksModel Performance EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedTable 1 Aggregate excluding Human-InternalLMUNIT LLaMA3.1-70B-Decomposed-Weighted79.74Average Score12Mar 5, 2026
Table 1 Aggregate excluding Human-InternalLMUNIT LLaMA3.1-70B-Decomposed-Weighted79.74Average Score12Mar 5, 2026