ResearchDatasetsGRS BenchmarkGRS BenchmarkFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsGrounding Representational SimilarityGRS Benchmark 4 Numerical stress test0.2Kendall's tau4Grounding Representational SimilarityGRS Benchmark Antonym stress test 40.41Kendall's tau ($ au$)4