ResearchDatasetsNLP BenchmarkNLP BenchmarkFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsModel Merging7-task NLP benchmark1.18Avg Performance20Natural Language InferenceNLP Benchmark (SNLI, MNLI, SICK, QNLI, RTE, SciTail) Llama-3-8B (val)97.56SNLI Accuracy12Continual Learning8-domain NLP benchmark11.8Vanilla Forgetting5
Natural Language InferenceNLP Benchmark (SNLI, MNLI, SICK, QNLI, RTE, SciTail) Llama-3-8B (val)97.56SNLI Accuracy12