ResearchDatasetsClaude9Claude9FollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsHigh-stakes specialized classificationClaude9 (test)50.31Macro F137Text ClassificationClaude9 (test)57.5Macro-F114High-stakes specialized classificationClaude9 (val)44.09Macro F14