ResearchDatasetsZeroBenchZeroBenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMultimodal reasoningZeroBench26.35Accuracy22Multimodal reasoningZeroBench sub47.6Pass@118Image ReasoningZeroBench sub24.4Accuracy14Multimodal reasoningZeroBench main11Pass@113MathZeroBench17.66Score8General Reasoning & UnderstandingZeroBench18.9Accuracy8Visual PuzzlesZeroBench main12Pass@17