ResearchDatasetsTRBenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMultimodal Tool-use ReasoningTRBench Total83.21Accuracy7Multimodal Tool-use ReasoningTRBench Mathematics93.55Alg. Accuracy7Multimodal Tool-use ReasoningTRBench General sub-dataset46Cultural Understanding Score7Multimodal Tool-use ReasoningTRBench Science88Accuracy (Biology)7