ResearchDatasetsCS-BenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsGeneral and STEM reasoningCS-Bench73.96Pass@120Chart spatial understandingCS-Bench45.3R@0.38Autonomous LLM Fine-tuningCS-Bench85.3Accuracy4