ResearchDatasetsMINT-BenchMINT-BenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsTool-augmented reasoningMINT-Bench9.85Success Rate (Turn 1)5multi-turn interaction-based problem solvingMINT-Bench 1.0 (test)11.76Code Generation Score5