ResearchTasksPhysics-based puzzle solvingPhysics-based puzzle solvingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedINTERPHYRE 1.0 (test)Claude Sonnet100Cliffhanger Score12Jun 30, 2026