ResearchTasksPhysics Problem SolvingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedScibench fundPoT + REFTOOL74.6Accuracy24Mar 4, 2026UGPhysicsGPT-567.6Accuracy12May 29, 2026PHYSICS (held-out)EXPERT20.8DBS9Feb 26, 2026Interphyre Two Body Problem level 1.0 (test)Qwen-2.5-7B HEXA34Accuracy4Jun 30, 2026Interphyre Down to Earth level 1.0 (test)Qwen-2.5-7B HEXA72Accuracy4Jun 30, 2026Interphyre Catapult level 1.0 (test)GPT-OSS-120B HEXA54Accuracy2Jun 30, 2026