ResearchTasksSemantic Correctness EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedRepoProverNL vs. Lean82Faithfulness2Jun 15, 2026M2FNL vs. Lean73Faithfulness2Jun 15, 2026OpenMathNL vs. Lean54Faithfulness2Jun 15, 2026