ResearchBenchmarksHint/Question Generation on PeanoBench 21 incorrect proofsFollow3.7AccuracyLeanTutor3.0763.2383.43.562Jun 10, 2025Jul 18, 2025Aug 25, 2025Oct 2, 2025Nov 9, 2025Dec 17, 2025Jan 24, 2026Evaluation ResultsMethodMethodLinksAccuracyRelevanceReadabilityAnswer LeakageLeanTutorFeedback Type=Hint/Que...Feedback Type=Hint/Question2026.013.73.74.74.4LeanTutorFeedback Type=Hint/Que...Feedback Type=Hint/Question2025.063.73.74.74.4BaselineFeedback Type=Hint/Que...Feedback Type=Hint/Question2026.013.12.94.74.3BaselineFeedback Type=Hint/Que...Feedback Type=Hint/Question2025.063.12.94.74.3