ResearchBenchmarksStructured video reasoning on Sliding Puzzle HardFollow88.7Exact Match RateTBS-2039.40452.2026577.798Jun 11, 2026Evaluation ResultsMethodMethodLinksExact Match RateTBS-20Budget=20Budget=202026.0688.7TBS-10Budget=10Budget=102026.0681.3BoN-20Budget=20Budget=202026.0681.3BoN-10Budget=10Budget=102026.0674BoN-5Budget=5Budget=52026.0665.7BoN-1Budget=1Budget=12026.0641.3