ResearchBenchmarksStructured video reasoning on Keys and Doors Hard IDFollow99Exact Match RateTBS-2046.27259.96173.6587.339Jun 11, 2026Evaluation ResultsMethodMethodLinksExact Match RateTBS-20Budget=20Budget=202026.0699BoN-20Budget=20Budget=202026.0697.7TBS-10Budget=10Budget=102026.0697BoN-10Budget=10Budget=102026.0696.7BoN-5Budget=5Budget=52026.0690BoN-1Budget=1Budget=12026.0648.3