ResearchBenchmarksSlide and Talk Delivery Generation on 20 Research Domains Avg (test)Follow86SA ScoreDeepSlide75.678.38183.7Apr 1, 2026Evaluation ResultsMethodMethodLinksSA ScoreSD ScoreDeepSlide2026.048676Manus2026.048273Gamma2026.048072NotebookLM2026.048049PPTAgent2026.047861Coze2026.047748Qwen2026.047661