ResearchBenchmarksSlide and Talk Delivery Generation on 20 Research Domains 04. NLP (test)Follow0.93SA ScoreDeepSlide0.75320.79910.8450.8909Apr 1, 2026Evaluation ResultsMethodMethodLinksSA ScoreSD ScoreDeepSlide2026.040.930.74Manus2026.040.820.71Coze2026.040.810.49Gamma2026.040.810.74PPTAgent2026.040.80.7NotebookLM2026.040.80.49Qwen2026.040.760.59