ResearchBenchmarksStrategic AI Persuasion (Sender) on MixTalk Large EnvironmentFollow1.68BT Scoregrok-4.1f0.39040.72521.061.3948Feb 1, 2026Evaluation ResultsMethodMethodLinksBT ScoreMean ScoreTOR Scoregrok-4.1f2026.021.68540.07Kimi-k2t2026.021.35520.12gpt-5m2026.020.89500.11gem-3fpr2026.020.63470.13gpt-4.1m2026.020.44450.16