ResearchBenchmarksStrategic AI Persuasion (Receiver) on MixTalk Small EnvironmentFollow1.54BT Scoregem-3fpr0.01120.40810.8051.2019Feb 1, 2026Evaluation ResultsMethodMethodLinksBT ScoreMean ScoreTOR Scoregem-3fpr2026.021.545225gpt-5m2026.021.465622grok-4.1f2026.021.144830Kimi-k2t2026.020.793642gpt-4.1m2026.020.07-2097