List your company

Theory of Mind Question Answering on FanToM

91.7AccuracyHuman
53.84463.67273.583.328Apr 20, 2026

Evaluation results

MethodLinks
HumanEvaluator LLM=GPT-4o2026.0491.7
TTEvaluator LLM=GPT-4o2026.0487.4
PDDL-MINDEvaluator LLM=GPT-4o2026.0480
EnigmaToMEvaluator LLM=GPT-4o2026.0455.3