List your company

Theory of Mind Question Answering on MuMa-ToM

93.5AccuracyHuman
31.51647.60863.779.792Apr 20, 2026

Evaluation results

MethodLinks
HumanEvaluator LLM=GPT-4o2026.0493.5
PDDL-MINDEvaluator LLM=GPT-4o2026.0488.8
AutoToMEvaluator LLM=GPT-4o2026.0481.4
LIMPEvaluator LLM=GPT-4o2026.0476.6
BIP-ALMEvaluator LLM=GPT-4o2026.0433.9