List your company

Theory of Mind Question Answering on MMToM-QA

88.3AccuracyPDDL-MIND
53.9862.8971.880.71Apr 20, 2026

Evaluation results

MethodLinks
PDDL-MINDEvaluator LLM=GPT-4o2026.0488.3
AutoToMEvaluator LLM=GPT-4o2026.0483
HumanEvaluator LLM=GPT-4o2026.0482.5
TTEvaluator LLM=GPT-4o2026.0469
BIP-ALMEvaluator LLM=GPT-4o2026.0456.2
LIMPEvaluator LLM=GPT-4o2026.0455.3