List your company

Theory of Mind Reasoning on FanToM

96.131st-Order AccuracyRECTOM
62.236471.035779.83588.6343Jun 10, 2026

Evaluation results

MethodLinks
RECTOMModel=GPT-5.42026.0696.1399.397.53
RECTOMModel=Qwen3.52026.0692.8286.0189.81
TIMETOMModel=GPT-5.42026.0692.2792.3192.28
SIMTOMModel=GPT-5.42026.0691.1695.893.21
RECTOMModel=Gemini-32026.0691.1691.6191.36
SIMTOMModel=Qwen3.52026.0689.581.8286.11
CoTModel=GPT-5.42026.0688.9586.7187.96
RECTOMModel=Gemma-42026.0687.2984.6286.11
TIMETOMModel=Qwen3.52026.0686.7485.3186.11
SIMTOMModel=Gemini-32026.0682.3289.5185.49
CoTModel=Qwen3.52026.0678.4585.3181.48
CoTModel=Gemini-32026.0677.3590.2183.02
TIMETOMModel=Gemma-42026.0676.2479.7277.78
TIMETOMModel=Gemini-32026.0674.5991.6182.1
SIMTOMModel=Gemma-42026.0671.2780.4275.31
CoTModel=Gemma-42026.0663.5475.5268.83