Share your thoughts, 1 month free Claude Pro on usSee more

Belief Prediction on ToM-BPD (test)

54.64Belief Accuracy

TTBYS

Updated 12d ago

Evaluation Results

Method	Links
TTBYS 2026.05		54.64
TTBYS 2026.05		43.62
Qwen-3-8B + MM 2026.05		42.05
Qwen-3-8B + HM 2026.05		41.21
Qwen-3-8B + CoT 2026.05		39.42
Qwen-3-8B 2026.05		38.64
TTBYS 2026.05		36.96
GPT-4o-mini + MM 2026.05		31.96
GPT-5 + MM 2026.05		31.74
LLaMA-3.1-8B-Instruct + MM 2026.05		31.67
LLaMA-3.1-8B-Instruct + HM 2026.05		30.8
GPT-4o-mini + HM 2026.05		30.6
GPT-5 + HM 2026.05		29.6
Gemini-3-pro-high + MM 2026.05		29.28
Mixtral-7B-Instruct + MM 2026.05		29.06
Gemini-3-pro-high + HM 2026.05		27.9
LLaMA-3.1-8B-Instruct + CoT 2026.05		27.69
Mixtral-7B-Instruct + HM 2026.05		26.8
LLaMA-3.1-8B-Instruct 2026.05		25.67
Mixtral-7B-Instruct + CoT 2026.05		24.13
GPT-4o-mini + CoT 2026.05		23.41
Mixtral-7B-Instruct 2026.05		22.86
GPT-5 + CoT 2026.05		22.68
GPT-5 2026.05		21.84
GPT-4o-mini 2026.05		21.45
Gemini-3-pro-high + CoT 2026.05		18.34
Gemini-3-pro-high 2026.05		17.84