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

Desire Prediction on ToM-BPD (test)

72.82Desire Accuracy

TTBYS

Updated 12d ago

Evaluation Results

Method	Links
TTBYS 2026.05		72.82
Gemini-3-pro-high 2026.05		72.26
GPT-5 2026.05		71.62
TTBYS 2026.05		71.44
GPT-5 + CoT 2026.05		70.91
Gemini-3-pro-high + CoT 2026.05		70.68
TTBYS 2026.05		69.43
GPT-5 + MM 2026.05		69.33
Gemini-3-pro-high + HM 2026.05		68.84
GPT-5 + HM 2026.05		68.33
GPT-4o-mini + CoT 2026.05		66.33
Gemini-3-pro-high + MM 2026.05		66.33
LLaMA-3.1-8B-Instruct + MM 2026.05		66.33
Qwen-3-8B + HM 2026.05		65.84
GPT-4o-mini 2026.05		65.82
GPT-4o-mini + MM 2026.05		65.15
GPT-4o-mini + HM 2026.05		64.87
Qwen-3-8B + MM 2026.05		64.33
Mixtral-7B-Instruct + HM 2026.05		60.22
Mixtral-7B-Instruct + MM 2026.05		59.7
LLaMA-3.1-8B-Instruct + HM 2026.05		54.14
Qwen-3-8B + CoT 2026.05		50.9
Qwen-3-8B 2026.05		50.43
Mixtral-7B-Instruct 2026.05		45.64
Mixtral-7B-Instruct + CoT 2026.05		44.1
LLaMA-3.1-8B-Instruct + CoT 2026.05		36.25
LLaMA-3.1-8B-Instruct 2026.05		34.41