List your company

Strategy Prediction on ToM-BPD (test)

39.78Strategy AccuracyTTBYS
1319.952526.90533.8575May 21, 2026

Evaluation results

MethodLinks
TTBYSBackbone=Qwen-3-8B, Enhancement=TTBYS2026.0539.78
TTBYSBackbone=LLaMA-3.1-8B-Instruct, Enhancement=TTBYS2026.0537.76
TTBYSBackbone=Mixtral-7B-Instruct, Enhancement=TTBYS2026.0536.79
GPT-4o-mini + MMBackbone=GPT-4o-mini, Enhancement=MM2026.0528.18
GPT-4o-mini + HMBackbone=GPT-4o-mini, Enhancement=HM2026.0527.72
GPT-5 + MMBackbone=GPT-5, Enhancement=MM2026.0527.14
GPT-4o-miniBackbone=GPT-4o-mini, Enhancement=Basic2026.0527.13
GPT-4o-mini + CoTBackbone=GPT-4o-mini, Enhancement=CoT2026.0526.68
GPT-5 + HMBackbone=GPT-5, Enhancement=HM2026.0526.68
Gemini-3-pro-high + MMBackbone=Gemini-3-pro-high, Enhancement=MM2026.0524.59
Gemini-3-pro-high + HMBackbone=Gemini-3-pro-high, Enhancement=HM2026.0523.68
Qwen-3-8B + HMBackbone=Qwen-3-8B, Enhancement=HM2026.0523.68
GPT-5Backbone=GPT-5, Enhancement=Basic2026.0522.81
LLaMA-3.1-8B-Instruct + MMBackbone=LLaMA-3.1-8B-Instruct, Enhancement=MM2026.0522.63
LLaMA-3.1-8B-Instruct + HMBackbone=LLaMA-3.1-8B-Instruct, Enhancement=HM2026.0522.12
Qwen-3-8B + MMBackbone=Qwen-3-8B, Enhancement=MM2026.0521.89
Qwen-3-8BBackbone=Qwen-3-8B, Enhancement=Basic2026.0521.42
GPT-5 + CoTBackbone=GPT-5, Enhancement=CoT2026.0521.16
Gemini-3-pro-highBackbone=Gemini-3-pro-high, Enhancement=Basic2026.0520.67
Qwen-3-8B + CoTBackbone=Qwen-3-8B, Enhancement=CoT2026.0519.86
Gemini-3-pro-high + CoTBackbone=Gemini-3-pro-high, Enhancement=CoT2026.0519.84
Mixtral-7B-Instruct + HMBackbone=Mixtral-7B-Instruct, Enhancement=HM2026.0517.84
Mixtral-7B-Instruct + CoTBackbone=Mixtral-7B-Instruct, Enhancement=CoT2026.0517.64
Mixtral-7B-Instruct + MMBackbone=Mixtral-7B-Instruct, Enhancement=MM2026.0517.12
LLaMA-3.1-8B-Instruct + CoTBackbone=LLaMA-3.1-8B-Instruct, Enhancement=CoT2026.0516.8
Mixtral-7B-InstructBackbone=Mixtral-7B-Instruct, Enhancement=Basic2026.0516.41
LLaMA-3.1-8B-InstructBackbone=LLaMA-3.1-8B-Instruct, Enhancement=Basic2026.0514.03