Desire Prediction on ToM-BPD (test)
72.82Desire AccuracyTTBYS
Evaluation Results
| Method | Links | |
|---|---|---|
| TTBYSBackbone=Qwen-3-8B, Enhancement=TTBYS2026.05 | 72.82 | |
| Gemini-3-pro-highBackbone=Gemini-3-pro-high, Enhancement=Basic Prompting2026.05 | 72.26 | |
| GPT-5Backbone=GPT-5, Enhancement=Basic Prompting2026.05 | 71.62 | |
| TTBYSBackbone=Mixtral-7B-Instruct, Enhancement=TTBYS2026.05 | 71.44 | |
| GPT-5 + CoTBackbone=GPT-5, Enhancement=CoT2026.05 | 70.91 | |
| Gemini-3-pro-high + CoTBackbone=Gemini-3-pro-high, Enhancement=CoT2026.05 | 70.68 | |
| TTBYSBackbone=LLaMA-3.1-8B-Instruct, Enhancement=TTBYS2026.05 | 69.43 | |
| GPT-5 + MMBackbone=GPT-5, Enhancement=MM2026.05 | 69.33 | |
| Gemini-3-pro-high + HMBackbone=Gemini-3-pro-high, Enhancement=HM2026.05 | 68.84 | |
| GPT-5 + HMBackbone=GPT-5, Enhancement=HM2026.05 | 68.33 | |
| GPT-4o-mini + CoTBackbone=GPT-4o-mini, Enhancement=CoT2026.05 | 66.33 | |
| Gemini-3-pro-high + MMBackbone=Gemini-3-pro-high, Enhancement=MM2026.05 | 66.33 | |
| LLaMA-3.1-8B-Instruct + MMBackbone=LLaMA-3.1-8B-Instruct, Enhancement=MM2026.05 | 66.33 | |
| Qwen-3-8B + HMBackbone=Qwen-3-8B, Enhancement=HM2026.05 | 65.84 | |
| GPT-4o-miniBackbone=GPT-4o-mini, Enhancement=Basic Prompting2026.05 | 65.82 | |
| GPT-4o-mini + MMBackbone=GPT-4o-mini, Enhancement=MM2026.05 | 65.15 | |
| GPT-4o-mini + HMBackbone=GPT-4o-mini, Enhancement=HM2026.05 | 64.87 | |
| Qwen-3-8B + MMBackbone=Qwen-3-8B, Enhancement=MM2026.05 | 64.33 | |
| Mixtral-7B-Instruct + HMBackbone=Mixtral-7B-Instruct, Enhancement=HM2026.05 | 60.22 | |
| Mixtral-7B-Instruct + MMBackbone=Mixtral-7B-Instruct, Enhancement=MM2026.05 | 59.7 | |
| LLaMA-3.1-8B-Instruct + HMBackbone=LLaMA-3.1-8B-Instruct, Enhancement=HM2026.05 | 54.14 | |
| Qwen-3-8B + CoTBackbone=Qwen-3-8B, Enhancement=CoT2026.05 | 50.9 | |
| Qwen-3-8BBackbone=Qwen-3-8B, Enhancement=Basic Prompting2026.05 | 50.43 | |
| Mixtral-7B-InstructBackbone=Mixtral-7B-Instruct, Enhancement=Basic Prompting2026.05 | 45.64 | |
| Mixtral-7B-Instruct + CoTBackbone=Mixtral-7B-Instruct, Enhancement=CoT2026.05 | 44.1 | |
| LLaMA-3.1-8B-Instruct + CoTBackbone=LLaMA-3.1-8B-Instruct, Enhancement=CoT2026.05 | 36.25 | |
| LLaMA-3.1-8B-InstructBackbone=LLaMA-3.1-8B-Instruct, Enhancement=Basic Prompting2026.05 | 34.41 |