Therapeutic Game Evaluation on LETGAMESEVAL Human-portrayed SPs
4.74Helpfulness ScoreLETGAMES
Evaluation Results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LETGAMESGame Backbone=GPT-4o2026.02 | 4.74 | 95.24 | 98.77 | 98.41 | 94.49 | 93.65 | 3.67 | 4.28 | 4.33 | 3.86 | 4.14 | |
| LETGAMESGame Backbone=GPT-4o Mini2026.02 | 4.63 | 95.24 | 99.4 | 100 | 92.62 | 93.33 | 3.24 | 4.28 | 4.33 | 3.71 | 3.86 | |
| ReMeGame Backbone=GPT-4o2026.02 | 3.55 | — | 99.1 | 44.5 | 98.25 | — | 3.45 | — | — | 2.4 | 2.38 | |
| ReMeGame Backbone=GPT-4o Mini2026.02 | 3.48 | — | 99.9 | 46.5 | 98.85 | — | 3.15 | — | — | 2.42 | 2.4 |