Therapeutic Game Evaluation on LETGAMESEVAL LLM-based SPs
4.98Helpfulness ScoreLETGAMES
Evaluation Results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LETGAMESGame Backbone=GPT-4o2026.02 | 4.98 | 93.81 | 100 | 100 | 98.98 | 97.94 | 3.61 | 4.87 | 4.74 | 4.13 | 4.58 | |
| LETGAMESGame Backbone=GPT-4o Mini2026.02 | 4.85 | 87.2 | 99.83 | 100 | 98.36 | 94.18 | 3.6 | 4.14 | 4.53 | 3.83 | 4.06 | |
| ReMeGame Backbone=GPT-4o2026.02 | 3.6 | — | 99.33 | 43.2 | 99.05 | — | 3.38 | — | — | 2.38 | 2.34 | |
| ReMeGame Backbone=GPT-4o Mini2026.02 | 3.51 | — | 100 | 45.78 | 99.13 | — | 3.4 | — | — | 2.47 | 2.45 |