Personality Assessment on Gamified Personality Assessment Annotator 3 ground truth
1.239Score (Openness)DeepSeek-V3.2
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| DeepSeek-V3.2Condition=Single-trait2025.07 | 1.239 | 1.274 | 1.189 | 1.152 | 1.155 | 1.027 | |
| GLM-5Condition=Single-trait2025.07 | 1.004 | 1.041 | 1.113 | 1.042 | 1.025 | 0.866 | |
| Kimi-K2.5Condition=Single-trait2025.07 | 0.997 | 1.026 | 1.026 | 0.998 | 1.03 | 0.872 | |
| Claude Sonnet 4.6Condition=Single-trait2025.07 | 0.975 | 1.01 | 1.016 | 0.962 | 0.925 | 0.843 | |
| Qwen3.5-PlusCondition=Single-trait2025.07 | 0.906 | 0.912 | 0.958 | 0.921 | 0.897 | 0.776 | |
| GPT-5.4Condition=Single-trait2025.07 | 0.809 | 0.785 | 0.829 | 0.772 | 0.781 | 0.716 |