Personality Assessment on Gamified Personality Assessment Annotator 4 ground truth
1.301Score (Openness)DeepSeek-V3.2
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| DeepSeek-V3.2Condition=Single-trait2025.07 | 1.301 | 1.35 | 1.264 | 1.218 | 1.238 | 1.107 | |
| GLM-5Condition=Single-trait2025.07 | 1.081 | 1.105 | 1.185 | 1.078 | 1.09 | 0.942 | |
| Kimi-K2.5Condition=Single-trait2025.07 | 1.07 | 1.11 | 1.102 | 1.083 | 1.106 | 0.958 | |
| Claude Sonnet 4.6Condition=Single-trait2025.07 | 1.052 | 1.081 | 1.101 | 1.041 | 1.014 | 0.942 | |
| Qwen3.5-PlusCondition=Single-trait2025.07 | 0.974 | 0.968 | 1.018 | 0.977 | 0.964 | 0.848 | |
| GPT-5.4Condition=Single-trait2025.07 | 0.864 | 0.843 | 0.9 | 0.825 | 0.848 | 0.782 |