Personality Assessment on Gamified Personality Assessment Annotator 1 ground truth
1.312Score (Openness)DeepSeek-V3.2
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| DeepSeek-V3.2Condition=Single-trait2025.07 | 1.312 | 1.361 | 1.27 | 1.216 | 1.263 | 1.128 | |
| GLM-5Condition=Single-trait2025.07 | 1.094 | 1.12 | 1.188 | 1.08 | 1.105 | 0.96 | |
| Kimi-K2.5Condition=Single-trait2025.07 | 1.092 | 1.129 | 1.118 | 1.1 | 1.127 | 0.982 | |
| Claude Sonnet 4.6Condition=Single-trait2025.07 | 1.074 | 1.111 | 1.118 | 1.069 | 1.045 | 0.974 | |
| Qwen3.5-PlusCondition=Single-trait2025.07 | 0.977 | 0.975 | 1.02 | 0.998 | 0.985 | 0.866 | |
| GPT-5.4Condition=Single-trait2025.07 | 0.874 | 0.851 | 0.91 | 0.829 | 0.868 | 0.796 |