Personality Assessment on Gamified Personality Assessment Annotator 2 ground truth
1.39Score (Openness)DeepSeek-V3.2
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| DeepSeek-V3.2Condition=Single-trait2025.07 | 1.39 | 1.43 | 1.353 | 1.293 | 1.332 | 1.203 | |
| GLM-5Condition=Single-trait2025.07 | 1.149 | 1.174 | 1.24 | 1.131 | 1.157 | 1.008 | |
| Kimi-K2.5Condition=Single-trait2025.07 | 1.146 | 1.191 | 1.196 | 1.15 | 1.193 | 1.054 | |
| Claude Sonnet 4.6Condition=Single-trait2025.07 | 1.13 | 1.16 | 1.161 | 1.126 | 1.101 | 1.024 | |
| Qwen3.5-PlusCondition=Single-trait2025.07 | 1.021 | 1.026 | 1.055 | 1.031 | 1.027 | 0.915 | |
| GPT-5.4Condition=Single-trait2025.07 | 0.913 | 0.89 | 0.944 | 0.877 | 0.901 | 0.836 |