Virtue Profiling on VirtueMap Questionnaire
96.2Rank ConsistencyClaude
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| ClaudeNumber of valid full-questionnaire runs (n)=32026.06 | 96.2 | 4.47 | 89.3 | 83.1 | 86 | 83.1 | 72.6 | |
| GeminiNumber of valid full-questionnaire runs (n)=52026.06 | 94.3 | 3.62 | 90.6 | 78.9 | 82.9 | 77.3 | 77.7 | |
| GrokNumber of valid full-questionnaire runs (n)=42026.06 | 93.6 | 3.77 | 91.8 | 78.9 | 81.4 | 76.8 | 78.4 | |
| QwenNumber of valid full-questionnaire runs (n)=52026.06 | 91.4 | 4.28 | 93.4 | 82.9 | 81.3 | 76.9 | 80.4 | |
| GPTNumber of valid full-questionnaire runs (n)=52026.06 | 91.2 | 3.57 | 92.3 | 83 | 81.1 | 76.3 | 82.3 | |
| LlamaNumber of valid full-questionnaire runs (n)=62026.06 | 87.3 | 4.61 | 87.4 | 80.4 | 83.1 | 80.7 | 72.7 | |
| DeepSeekNumber of valid full-questionnaire runs (n)=42026.06 | 86.9 | 4.08 | 89.8 | 74.1 | 78.8 | 72.1 | 77.9 | |
| MistralNumber of valid full-questionnaire runs (n)=62026.06 | 86 | 4.26 | 91.2 | 79.1 | 80.8 | 75.6 | 78.2 | |
| MiniMaxNumber of valid full-questionnaire runs (n)=62026.06 | 85.7 | 4.78 | 87.9 | 83.8 | 85.4 | 83 | 72 |