Real-Life Creative Problem Solving Evaluation
70.03Preference AccuracyDICAI
Evaluation Results
| Method | Links | |
|---|---|---|
| DICAIJudge Model=GPT-4o2026.06 | 70.03 | |
| ICAIJudge Model=GPT-4o2026.06 | 56 | |
| AutoRubricJudge Model=GPT-4o2026.06 | 42.39 | |
| CoTJudge Model=GPT-4o2026.06 | 38.07 | |
| CoT-SCJudge Model=GPT-4o2026.06 | 35.99 | |
| ToTJudge Model=GPT-4o2026.06 | 35.6 | |
| Self-RefineJudge Model=GPT-4o2026.06 | 32.01 |