Feedback Evaluation on DRS-BENCH IDD
0.742Human ScoreAGENTIC-DRS
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| AGENTIC-DRSBackbone=Gemini2025.08 | 0.742 | 0.834 | 0.802 | 0.785 | |
| AGENTIC-DRSBackbone=GPT-4o2025.08 | 0.74 | 0.837 | 0.791 | 0.804 |
| Method | Links | ||||
|---|---|---|---|---|---|
| AGENTIC-DRSBackbone=Gemini2025.08 | 0.742 | 0.834 | 0.802 | 0.785 | |
| AGENTIC-DRSBackbone=GPT-4o2025.08 | 0.74 | 0.837 | 0.791 | 0.804 |