Feedback Evaluation on DRS-BENCH Afixa
73.6Human ScoreAGENTIC-DRS
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| AGENTIC-DRSBackbone=GPT-4o2025.08 | 73.6 | 81.7 | 79.4 | 80.3 | |
| AGENTIC-DRSBackbone=Gemini2025.08 | 72 | 82.1 | 76.9 | 76.2 |
| Method | Links | ||||
|---|---|---|---|---|---|
| AGENTIC-DRSBackbone=GPT-4o2025.08 | 73.6 | 81.7 | 79.4 | 80.3 | |
| AGENTIC-DRSBackbone=Gemini2025.08 | 72 | 82.1 | 76.9 | 76.2 |