Multi-turn Competitive Debate Simulation on ORCHID
1.25S ScoreR-Debater
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| R-DebaterModel=DeepSeek-V32025.12 | 1.25 | 1.11 | 1.19 | 1.25 | |
| R-DebaterModel=GPT-4o2025.12 | 1.13 | 1.16 | 1.26 | 1.23 | |
| Agent4DebateModel=GPT-4o2025.12 | 0.87 | 0.84 | 0.74 | 0.77 | |
| Agent4DebateModel=DeepSeek-V32025.12 | 0.75 | 0.89 | 0.81 | 0.75 |