Repeated Negotiation on Repeated Negotiation (vs Claude) (test)
6.94Buyer Avg RewardBoN-oppo
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BoN-oppoBase Model=Gemini, Opponent=Claude2026.02 | 6.94 | 4.86 | |
| BoN-simulationBase Model=Gemini, Opponent=Claude2026.02 | 5.53 | 1.03 | |
| BoN-oppo (iid)Base Model=Gemini, Opponent=Claude2026.02 | 3.23 | -0.1 | |
| BoN-evalBase Model=Gemini, Opponent=Claude2026.02 | 1.03 | -0.5 | |
| Baseline w. thinkingBase Model=Gemini, Opponent=Claude2026.02 | 0.63 | 0.8 |