CaSiNo
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Bargaining Allocation | CaSiNo | IR (%)100 | 8 | |
| Opponent priority-ordering prediction | CaSiNo (5-fold CV) | EMA53.84 | 5 | |
| Opponent modeling | CaSiNo (External) | EMA53.84 | 5 | |
| Negotiation | CaSiNo | IR1 | 3 | |
| Negotiation performance and belief calibration | CaSiNo native (held-out dialogues) | Accept-F10.947 | 3 | |
| Negotiation | CaSiNo (test) | IR1 | 1 | |
| Negotiation Comprehension & Simulation | Augmented CaSiNo | Success Rate (Simple Tasks)60 | 1 | |
| Mental State Inference | Augmented CaSiNo | Accuracy40 | 1 | |
| Joint Outcome & Utility Prediction | CaSiNo | Accuracy95.5 | 1 | |
| Opponent priority-ordering prediction | CaSiNo (150-dialogue held-out split) | EMA37.3 | 1 |
Showing 10 of 10 rows