Multiple-Choice Reasoning on Date Understanding (test)
78.2AccuracyRIOT
Evaluation results
| Method | Links | |
|---|---|---|
| RIOToptimization=automatic2025.06 | 78.2 | |
| Twenty-Shot CoToptimization=manual, shots=202025.06 | 76.3 | |
| OPROoptimization=automatic2025.06 | 76.3 | |
| Zero-Shot CoToptimization=manual, shots=02025.06 | 76.1 | |
| DSPyoptimization=automatic2025.06 | 74.3 | |
| Four-Shot CoToptimization=manual, shots=42025.06 | 73.2 | |
| APEoptimization=automatic2025.06 | 72.8 | |
| TextGradoptimization=automatic2025.06 | 71.9 |