Code Reasoning (Input Prediction) on CRUXEval-I (1-shot)
79.75AccuracyERNIE 5.0-Base
Evaluation Results
| Method | Links | |
|---|---|---|
| ERNIE 5.0-BaseNumber of shots=1-shot2026.02 | 79.75 | |
| Kimi K2-BaseNumber of shots=1-shot2026.02 | 73.64 | |
| DS V3.2-Exp-BaseNumber of shots=1-shot2026.02 | 59.54 |