Code Reasoning on MBPP base and extended (out-of-distribution)
55.83Accuracy
InftyThink+
Updated 4d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.02 | 55.83 | 47.38 | 9.27 | 49.19 | |
2026.02 | 53.85 | 45.92 | 4.64 | 23.62 | |
2026.02 | 50.09 | 45.43 | 6.69 | 80.36 | |
2026.02 | 49.28 | 42.05 | 4.73 | 26.36 | |
2026.02 | 48.07 | 41.01 | 5.48 | 62.45 |