Coding Ability on MBPP (test)
51.58Accuracy
Alpaca-GPT4
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.03 | 51.58 | 36.03 | - | |
2026.03 | 49.74 | 37.06 | 2.88 | |
2026.03 | 49.47 | 37.16 | 3.15 | |
2026.03 | 48.41 | 37.7 | 4.65 | |
2026.03 | 47.88 | 36.71 | 1.89 | |
2026.03 | 47.62 | 37.2 | 3.24 | |
2026.03 | 47.47 | 37.18 | 3.2 | |
| 47.35 | 35.69 | -0.94 | ||
2026.03 | 47.08 | 36.47 | 1.23 | |
2026.03 | 46.56 | 36.17 | 0.39 | |
2026.03 | 46.08 | 35.18 | -2.34 | |
2026.03 | 44.97 | 35.68 | -0.98 |