Code Generation on BigCodeBench Lite-Pro Compositional Stream
66.7Accuracy
MEMPROBE
Updated 1d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 66.7 | 21.9 | - | |
2026.06 | 64.6 | - | 2.1 | |
2026.06 | 62.5 | 17.7 | - | |
2026.06 | 62.5 | - | 0 | |
2026.06 | 60.4 | - | - | |
2026.06 | 60.4 | - | - | |
| 59 | - | - | ||
| 59 | - | - | ||
2026.06 | 58.3 | 13.5 | - | |
2026.06 | 56.3 | - | 2 | |
2026.06 | 50.7 | - | 2.1 | |
2026.06 | 48.6 | 3.8 | - | |
2026.06 | 45.8 | - | 1.4 | |
2026.06 | 44.8 | - | - | |
2026.06 | 44.8 | - | - | |
2026.06 | 44.4 | 0.4 | - | |
2026.06 | 44.4 | - | 0.6 | |
2026.06 | 43.8 | 1 | - | |
2026.06 | 39.6 | 5.2 | - | |
2026.06 | 38.2 | - | 1.4 |