Code Generation on HumanEval (var@10, var@100, Pres.)
35.88Variation Rate @ k=10
Dense
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 35.88 | 20.06 | 100 | |
2026.06 | 35.72 | 13.44 | 105.2 | |
2026.06 | 34.71 | 12.5 | 100 | |
2026.06 | 33.89 | 15.24 | 100 | |
2026.06 | 31.97 | 12.22 | 87.3 | |
2026.06 | 29.44 | 15.04 | 78.5 | |
2026.06 | 29.33 | 12.08 | 90.6 | |
2026.06 | 27.71 | 12.37 | 89.4 | |
2026.06 | 27.12 | 12.17 | 87.7 | |
2026.06 | 26.98 | 9.5 | 71 | |
2026.06 | 26.96 | 10.39 | 63.5 | |
2026.06 | 26.62 | 7.11 | 62.6 | |
2026.06 | 26.48 | 12.17 | 86.8 | |
2026.06 | 23.64 | 8.25 | 61.9 | |
2026.06 | 23 | 8.72 | 53.8 | |
2026.06 | 22.18 | 6.05 | 46 | |
2026.06 | 20.53 | 7.55 | 47.4 | |
2026.06 | 20.24 | 10.23 | 70.1 | |
2026.06 | 18.91 | 7.08 | 51.1 | |
2026.06 | 18.8 | 4.75 | 43.3 | |
2026.06 | 18.51 | 9.74 | 65.6 | |
2026.06 | 16.72 | 9.21 | 60.9 | |
2026.06 | 16.46 | 4.19 | 33.4 | |
2026.06 | 14.27 | 3.56 | 32.7 | |
2026.06 | 12.43 | 2.63 | 23.9 | |
2026.06 | 9.83 | 2.67 | 23.3 | |
2026.06 | 8.57 | 1.75 | 16.3 |