Code Generation on MBPP+ (F0)
0False Release RateFirst_p
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| First_palpha=0.102026.05 | 0 | — | |
| First_palpha=0.052026.05 | 0 | — | |
| always-valid release wrapperalpha=0.102026.05 | 0 | — | |
| always-valid release wrapperalpha=0.052026.05 | 0 | — | |
| always-valid release wrapperalpha=0.202026.05 | 3.33 | 10 | |
| First_palpha=0.202026.05 | 6.67 | 3.5 | |
| Stability2026.05 | 23.33 | 2.7143 | |
| Entropy2026.05 | 76.67 | 1.7826 |