Crumbl Cookies
Rebuilt by Claude Opus 5.5: 194 of 531 hidden tests passed (36.5%)
reference.local/
Referencerebuild.local/
Claude Opus 5.5| Model | Passed | % | Screenshot |
|---|---|---|---|
| 194 | 36.5 | ||
| 180 | 33.9 | ||
| 144 | 27.1 | ||
| 137 | 25.8 | ||
| 98 | 18.5 | ||
| 41 | 7.7 | ||
| 34 | 6.4 | ||
| 0 | 0.0 | — |