Blue Apron
Rebuilt by Claude Opus 5.5: 89 of 410 hidden tests passed (21.7%)
reference.local/
Referencerebuild.local/
Claude Opus 5.5| Model | Passed | % | Screenshot |
|---|---|---|---|
| 89 | 21.7 | ||
| 62 | 15.1 | ||
| 58 | 14.1 | ||
| 53 | 12.9 | ||
| 49 | 12.0 | ||
| 41 | 10.0 | ||
| 26 | 6.3 | ||
| 20 | 4.9 |