Blinkist
Rebuilt by Claude Opus 5.5: 120 of 437 hidden tests passed (27.5%)
reference.local/
Referencerebuild.local/
Claude Opus 5.5| Model | Passed | % | Screenshot |
|---|---|---|---|
| 120 | 27.5 | ||
| 101 | 23.1 | ||
| 90 | 20.6 | ||
| 88 | 20.1 | ||
| 82 | 18.8 | ||
| 79 | 18.1 | ||
| 68 | 15.6 | ||
| 43 | 9.8 |