Medium
Rebuilt by Claude Opus 5.5: 81 of 650 hidden tests passed (12.5%)
reference.local/
Referencerebuild.local/
Claude Opus 5.5| Model | Passed | % | Screenshot |
|---|---|---|---|
| 81 | 12.5 | ||
| 81 | 12.5 | ||
| 81 | 12.5 | ||
| 78 | 12.0 | ||
| 67 | 10.3 | ||
| 56 | 8.6 | ||
| 52 | 8.0 | ||
| 29 | 4.5 |
Rebuilt by Claude Opus 5.5: 81 of 650 hidden tests passed (12.5%)
Reference
Claude Opus 5.5| Model | Passed | % | Screenshot |
|---|---|---|---|
| 81 | 12.5 | ||
| 81 | 12.5 | ||
| 81 | 12.5 | ||
| 78 | 12.0 | ||
| 67 | 10.3 | ||
| 56 | 8.6 | ||
| 52 | 8.0 | ||
| 29 | 4.5 |