Amazon
Rebuilt by Claude Opus 5.5: 582 of 1,025 hidden tests passed (56.8%)
reference.local/
Referencerebuild.local/
Claude Opus 5.5| Model | Passed | % | Screenshot |
|---|---|---|---|
| 582 | 56.8 | ||
| 495 | 48.3 | ||
| 429 | 41.9 | ||
| 402 | 39.2 | ||
| 398 | 38.8 | ||
| 386 | 37.7 | ||
| 313 | 30.5 | ||
| Error | — |