Bean Box
Rebuilt by Claude Opus 5.5: 322 of 987 hidden tests passed (32.6%)
reference.local/
Referencerebuild.local/
Claude Opus 5.5| Model | Passed | % | Screenshot |
|---|---|---|---|
| 322 | 32.6 | ||
| 284 | 28.8 | ||
| 270 | 27.4 | ||
| 265 | 26.8 | ||
| 234 | 23.7 | ||
| 40 | 4.1 | ||
| 38 | 3.9 | — | |
| 9 | 0.9 |