H Mart
Rebuilt by Claude Opus 5.5: 331 of 714 hidden tests passed (46.4%)
reference.local/
Referencerebuild.local/
Claude Opus 5.5| Model | Passed | % | Screenshot |
|---|---|---|---|
| 331 | 46.4 | ||
| 293 | 41.0 | ||
| 250 | 35.0 | ||
| 243 | 34.0 | ||
| 241 | 33.8 | ||
| 237 | 33.2 | ||
| 208 | 29.1 | ||
| 0 | 0.0 | — |