Airtable
Rebuilt by Claude Opus 5.5: 74 of 589 hidden tests passed (12.6%)
reference.local/
Referencerebuild.local/
Claude Opus 5.5| Model | Passed | % | Screenshot |
|---|---|---|---|
| 74 | 12.6 | ||
| 60 | 10.2 | ||
| 41 | 7.0 | ||
| 36 | 6.1 | ||
| 35 | 5.9 | ||
| 33 | 5.6 | ||
| 27 | 4.6 | ||
| 26 | 4.4 |
Rebuilt by Claude Opus 5.5: 74 of 589 hidden tests passed (12.6%)
Reference
Claude Opus 5.5| Model | Passed | % | Screenshot |
|---|---|---|---|
| 74 | 12.6 | ||
| 60 | 10.2 | ||
| 41 | 7.0 | ||
| 36 | 6.1 | ||
| 35 | 5.9 | ||
| 33 | 5.6 | ||
| 27 | 4.6 | ||
| 26 | 4.4 |