Repair and metadata
1 scenario, 1 run by an agent. Each run shows its result, time and new tokens.
| Scenario | Codexwithout deft | Codexwith deft, skill installed | Claude Opus 5.5without deft | Claude Opus 5.5with deft, skill installed | Claude Codewithout deft | Claude Codewith deft |
|---|---|---|---|---|---|---|
| Set the document titleSet the PDF title of paper.pdf to Trace compilation and save it as titled.pdf. | pass18s · 4.3k | pass17s · 25.3k | pass12s · 9.0k | pass14s · 10.0k | not run | not run |