Multi-step jobs
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 |
|---|---|---|---|---|---|---|
| Turn a workbook into a reportSend the numbers in temperature.xlsx to a client as a PDF with a proper table, temperature.pdf, and give me a Word copy, temperature.docx, that I can edit. | pass64s · 12.8k | pass22s · 6.7k | pass93s · 22.6k | pass38s · 21.6k | not run | not run |