Document facts
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 |
|---|---|---|---|---|---|---|
| How long is this documentHow many words are in demo.docx? Write the number to count.txt. | pass12s · 3.1k | pass18s · 4.8k | pass24s · 12.1k | pass9s · 10.1k | not run | not run |