Evals / documents

Edit a document

2 scenarios, 2 run by an agent. Each run shows its result, time and new tokens.

ScenarioCodexwithout deftCodexwith deft, skill installedClaude Opus 5.5without deftClaude Opus 5.5with deft, skill installedClaude Codewithout deftClaude Codewith deft
Find and replace in WordReplace every Calibri with Georgia in letter.docx and save it as changed.docx, keeping the formatting.pass16s · 10.8kpass18s · 8.2kpass22s · 12.4kpass33s · 16.1knot runnot run
Add a table of contentsAdd a table of contents to rust-readme.md and save it as with-toc.md.pass13s · 5.3kpass18s · 9.2kpass14s · 10.5kpass15s · 10.7knot runnot run