Evals / documents

Convert between formats

4 scenarios, 4 run by an agent. Each run shows its result, time and new tokens.

ScenarioCodexwithout deftCodexwith deft, skill installedCodexwith deft, skill as agents.mdClaude Opus 5.5without deftClaude Opus 5.5with deft, skill installedClaude Codewithout deftClaude Codewith deft
Markdown to WordConvert report.md to a Word document called report.docx.pass57s · 11.5kpass13s · 4.6kpass64s · 18.9kpass42s · 16.5kpass10s · 9.1knot runnot run
Markdown to a web pageTurn commonmark.md into a complete standalone HTML page called index.html.pass98s · 14.9kpass17s · 7.4kpass14s · 16.1kpass28s · 14.7kpass11s · 10.6knot runnot run
Word to a web pageConvert demo.docx to demo.html.pass66s · 18.8kpass14s · 8.9knot runpass27s · 14.1kpass9s · 9.2knot runnot run
Web page to WordConvert article.html to article.docx.pass53s · 8.5kpass12s · 7.8knot runpass51s · 18.8kpass11s · 9.1knot runnot run