Evals / documents

Make a PDF

6 scenarios, 6 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
Report with an image and tableRender report.md as report.pdf. The chart image next to it must appear in the PDF.fail50s · 12.9kpass14s · 5.0kpass12s · 10.2kpass24s · 12.0kpass21s · 12.3knot runnot run
Chinese Markdown to PDF把 books.md 转成 PDF,保存为 books.pdf,中文必须正常显示。fail98s · 30.0kpass19s · 5.9kpass15s · 10.5kpass69s · 24.1kpass23s · 13.7knot runnot run
README to PDFRender rust-readme.md as a nicely formatted PDF called readme.pdf.pass60s · 15.0kpass15s · 8.2kpass13s · 25.0kpass61s · 21.1kpass12s · 13.0knot runnot run
Word to PDFConvert demo.docx to demo.pdf.fail54s · 18.2kpass12s · 4.3knot runpass38s · 16.1kpass26s · 13.3knot runnot run
Web page to PDFConvert article.html to article.pdf.pass120s · 17.5kpass13s · 4.5knot runpass62s · 19.5kpass16s · 10.1knot runnot run
E-book to PDFConvert frankenstein.epub to book.pdf.pass34s · 7.2kpass19s · 5.5knot runpass82s · 30.2kpass9s · 9.8knot runnot run