Evals / tables

Format conversion

5 scenarios, 5 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
Large CSV to ExcelConvert gdp.csv to an Excel file called gdp.xlsx.pass33s · 6.1kpass14s · 9.8kpass10s · 8.9kpass21s · 12.4kpass6s · 9.2knot runnot run
Parse a European CSVventas.csv came from a Spanish Excel. Convert it to ventas.json as an array of objects.pass12s · 6.0kpass17s · 5.7kpass12s · 10.5kpass15s · 9.7kpass13s · 11.2knot runnot run
Read LibreOffice and old Excel filesConvert the first sheet of issues.ods to ods.csv and the first sheet of issues.xls to xls.csv.pass113s · 38.5kpass17s · 5.4kpass14s · 5.8kpass32s · 18.4kpass14s · 10.3knot runnot run
Chinese table to Excel把 销售.csv 转成 Excel 文件 销售.xlsx。pass37s · 9.4kpass12s · 4.0kpass11s · 5.1kpass18s · 11.3kpass12s · 9.2knot runnot run
Table for a reportTurn temperature.xlsx into a Markdown table in table.md.pass20s · 6.3kpass12s · 4.6kpass10s · 5.3kpass26s · 10.0kpass15s · 9.3knot runnot run