Evals / tables

Workbook sheets

3 scenarios, 3 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
Answer a question about a workbookList the sheet names in issues.xlsx, one per line, in sheets.txt.pass14s · 3.7kpass14s · 12.0kpass16s · 10.6kpass12s · 8.5kpass13s · 10.2knot runnot run
Export one sheetExport the sheet named issue2 from issues.xlsx to issue2.csv.pass32s · 7.0kpass14s · 8.7kpass11s · 5.2kpass10s · 10.3kpass8s · 9.8knot runnot run
Export every sheetExport every sheet of issues.xlsx to its own CSV in a folder called sheets.pass39s · 7.8kpass22s · 11.2kpass18s · 12.0kpass34s · 12.3kpass13s · 11.9knot runnot run