Evals / tables

Reshape

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
Pivot tableFrom gdp.csv make a table with one row per Country Name and one column per Year holding Value. Save it as wide.csv.pass12s · 3.6kpass13s · 5.5kpass10s · 10.4kpass39s · 11.6knot runnot run
Split into files of 100 rowsSplit countries.csv into files of 100 rows each in a folder called parts.pass14s · 3.7kpass18s · 6.1kpass23s · 10.5kpass9s · 10.1knot runnot run