Evals / image

Background and transparency

2 scenarios, 2 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
Remove a white backgroundMake the white parts of dice.png transparent and save it as cut.png.pass30s · 8.9kpass21s · 11.1knot runpass33s · 12.7kpass36s · 15.3knot runnot run
Flatten transparencyConvert dice.png to dice.jpg with a white background where it is transparent.pass11s · 3.3kpass13s · 4.2kpass7s · 4.9kpass10s · 8.8kpass9s · 9.8knot runnot run