Evals / video

Logos and watermarks

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
Put a logo on a videoAdd dice.png as a logo in the top left corner of bunny.mp4. Save it as branded.mp4.pass16s · 8.8kpass20s · 9.4knot runpass28s · 11.5kpass15s · 10.4knot runnot run
Put a watermark on a videoAdd the text SAMPLE in the bottom right corner of bunny.mp4 for its whole length. Save it as marked.mp4.pass17s · 6.4kpass18s · 5.5kpass18s · 6.4kpass27s · 12.3kpass19s · 12.9knot runnot run