Evals / video

Size and compression

1 scenario, 1 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
Shrink a video to a size limitbunny.mp4 must be under 400KB for an upload form. Save it as small.mp4, keeping the full length.pass17s · 9.0kpass19s · 12.4kpass15s · 5.9kpass18s · 9.3kpass18s · 10.5knot runnot run