Evals / video

Reframe

1 scenario, 1 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
Fit into a vertical framePut bunny.mp4 into a 1080x1920 vertical frame with black bars, keeping the whole picture. Save it as tall.mp4.pass14s · 8.7kpass14s · 5.5kpass18s · 9.0kpass19s · 10.2knot runnot run