Evals / video

Stills, GIFs and slideshows

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
Make a GIFMake a 320 pixel wide GIF called clip.gif from the first 3 seconds of bunny.mp4.pass11s · 4.5kpass13s · 8.5kpass11s · 9.6kpass13s · 8.7kpass11s · 10.2knot runnot run
Photos to a videoMake a slideshow show.mp4 from hopper.png and DSCN0010.jpg, three seconds each.pass12s · 8.0kpass17s · 5.7knot runpass12s · 9.5kpass12s · 10.3knot runnot run