Evals / video

Speed and stabilise

2 scenarios, 2 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
Speed up a clipMake bunny.mp4 play twice as fast and save it as fast.mp4.pass12s · 5.1kpass17s · 4.7kpass16s · 8.9kpass17s · 9.8knot runnot run
Steady a shaky clipshaky.mp4 was filmed by hand. Stabilize it and save it as steady.mp4.pass39s · 13.2kpass44s · 9.6kpass119s · 14.6kpass38s · 10.7knot runnot run