Evals / image

Site icons

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
Website iconsMake a favicon set from dice.png in a folder called icons.pass28s · 18.0kpass15s · 5.6kpass23s · 11.6kpass17s · 10.4knot runnot run