Opus 5.5 video test scores 7/10 on a single prompt

airplanestar 𓂀 @airplanestar_Originally posted 2026.09.27

Open original on X

testing Claude Opus 5.5 👀 this one is interesting. the model is clearly capable, but unfortunately it didn't nail the whole thing with a one-shot prompt. had to make a few adjustments before getting it to this point. personal take: 7/10 still, DeepSeek 4.1 Flash did better for me on this specific challenge, it got the result in one shot with the same prompt. more models to test👀

This post quotes another post: x.com/airplanestar_/status/2103724189807190454