multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
Why it matters
A same-prompts-every-time read on Claude Sonnet 5 across browser control, C++ game code, 3D scenes, frontend design and multimodalA model that works with more than text — reading images, audio, or video, and sometimes generating them too.Full definition → tasks, comparable against the same reviewer's runs on rival models.
