2 related articles
产品体验Testing Claude Haiku 4.5 on 5 visual programming tasks including 3D modeling and physics simulation reveals systematic failures in reasoning, instruction following, and code quality.
产品体验Hands-on testing of Claude Haiku 4.5's coding ability, comparing it with Sonnet 4.5 and Opus 4.1 across weather cards, physics simulation, and 3D rendering tasks.