SketchAgentBench – evaluate LLMs on 3D spatial reasoning
One photo. One prompt. Code, render, inspect, refine. 11 models, 25 photos, 275 runs—each scored on its final 3D scene.
One photo. One prompt. Code, render, inspect, refine. 11 models, 25 photos, 275 runs—each scored on its final 3D scene.