Roboflow benchmark: GPT-5.6 Sol is OpenAI's best vision model

In Roboflow's upcoming VLM benchmark, GPT-5.6 Sol scored 46.2 mAP@50 on object detection, up from GPT-5.5's 13.8; Terra and Luna hit 44.7 and 43.3. Sol also excelled at document layout detection and dense scenes.