GPT-5.6 Sol: OpenAI's Best Vision Model Yet, But Gemini 3.5 Flash Still Leads

GPT 5.6 Sol is the best "vision" model OpenAI ever released

OpenAI's latest GPT-5.6 lineup, including Sol, Terra, and Luna, shows significant vision improvements, especially in object detection and counting. Sol scored 46.2 mAP@50 in detection, up from 13.8 for GPT-5.5, and improved counting accuracy to 73.0%. However, Sol lags in OCR and text extraction, and its higher token usage and cost make Gemini 3.5 Flash a more practical choice for high-volume tasks. The models also struggle with large images and certain complex scenes, but overall, OpenAI is now a stronger contender in vision.