OpenAI has launched its new image generation model, ChatGPT Images 2.0, which Sam Altman claims represents a leap in quality comparable to the jump from GPT-3 to GPT-5. Early testing suggests the model excels at complex, detailed illustrations, outperforming competitors like Google's Gemini and Anthropic's Claude Opus 4.7 in a 'Where's Waldo' style challenge involving a raccoon with a ham radio. However, the model may struggle with accurately solving its own generated puzzles. AI
Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →
IMPACT Sets new SOTA on complex illustration generation, potentially displacing Gemini and Claude.
RANK_REASON Frontier-lab model release with system card
