OpenAI's Anonymous Image Model Hits LMArena, Exposed by SynthID Watermark
新智元 · wechat · 2026-08-10
An anonymous image model codenamed 'mona-lisa-1' has quietly appeared on the LMArena blind test leaderboard. Developers used OpenAI's verification tool to discover a SynthID watermark, confirming it as OpenAI's new release.
Tests show that compared to the current GPTImage2, this model significantly improves in realism and detail, with noticeably less plastic feel. It easily handles complex infographics, web UIs, and even human organ breakdown diagrams. However, multiple tests indicate its knowledge base is stuck in 2025, suggesting it's not a new architecture but a new checkpoint on the same foundation.
Related event: Mysterious OpenAI Image Model 'Mona-lisa-1' Spotted on LMArena(4 posts)→
More from Models
- Opus 5.5 turns heads with surprisingly polished vertical video demo — FinanceYF5 · 2026-10-16
- Astra 6.1 may arrive before end of month, reads dev's 'we are cooking' tease — haider1 · 2026-10-16
- Open-source OCR model indra-ocr trends on Hugging Face with CPU support — datalab-to · 2026-10-16
- Xiaohongshu's Vela 35B turns anonymized user behavior into supervision, gains +11.5 on VelaBench — AdinaYakup · 2026-10-16
- KOL: No better model than Anthropic's Opus right now, its magic is back — kimmonismus · 2026-10-16
- Users blast Gemini in Chrome's 'draconian' usage caps: memory costs 2-4% per use — North-American · 2026-10-16