OpenAI's GPT-Image-2.5 Sweeps All Three LMArena Image Leaderboards, +81 Pts in Multi-Image Edit
airesearch12 · x · 2026-09-09
OpenAI shipped ChatGPT Images 2.5 in two flavors, and both now top LMArena: GPT-Image-2.5-Sunburst takes #1 and Flare #2 across the Text-to-Image, Single-Image Edit, and Multi-Image Edit Arenas.
Gains over GPT-Image-2 (medium) are substantial (Sunburst | Flare): +40 | +18 pts on text-to-image, +59 | +30 on single-image edit, and +81 | +47 on multi-image edit. Sunburst targets the highest generation quality while Flare keeps a big speed advantage over the previous model.
Official highlights: faster generation, higher fidelity for natural, recognizable images, consistent details across multiple edits, and comment-based edits that change only what you specify.
Related event: GPT-Image-2.5 Variants Sweep Major Image Arena Leaderboards(6 posts)→
More from Multimodal
- Matt Turck generates an Anthropic S-1 explainer video with a single unedited prompt — mattturck · 2026-10-27
- Local text-to-video trailer: Maestro on a 3080Ti plus Premiere Pro Beta's AI Assistant auto-editing — cocktailpeanut · 2026-10-27
- Gen games don't need to be realtime — turn-based interactivity works, devs argue — djcows · 2026-10-27
- Lip sync face-off: Omniflash vs Minimax H3 on The Everlight — Uszko_Visuals · 2026-10-27
- Short film 'Odissey of Aeons' made with MiniMax H3 video generation — Musikalandia · 2026-10-27
- Remiqora Video: open-source local studio turns one idea into 4K chained AI videos — inikolax · 2026-10-27