Qwen-Image-2.1 Tops Open Text-to-Image Arena at 1228 pts, Just 11 Behind GPT-Image

arena · x · 2026-09-22

LMArena announced that Qwen-Image-2.1 took the #1 spot among open models in the Text-to-Image Arena with 1228 points. It ranks #17 overall, just 4 points behind Gemini-3-pro-image-preview (nano-banana-pro) at #16 and 11 points behind GPT-Image-1.5-high-fidelity at #15 — open-source image generation is now within striking distance of the closed-source leaders.

Original post →

More from Multimodal

Multimodal channel →