Rankings

Arena.ai leaderboards: Elo op basis van blind head-to-head stemmen. Kies een categorie.

Image Edit

Beeldbewerking en inpainting.

28 mei 2026, 19:45

47 modellen

#	Model	Elo	±	Stemmen
	gpt-image-2 (medium) OpenAI · Proprietary ±5 · 62.2k stemmen	1467	±5	62.2k
	chatgpt-image-latest-high-fidelity (20251216) OpenAI · Proprietary ±4 · 376.3k stemmen	1392	±4	376.3k
	grok-imagine-image-quality (20260519) xAI · Proprietary ±8 · 6.1k stemmen	1388	±8	6.1k
4	gemini-3-pro-image-preview-2k (nano-banana-pro) Google · Proprietary ±3 · 366.7k stemmen	1387	±3	366.7k
5	gemini-3.1-flash-image-preview (nano-banana-2) [web-search] Google · Proprietary ±4 · 176.8k stemmen	1387	±4	176.8k
6	gemini-3-pro-image-preview (nano-banana-pro) Google · Proprietary ±3 · 518.3k stemmen	1387	±3	518.3k
7	gpt-image-1.5-high-fidelity OpenAI · Proprietary ±3 · 396.1k stemmen	1374	±3	396.1k
8	grok-imagine-image-quality xAI · Proprietary ±6 · 16.7k stemmen	1359	±6	16.7k
9	uni-1.1-max Luma AI · Proprietary ±5 · 20.0k stemmen	1339	±5	20.0k
10	grok-imagine-image xAI · Proprietary ±3 · 274.2k stemmen	1332	±3	274.2k
11	uni-1.1 Luma AI · Proprietary ±5 · 22.2k stemmen	1315	±5	22.2k
12	wan2.7-image-pro Alibaba · Proprietary ±4 · 40.2k stemmen	1303	±4	40.2k
13	seedream-4.5 Bytedance · Proprietary ±3 · 718.2k stemmen	1303	±3	718.2k
14	hunyuan-image-3.0-instruct Tencent · Open weights ±4 · 211.4k stemmen	1302	±4	211.4k
15	wan2.7-image Alibaba · Proprietary ±4 · 40.9k stemmen	1302	±4	40.9k

Elo-score op basis van blind head-to-head stemmen. Hoger is beter. ± is het 95% betrouwbaarheidsinterval. Zelfde formaat als Arena.ai.