Image Edit · Agentic

Best agentic AI image editors: AI Image Arena ranked

Nov 17, 2026 · 70,175 votes · 25 models

GPT-Image-2.5 Sunburst by OpenAI leads with 1535 points, ahead of GPT-Image-2.5 Flare (1485) and GPT-Image-2.6 Flare (Medium) (1473).

Lab
License
RankModelScoreSpreadVotes
1
GPT-Image-2.5 SunburstOpenAI · Proprietary
1535 ±12
18,274
2
GPT-Image-2.5 FlareOpenAI · Proprietary
1485 ±11
2-47,932
3
GPT-Image-2.6 Flare (Medium)OpenAI · Proprietary
1473 ±23
2-51,169
4
GPT-Image-2.6 Sunburst (Medium)OpenAI · Proprietary
1465 ±23
2-61,201
5
GPT-Image-2 (Medium)OpenAI · Proprietary
1456 ±11
3-57,428
6
Grok Imagine Image 2.0xAI · Proprietary
1427 ±17
5-111,897
7
MAI-Image-2.6Microsoft AI · Proprietary
1417 ±13
6-113,488
8
Seedream 5.0 ProByteDance · Proprietary
1411 ±11
6-118,308
9
1411 ±10
6-118,786
10
1406 ±12
6-124,668
11
1405 ±12
6-125,226
12
Muse ImageMeta · Proprietary
1386 ±11
10-156,808
13
1375 ±12
12-165,092
14
GPT-Image-1.5 (High Fidelity)OpenAI · Proprietary
1359 ±12
13-164,751
15
Qwen-Image-2.1Alibaba · qwen-research
1359 ±16
12-162,033
16
MiniMax H3-ImageMiniMax · minimax-h3-image-community-license-agreement
1349 ±36
12-18353
17
Grok Imagine ImagexAI · Proprietary
1316 ±10
16-1911,706
18
Ideogram 4.5Ideogram · Proprietary
1307 ±10
16-218,469
19
UNI-1.1Luma AI · Proprietary
1299 ±13
17-224,417
20
1287 ±10
18-2210,730
21
Seedream 5.0 LiteByteDance · Proprietary
1286 ±11
18-227,829
22
Seedream 4.5ByteDance · Proprietary
1285 ±10
19-2210,100
23
Wan 2.5 PreviewAlibaba · Proprietary
1218 ±33
23-25506
24
FLUX.2 [pro]Black Forest Labs · Proprietary
1211 ±13
23-254,455
25
Wan 2.6 ImageAlibaba · Proprietary
1194 ±13
23-254,724

Score: Bradley-Terry rating - the bar shows it on one scale for the whole board, the thin line is the 95% confidence interval (± half of it next to the number). Spread: every rank the model could hold given that interval - models whose lines overlap are statistically tied.

Data: LMArena (lmarena-ai/leaderboard-dataset), CC BY 4.0. Published Nov 17, 2026. Flashlook mirrors the rankings unchanged - about the data.

Confidence intervals on model strength

Dot = score, line = 95% interval. Hover a dot for the numbers.

GPT-Image-2.5 Sunburst
GPT-Image-2.5 Flare
GPT-Image-2.6 Flare (Medium)
GPT-Image-2.6 Sunburst (Medium)
GPT-Image-2 (Medium)
Grok Imagine Image 2.0
MAI-Image-2.6
Seedream 5.0 Pro
Grok Imagine Image 2.0 (20260801)
ChatGPT Image Latest (High Fidelity, 20251216)
Gemini 3 Pro Image (nano-banana-pro, 2K)
Muse Image
Gemini 3.1 Flash Image (nano-banana-2, Web Search)
GPT-Image-1.5 (High Fidelity)
Qwen-Image-2.1
MiniMax H3-Image
Grok Imagine Image
Ideogram 4.5
UNI-1.1
Gemini 2.5 Flash Image Preview (nano-banana)
Seedream 5.0 Lite
Seedream 4.5
Wan 2.5 Preview
FLUX.2 [pro]
Wan 2.6 Image
12001300140015001600