1
O
gpt-image-2 (medium)
gpt-image-2 (medium)Openai
100.0
77.2K
-
¥36.4 / ¥233Input/Output
Image · Image Edit · Single-Image Edit Leaderboard
Ranking for Image Edit / Single-Image Edit, based on public preference data.
Single-Image Edit model ranking guide
Ranking for Image Edit / Single-Image Edit, based on public preference data.
gpt-image-2 (medium)mai-image-2.5chatgpt-image-latest-high-fidelity (20251216)grok-imagine-image-quality (20260519)gemini-3.1-flash-image-preview (nano-banana-2) [web-search]
2
M
mai-image-2.5
mai-image-2.5Microsoft Ai
97.9
5.6K
32K
¥36 / ¥338Input/Output
3
Ochatgpt-image-latest-high-fidelity (20251216)
chatgpt-image-latest-high-fidelity (20251216)Openai
95.7
391.1K
1M
¥36 / ¥216Input/Output
4
X
grok-imagine-image-quality (20260519)
grok-imagine-image-quality (20260519)Xai
93.6
8K
1M
¥9 / ¥18Input/Output
5
G
gemini-3.1-flash-image-preview (nano-banana-2) [web-search]
gemini-3.1-flash-image-preview (nano-banana-2) [web-search]Google
91.5
193.7K
131K
¥3.6 / ¥21.6Input/Output
6
Ggemini-3-pro-image-preview-2k (nano-banana-pro)
gemini-3-pro-image-preview-2k (nano-banana-pro)Google
89.4
383.6K
1.05M
¥14.4 / ¥86.4Input/Output
7
Ggemini-3-pro-image-preview (nano-banana-pro)
gemini-3-pro-image-preview (nano-banana-pro)Google
87.2
518.4K
1.05M
¥14.4 / ¥86.4Input/Output
8
Ogpt-image-1.5-high-fidelity
gpt-image-1.5-high-fidelityOpenai
85.1
411.2K
1M
¥36 / ¥216Input/Output
9
Xgrok-imagine-image-quality
grok-imagine-image-qualityXai
83.0
32.6K
1M
¥9 / ¥18Input/Output
10
L
uni-1.1-max
uni-1.1-maxLuma Ai
80.9
31.8K
-
-
11
Xgrok-imagine-image
grok-imagine-imageXai
78.7
312.8K
1M
¥9 / ¥18Input/Output
12
Luni-1.1
uni-1.1Luma Ai
76.6
35.4K
-
-
13
A
wan2.7-image-pro
wan2.7-image-proAlibaba
74.5
40.8K
8.19K
¥0 / ¥0Input/Output
14
B
seedream-4.5
seedream-4.5Bytedance
72.3
748.5K
-
-
15
Awan2.7-image
wan2.7-imageAlibaba
70.2
41.6K
8.19K
¥0 / ¥0Input/Output
16
TE
hunyuan-image-3.0-instruct
hunyuan-image-3.0-instructTencent
68.1
225.4K
-
-
17
Ggemini-2.5-flash-image-preview (nano-banana)
gemini-2.5-flash-image-preview (nano-banana)Google
66.0
10849.5K
1.05M
¥2.16 / ¥18Input/Output
18
Bseedream-5.0-lite
seedream-5.0-liteBytedance
63.8
193.9K
-
-
19
Aqwen-image-2.0-pro-2026-04-22
qwen-image-2.0-pro-2026-04-22Alibaba
61.7
7.1K
8.19K
¥0 / ¥0Input/Output
20
Bseedream-4-2k
seedream-4-2kBytedance
59.6
213K
-
-
21
BF
flux-2-max
flux-2-maxBfl
57.4
340.1K
-
-
22
R
reve-v1.1
reve-v1.1Reve
55.3
611.9K
-
-
23
Aqwen-image-2.0-2026-03-03
qwen-image-2.0-2026-03-03Alibaba
53.2
129.4K
8.19K
¥0 / ¥0Input/Output
24
K
kling-image-o1
kling-image-o1Kling
51.1
122.5K
200K
¥108 / ¥432Input/Output
25
BFflux-2-pro
flux-2-proBfl
48.9
356.6K
-
-
26
Aqwen-image-edit
qwen-image-editAlibaba
46.8
1981.3K
-
¥0 / ¥0Input/Output
27
Rreve-v1
reve-v1Reve
44.7
380.9K
-
-
28
Aqwen-image-edit-2511
qwen-image-edit-2511Alibaba
42.6
329.9K
8.19K
¥3.6 / ¥14.4Input/Output
29
Awan2.6-image
wan2.6-imageAlibaba
40.4
393.9K
-
-
30
BFflux-2-flex
flux-2-flexBfl
38.3
402.3K
-
-
31
BFflux-2-klein-9b
flux-2-klein-9bBfl
36.2
485K
-
-
32
BFflux-2-dev
flux-2-devBfl
34.0
168.2K
-
-
33
Bseedream-4-high-res-fal
seedream-4-high-res-falBytedance
31.9
1171.4K
-
-
34
Bseedream-4-fal
seedream-4-falBytedance
29.8
153.9K
-
-
35
UNp-image-edit
-
27.7
322.8K
-
¥0 / ¥0Input/Output
36
Rreve-v1.1-fast
reve-v1.1-fastReve
25.5
515.4K
-
-
37
Rreve-edit-fast
reve-edit-fastReve
23.4
221.3K
-
-
38
BFflux-2-klein-4b
flux-2-klein-4bBfl
21.3
485.5K
-
-
39
Awan2.5-i2i-preview
wan2.5-i2i-previewAlibaba
19.1
368K
-
-
40
BFflux-1-kontext-max
flux-1-kontext-maxBfl
17.0
391.7K
-
-
41
BFflux-1-kontext-pro
flux-1-kontext-proBfl
14.9
6424K
-
-
42
BFflux-1-kontext-dev
flux-1-kontext-devBfl
12.8
3652.1K
-
-
43
Bseededit-3.0
seededit-3.0Bytedance
10.6
4950.1K
-
-
44
Ogpt-image-1
gpt-image-1Openai
8.5
2861.2K
-
¥36 / ¥288Input/Output
45
Ogpt-image-1-mini
gpt-image-1-miniOpenai
6.4
642.2K
1M
¥36 / ¥216Input/Output
46
Ggemini-2.0-flash-preview-image-generation
gemini-2.0-flash-preview-image-generationGoogle
4.3
4965.7K
1.05M
¥1.08 / ¥4.32Input/Output
47
Bbagel
bagelBytedance
2.1
13.6K
-
-
48
ST
step1x-edit
step1x-editStepfun
0.0
155.7K
-
-
gpt-image-2 (medium) why it ranks first
gpt-image-2 (medium) ranks first with a percent score of 100.0 and 77.2K samples. Use it as the first option for this leaderboard, then compare price, context and availability.
Do not only look at rank #1
Start with the leaderboard closest to your task. Compare the top models by score and sample size, then check price, context length, open or closed access, and provider availability.
Compare adjacent capabilities
FAQ
单图片编辑排行榜看什么指标？
主要看排名、百分制分数、样本量和来源。分数用于快速比较同一榜单内模型表现，样本量用于判断结果稳定性。
为什么不同榜单不能直接混合成总分？
不同榜单的任务、样本和评测口径不同，模力榜默认只在同一榜单内排序，避免把写作、代码、图像等能力强行合并。
单图片编辑模型应该怎么选？
优先看与你任务最接近的榜单，再结合价格、上下文长度、开源闭源和厂商可用性。排名靠前不代表适合所有预算和部署方式。
榜单多久更新？
页面展示的是最新成功采集的公开榜单数据。当前优先使用 LMArena leaderboard dataset，并在页面来源中保留原始链接。