1
O
gpt-image-2 (medium)
gpt-image-2 (medium)Openai
100.0
4.6K
-
¥36.4 / ¥233Input/Output
Image · Text-to-Image · Art Leaderboard
Ranking for Text-to-Image / Art, based on public preference data.
Art model ranking guide
Ranking for Text-to-Image / Art, based on public preference data.
gpt-image-2 (medium)gemini-3.1-flash-image-preview (nano-banana-2) [web-search]mai-image-2.5-previewgpt-image-1.5-high-fidelitygemini-3-pro-image-preview-2k (nano-banana-pro)
2
G
gemini-3.1-flash-image-preview (nano-banana-2) [web-search]
gemini-3.1-flash-image-preview (nano-banana-2) [web-search]Google
98.4
9.2K
131K
¥3.6 / ¥21.6Input/Output
3
M
mai-image-2.5-preview
mai-image-2.5-previewMicrosoft Ai
96.8
800
32K
¥36 / ¥338Input/Output
4
Ogpt-image-1.5-high-fidelity
gpt-image-1.5-high-fidelityOpenai
95.2
15.7K
1M
¥36 / ¥216Input/Output
5
Ggemini-3-pro-image-preview-2k (nano-banana-pro)
gemini-3-pro-image-preview-2k (nano-banana-pro)Google
93.7
15.4K
1.05M
¥14.4 / ¥86.4Input/Output
6
Ggemini-3-pro-image-preview (nano-banana-pro)
gemini-3-pro-image-preview (nano-banana-pro)Google
92.1
12.6K
1.05M
¥14.4 / ¥86.4Input/Output
7
X
grok-imagine-image-quality
grok-imagine-image-qualityXai
90.5
2.5K
1M
¥9 / ¥18Input/Output
8
L
uni-1.1-max
uni-1.1-maxLuma Ai
88.9
1.3K
-
-
9
Luni-1.1
uni-1.1Luma Ai
87.3
1.4K
-
-
10
A
qwen-image-2.0-pro-2026-04-22
qwen-image-2.0-pro-2026-04-22Alibaba
85.7
465
8.19K
¥0 / ¥0Input/Output
11
Xgrok-imagine-image
grok-imagine-imageXai
84.1
21.2K
1M
¥9 / ¥18Input/Output
12
R
recraft-v4.1-utility-pro
recraft-v4.1-utility-proRecraft
82.5
385
-
-
13
Mmai-image-2
mai-image-2Microsoft Ai
81.0
5.9K
32K
¥36 / ¥338Input/Output
14
BF
flux-2-max
flux-2-maxBfl
79.4
15.7K
-
-
15
Xgrok-imagine-image-pro
grok-imagine-image-proXai
77.8
12.7K
1M
¥9 / ¥18Input/Output
16
B
seedream-4-2k
seedream-4-2kBytedance
76.2
1.7K
-
-
17
BFflux-2-pro
flux-2-proBfl
74.6
20.9K
-
-
18
R
reve-v1.5
reve-v1.5Reve
73.0
2.2K
-
-
19
Awan2.6-t2i
wan2.6-t2iAlibaba
71.4
18.1K
-
-
20
Rrecraft-v4.1-pro
recraft-v4.1-proRecraft
69.8
411
-
-
21
BFflux-2-dev
flux-2-devBfl
68.3
8.7K
-
-
22
BFflux-2-flex
flux-2-flexBfl
66.7
20.8K
-
-
23
TE
hunyuan-image-3.0
hunyuan-image-3.0Tencent
65.1
25.7K
-
-
24
Bseedream-4.5
seedream-4.5Bytedance
63.5
25.2K
-
-
25
Ggemini-2.5-flash-image-preview (nano-banana)
gemini-2.5-flash-image-preview (nano-banana)Google
61.9
101.7K
1.05M
¥2.16 / ¥18Input/Output
26
Aqwen-image-2512
qwen-image-2512Alibaba
60.3
10.5K
8.19K
¥3.6 / ¥14.4Input/Output
27
Gimagen-ultra-4.0-generate-001
imagen-ultra-4.0-generate-001Google
58.7
46.5K
-
-
28
Bseedream-5.0-lite
seedream-5.0-liteBytedance
57.1
8.8K
-
-
29
Bseedream-4-fal
seedream-4-falBytedance
55.6
1.4K
-
-
30
Awan2.5-t2i-preview
wan2.5-t2i-previewAlibaba
54.0
27.7K
-
-
31
Ogpt-image-1
gpt-image-1Openai
52.4
33.8K
-
¥36 / ¥288Input/Output
32
HI
hidream-o1-image
hidream-o1-imageHidream
50.8
779
200K
¥108 / ¥432Input/Output
33
Rrecraft-v4
recraft-v4Recraft
49.2
8.7K
-
-
34
Gimagen-4.0-generate-001
imagen-4.0-generate-001Google
47.6
63.7K
-
-
35
Ogpt-image-1-mini
gpt-image-1-miniOpenai
46.0
21.7K
1M
¥36 / ¥216Input/Output
36
Bseedream-4-high-res-fal
seedream-4-high-res-falBytedance
44.4
23K
-
-
37
Aqwen-image-2.0-2026-03-03
qwen-image-2.0-2026-03-03Alibaba
42.9
6.1K
8.19K
¥0 / ¥0Input/Output
38
Mmai-image-1
mai-image-1Microsoft Ai
41.3
14.4K
32K
¥36 / ¥338Input/Output
39
Bseedream-3
seedream-3Bytedance
39.7
4.7K
-
-
40
BFflux-1-kontext-max
flux-1-kontext-maxBfl
38.1
7.3K
-
-
41
Az-image-turbo
z-image-turboAlibaba
36.5
2.6K
-
-
42
BFflux-2-klein-9b
flux-2-klein-9bBfl
34.9
17.7K
-
-
43
Awan2.7-image-pro
wan2.7-image-proAlibaba
33.3
2.9K
8.19K
¥0 / ¥0Input/Output
44
Awan2.7-image
wan2.7-imageAlibaba
31.7
2.9K
8.19K
¥0 / ¥0Input/Output
45
BFflux-1-kontext-pro
flux-1-kontext-proBfl
30.2
39.6K
-
-
46
Gimagen-3.0-generate-002
imagen-3.0-generate-002Google
28.6
59.7K
-
-
47
Aqwen-image
qwen-imageAlibaba
27.0
8.7K
8.19K
¥3.6 / ¥14.4Input/Output
48
Aqwen-image-prompt-extend
qwen-image-prompt-extendAlibaba
25.4
85.3K
8.19K
¥3.6 / ¥14.4Input/Output
49
Lphoton
photonLuma Ai
23.8
20.7K
-
-
50
BFflux-1.1-pro
flux-1.1-proBfl
22.2
18.3K
-
-
51
UNp-image
-
20.6
12.4K
-
-
52
I
ideogram-v3-quality
ideogram-v3-qualityIdeogram
19.0
16.8K
-
-
53
LA
lucid-origin
lucid-originLeonardo Ai
17.5
34.3K
-
-
54
BFflux-2-klein-4b
flux-2-klein-4bBfl
15.9
18.1K
-
-
55
R
runway-gen4
runway-gen4Runway
14.3
5.8K
-
-
56
Iideogram-v2
ideogram-v2Ideogram
12.7
18.8K
-
-
57
Z
glm-image
glm-imageZai
11.1
712
200K
¥5.4 / ¥18.7Input/Output
58
Odall-e-3
dall-e-3Openai
9.5
38.9K
-
-
59
UNstable-diffusion-v35-large
-
7.9
5.3K
0.26K
¥0.58 / ¥0Input/Output
60
Rrecraft-v3
recraft-v3Recraft
6.3
35K
-
-
61
BFflux-1-dev-fp8
flux-1-dev-fp8Bfl
4.8
12.8K
-
-
62
Ggemini-2.0-flash-preview-image-generation
gemini-2.0-flash-preview-image-generationGoogle
3.2
30.6K
1.05M
¥1.08 / ¥4.32Input/Output
63
BFflux-1-kontext-dev
flux-1-kontext-devBfl
1.6
25.9K
-
-
64
Bbagel
bagelBytedance
0.0
1.4K
-
-
gpt-image-2 (medium) why it ranks first
gpt-image-2 (medium) ranks first with a percent score of 100.0 and 4.6K 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
艺术排行榜看什么指标？
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。
艺术模型应该怎么选？
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。