1
O
gpt-image-2 (medium)
gpt-image-2 (medium)Openai
100.0
40.4K
-
¥36.4 / ¥233Input/Output
Image · Text-to-Image · Overall Leaderboard
Ranking for Text-to-Image / Overall, based on public preference data.
Overall model ranking guide
Ranking for Text-to-Image / Overall, based on public preference data.
gpt-image-2 (medium)gemini-3.1-flash-image-preview (nano-banana-2) [web-search]mai-image-2.5-previewgemini-3-pro-image-preview-2k (nano-banana-pro)gpt-image-1.5-high-fidelity
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
70.9K
131K
¥3.6 / ¥21.6Input/Output
3
M
mai-image-2.5-preview
mai-image-2.5-previewMicrosoft Ai
96.8
5.3K
32K
¥36 / ¥338Input/Output
4
Ggemini-3-pro-image-preview-2k (nano-banana-pro)
gemini-3-pro-image-preview-2k (nano-banana-pro)Google
95.2
109.6K
1.05M
¥14.4 / ¥86.4Input/Output
5
Ogpt-image-1.5-high-fidelity
gpt-image-1.5-high-fidelityOpenai
93.7
114.2K
1M
¥36 / ¥216Input/Output
6
Ggemini-3-pro-image-preview (nano-banana-pro)
gemini-3-pro-image-preview (nano-banana-pro)Google
92.1
82.6K
1.05M
¥14.4 / ¥86.4Input/Output
7
X
grok-imagine-image-quality
grok-imagine-image-qualityXai
90.5
19.4K
1M
¥9 / ¥18Input/Output
8
L
uni-1.1-max
uni-1.1-maxLuma Ai
88.9
8.9K
-
-
9
Mmai-image-2
mai-image-2Microsoft Ai
87.3
48.3K
32K
¥36 / ¥338Input/Output
10
Luni-1.1
uni-1.1Luma Ai
85.7
10K
-
-
11
Xgrok-imagine-image
grok-imagine-imageXai
84.1
166.8K
1M
¥9 / ¥18Input/Output
12
R
recraft-v4.1-utility-pro
recraft-v4.1-utility-proRecraft
82.5
2.5K
-
-
13
A
qwen-image-2.0-pro-2026-04-22
qwen-image-2.0-pro-2026-04-22Alibaba
81.0
5.2K
8.19K
¥0 / ¥0Input/Output
14
BF
flux-2-max
flux-2-maxBfl
79.4
111.5K
-
-
15
Xgrok-imagine-image-pro
grok-imagine-image-proXai
77.8
93K
1M
¥9 / ¥18Input/Output
16
R
reve-v1.5
reve-v1.5Reve
76.2
14.9K
-
-
17
BFflux-2-pro
flux-2-proBfl
74.6
147.1K
-
-
18
BFflux-2-flex
flux-2-flexBfl
73.0
143.2K
-
-
19
Ggemini-2.5-flash-image-preview (nano-banana)
gemini-2.5-flash-image-preview (nano-banana)Google
71.4
779.8K
1.05M
¥2.16 / ¥18Input/Output
20
TE
hunyuan-image-3.0
hunyuan-image-3.0Tencent
69.8
172.9K
-
-
21
BFflux-2-dev
flux-2-devBfl
68.3
58K
-
-
22
Gimagen-ultra-4.0-generate-001
imagen-ultra-4.0-generate-001Google
66.7
389.6K
-
-
23
B
seedream-4.5
seedream-4.5Bytedance
65.1
189K
-
-
24
Bseedream-4-2k
seedream-4-2kBytedance
63.5
12.6K
-
-
25
Awan2.6-t2i
wan2.6-t2iAlibaba
61.9
145.8K
-
-
26
Aqwen-image-2512
qwen-image-2512Alibaba
60.3
70K
8.19K
¥3.6 / ¥14.4Input/Output
27
Rrecraft-v4.1-pro
recraft-v4.1-proRecraft
58.7
2.7K
-
-
28
Gimagen-4.0-generate-001
imagen-4.0-generate-001Google
57.1
516.9K
-
-
29
Bseedream-5.0-lite
seedream-5.0-liteBytedance
55.6
68.1K
-
-
30
HI
hidream-o1-image
hidream-o1-imageHidream
54.0
5.1K
200K
¥108 / ¥432Input/Output
31
Bseedream-4-fal
seedream-4-falBytedance
52.4
11.9K
-
-
32
Awan2.5-t2i-preview
wan2.5-t2i-previewAlibaba
50.8
194.4K
-
-
33
Aqwen-image-2.0-2026-03-03
qwen-image-2.0-2026-03-03Alibaba
49.2
53.6K
8.19K
¥0 / ¥0Input/Output
34
Ogpt-image-1
gpt-image-1Openai
47.6
265.5K
-
¥36 / ¥288Input/Output
35
Bseedream-4-high-res-fal
seedream-4-high-res-falBytedance
46.0
169.3K
-
-
36
Rrecraft-v4
recraft-v4Recraft
44.4
69.2K
-
-
37
Ogpt-image-1-mini
gpt-image-1-miniOpenai
42.9
157.8K
1M
¥36 / ¥216Input/Output
38
Awan2.7-image-pro
wan2.7-image-proAlibaba
41.3
28.5K
8.19K
¥0 / ¥0Input/Output
39
Awan2.7-image
wan2.7-imageAlibaba
39.7
28.8K
8.19K
¥0 / ¥0Input/Output
40
Mmai-image-1
mai-image-1Microsoft Ai
38.1
94.5K
32K
¥36 / ¥338Input/Output
41
Az-image-turbo
z-image-turboAlibaba
36.5
18.3K
-
-
42
Bseedream-3
seedream-3Bytedance
34.9
36.9K
-
-
43
BFflux-1-kontext-max
flux-1-kontext-maxBfl
33.3
65.9K
-
-
44
BFflux-2-klein-9b
flux-2-klein-9bBfl
31.7
133.8K
-
-
45
Aqwen-image-prompt-extend
qwen-image-prompt-extendAlibaba
30.2
697.8K
8.19K
¥3.6 / ¥14.4Input/Output
46
BFflux-1-kontext-pro
flux-1-kontext-proBfl
28.6
332.1K
-
-
47
Gimagen-3.0-generate-002
imagen-3.0-generate-002Google
27.0
361.4K
-
-
48
Aqwen-image
qwen-imageAlibaba
25.4
85.1K
8.19K
¥3.6 / ¥14.4Input/Output
49
I
ideogram-v3-quality
ideogram-v3-qualityIdeogram
23.8
115.3K
-
-
50
Lphoton
photonLuma Ai
22.2
127.6K
-
-
51
UNp-image
-
20.6
97.3K
-
-
52
BFflux-2-klein-4b
flux-2-klein-4bBfl
19.0
135.7K
-
-
53
R
runway-gen4
runway-gen4Runway
17.5
46.6K
-
-
54
Rrecraft-v3
recraft-v3Recraft
15.9
192K
-
-
55
BFflux-1.1-pro
flux-1.1-proBfl
14.3
70.5K
-
-
56
LA
lucid-origin
lucid-originLeonardo Ai
12.7
286.6K
-
-
57
Iideogram-v2
ideogram-v2Ideogram
11.1
72.1K
-
-
58
Z
glm-image
glm-imageZai
9.5
4.6K
200K
¥5.4 / ¥18.7Input/Output
59
Ggemini-2.0-flash-preview-image-generation
gemini-2.0-flash-preview-image-generationGoogle
7.9
258.2K
1.05M
¥1.08 / ¥4.32Input/Output
60
BFflux-1-dev-fp8
flux-1-dev-fp8Bfl
6.3
49.2K
-
-
61
Odall-e-3
dall-e-3Openai
4.8
240.1K
-
-
62
BFflux-1-kontext-dev
flux-1-kontext-devBfl
3.2
216.3K
-
-
63
UNstable-diffusion-v35-large
-
1.6
23.4K
0.26K
¥0.58 / ¥0Input/Output
64
Bbagel
bagelBytedance
0.0
12.4K
-
-
gpt-image-2 (medium) why it ranks first
gpt-image-2 (medium) ranks first with a percent score of 100.0 and 40.4K 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
总榜排行榜看什么指标？
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。
总榜模型应该怎么选？
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。