1
O
gpt-image-2 (medium)
gpt-image-2 (medium)Openai
100.0
15.6K
-
¥36.4 / ¥233Input/Output
Image · Text-to-Image · Text Rendering Leaderboard
Ranking for Text-to-Image / Text Rendering, based on public preference data.
Text Rendering model ranking guide
Ranking for Text-to-Image / Text Rendering, 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
26.3K
131K
¥3.6 / ¥21.6Input/Output
3
M
mai-image-2.5-preview
mai-image-2.5-previewMicrosoft Ai
96.8
1.9K
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
36.8K
1.05M
¥14.4 / ¥86.4Input/Output
5
Ogpt-image-1.5-high-fidelity
gpt-image-1.5-high-fidelityOpenai
93.7
41.3K
1M
¥36 / ¥216Input/Output
6
X
grok-imagine-image-quality
grok-imagine-image-qualityXai
92.1
6.6K
1M
¥9 / ¥18Input/Output
7
Ggemini-3-pro-image-preview (nano-banana-pro)
gemini-3-pro-image-preview (nano-banana-pro)Google
90.5
24.6K
1.05M
¥14.4 / ¥86.4Input/Output
8
L
uni-1.1-max
uni-1.1-maxLuma Ai
88.9
3.1K
-
-
9
Luni-1.1
uni-1.1Luma Ai
87.3
3.5K
-
-
10
R
reve-v1.5
reve-v1.5Reve
85.7
5.1K
-
-
11
Xgrok-imagine-image
grok-imagine-imageXai
84.1
61.4K
1M
¥9 / ¥18Input/Output
12
Xgrok-imagine-image-pro
grok-imagine-image-proXai
82.5
32.7K
1M
¥9 / ¥18Input/Output
13
Mmai-image-2
mai-image-2Microsoft Ai
81.0
18.1K
32K
¥36 / ¥338Input/Output
14
A
qwen-image-2.0-pro-2026-04-22
qwen-image-2.0-pro-2026-04-22Alibaba
79.4
2.5K
8.19K
¥0 / ¥0Input/Output
15
BF
flux-2-flex
flux-2-flexBfl
77.8
47.6K
-
-
16
BFflux-2-max
flux-2-maxBfl
76.2
38.1K
-
-
17
R
recraft-v4.1-utility-pro
recraft-v4.1-utility-proRecraft
74.6
920
-
-
18
BFflux-2-dev
flux-2-devBfl
73.0
18K
-
-
19
BFflux-2-pro
flux-2-proBfl
71.4
49.4K
-
-
20
Rrecraft-v4.1-pro
recraft-v4.1-proRecraft
69.8
914
-
-
21
Ggemini-2.5-flash-image-preview (nano-banana)
gemini-2.5-flash-image-preview (nano-banana)Google
68.3
202.7K
1.05M
¥2.16 / ¥18Input/Output
22
TE
hunyuan-image-3.0
hunyuan-image-3.0Tencent
66.7
50.3K
-
-
23
Gimagen-ultra-4.0-generate-001
imagen-ultra-4.0-generate-001Google
65.1
90.2K
-
-
24
Awan2.6-t2i
wan2.6-t2iAlibaba
63.5
53.5K
-
-
25
B
seedream-4-2k
seedream-4-2kBytedance
61.9
3.1K
-
-
26
Awan2.5-t2i-preview
wan2.5-t2i-previewAlibaba
60.3
63K
-
-
27
HI
hidream-o1-image
hidream-o1-imageHidream
58.7
1.7K
200K
¥108 / ¥432Input/Output
28
Bseedream-4.5
seedream-4.5Bytedance
57.1
65.2K
-
-
29
Rrecraft-v4
recraft-v4Recraft
55.6
25.3K
-
-
30
Bseedream-5.0-lite
seedream-5.0-liteBytedance
54.0
24.8K
-
-
31
Aqwen-image-2512
qwen-image-2512Alibaba
52.4
21.9K
8.19K
¥3.6 / ¥14.4Input/Output
32
Bseedream-4-fal
seedream-4-falBytedance
50.8
2.7K
-
-
33
Gimagen-4.0-generate-001
imagen-4.0-generate-001Google
49.2
133.2K
-
-
34
Aqwen-image-2.0-2026-03-03
qwen-image-2.0-2026-03-03Alibaba
47.6
20.2K
8.19K
¥0 / ¥0Input/Output
35
Awan2.7-image-pro
wan2.7-image-proAlibaba
46.0
11.9K
8.19K
¥0 / ¥0Input/Output
36
Ogpt-image-1
gpt-image-1Openai
44.4
71K
-
¥36 / ¥288Input/Output
37
Awan2.7-image
wan2.7-imageAlibaba
42.9
11.9K
8.19K
¥0 / ¥0Input/Output
38
Bseedream-4-high-res-fal
seedream-4-high-res-falBytedance
41.3
53.2K
-
-
39
Ogpt-image-1-mini
gpt-image-1-miniOpenai
39.7
53.4K
1M
¥36 / ¥216Input/Output
40
Aqwen-image-prompt-extend
qwen-image-prompt-extendAlibaba
38.1
180.1K
8.19K
¥3.6 / ¥14.4Input/Output
41
BFflux-1-kontext-max
flux-1-kontext-maxBfl
36.5
15.8K
-
-
42
I
ideogram-v3-quality
ideogram-v3-qualityIdeogram
34.9
32.5K
-
-
43
Mmai-image-1
mai-image-1Microsoft Ai
33.3
30.3K
32K
¥36 / ¥338Input/Output
44
Az-image-turbo
z-image-turboAlibaba
31.7
5.6K
-
-
45
BFflux-2-klein-9b
flux-2-klein-9bBfl
30.2
48.3K
-
-
46
BFflux-1-kontext-pro
flux-1-kontext-proBfl
28.6
78.3K
-
-
47
Bseedream-3
seedream-3Bytedance
27.0
9K
-
-
48
Aqwen-image
qwen-imageAlibaba
25.4
15.7K
8.19K
¥3.6 / ¥14.4Input/Output
49
Iideogram-v2
ideogram-v2Ideogram
23.8
10.9K
-
-
50
Gimagen-3.0-generate-002
imagen-3.0-generate-002Google
22.2
76.7K
-
-
51
Lphoton
photonLuma Ai
20.6
33K
-
-
52
Z
glm-image
glm-imageZai
19.0
1.4K
200K
¥5.4 / ¥18.7Input/Output
53
UNp-image
-
17.5
34.3K
-
-
54
R
runway-gen4
runway-gen4Runway
15.9
17.1K
-
-
55
BFflux-2-klein-4b
flux-2-klein-4bBfl
14.3
49.1K
-
-
56
Ggemini-2.0-flash-preview-image-generation
gemini-2.0-flash-preview-image-generationGoogle
12.7
58.8K
1.05M
¥1.08 / ¥4.32Input/Output
57
LA
lucid-origin
lucid-originLeonardo Ai
11.1
67.8K
-
-
58
Rrecraft-v3
recraft-v3Recraft
9.5
42.6K
-
-
59
BFflux-1.1-pro
flux-1.1-proBfl
7.9
10.8K
-
-
60
Odall-e-3
dall-e-3Openai
6.3
49.9K
-
-
61
BFflux-1-dev-fp8
flux-1-dev-fp8Bfl
4.8
6.7K
-
-
62
BFflux-1-kontext-dev
flux-1-kontext-devBfl
3.2
50.2K
-
-
63
UNstable-diffusion-v35-large
-
1.6
3.2K
0.26K
¥0.58 / ¥0Input/Output
64
Bbagel
bagelBytedance
0.0
3.2K
-
-
gpt-image-2 (medium) why it ranks first
gpt-image-2 (medium) ranks first with a percent score of 100.0 and 15.6K 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
文字渲染排行榜看什么指标？
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。
文字渲染模型应该怎么选？
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。