Skip to content

AI Models with Vision

314 multimodal AI models that support image input and visual understanding, ranked by composite score. These models can analyze images, screenshots, diagrams, and documents alongside text prompts.

Vision Models

314

Of All Models

66%

Providers

42

Avg Score

62

Vision Model Rankings

All 314 models with vision capability, sorted by composite score. Score is computed from capabilities, pricing, context window, recency, output capacity, and versatility.

#ModelScore
1GPT-5.5 ProOpenAI90
2GPT-5.4 ProOpenAI88.7
3GPT-5.5 Pro (batch)OpenAI87.5
4GPT-5.4 Pro (batch)OpenAI86.2
5GPT-5.2 ProOpenAI85.3
6GPT-5 ProOpenAI83.6
7GPT-5.2 Pro (batch)OpenAI81.3
8GPT Astra Latest~openai78.1
9GPT-6 AstraOpenAI78.1
10GPT-6 Astra ProOpenAI78.1
11Claude Fable 5.1Anthropic78
12Claude Fable 5Anthropic78
13Claude Fable 5.2Anthropic75.5
14Claude Fable Latest~anthropic75.5
15Muse Wondermeta75.3
16o3 ProOpenAI74.5
17GPT-5 Pro (batch)OpenAI73.6
18Fugu Ultra v2sakana73
19Gemini 4 CarbonGoogle72.8
20Gemini 4 ArgonGoogle72.8
21GPT-5.5OpenAI72.5
22Gemini Pro Latest~google72.3
23GPT-6 Astra (batch)OpenAI71.8
24GPT-6 Astra Pro (batch)OpenAI71.8
25Claude Fable 5.1 (batch)Anthropic71.8
26Claude Opus 5Anthropic71.8
27Claude Fable 5 (batch)Anthropic71.8
28Claude Opus 4.8Anthropic71.8
29Gemini 4 Carbon (batch)Google71.6
30Gemini 4 Argon (batch)Google71.6
31Fugu Ultrasakana71.4
32Claude Opus 4.7Anthropic71
33Gemini 3.5 FlashGoogle70.7
34GPT-5.6 Sol ProOpenAI70.6
35GPT-5.6 SolOpenAI70.6
36Claude Fable 5.2 (batch)Anthropic70.5
37Claude Opus 5.5Anthropic70.5
38Muse Embermeta70.4
39Claude Opus 4.1Anthropic70.4
40Claude Opus Latest~anthropic69.9
41Muse Spark 1.3meta69.7
42Muse Spark 1.2meta69.7
43Muse Spark 1.1meta69.7
44Gemini 3.5 Flash (batch)Google69.6
45Nemotron 3.5 Super VL (free)NVIDIA69.5
46Gemini 3.8 FlashGoogle69.5
47Gemini 3.7 FlashGoogle69.4
48Gemini 3.6 FlashGoogle69.4
49Gemini 3.1 Pro Preview Custom ToolsGoogle69.3
50Gemini 3.5 Flash LiteGoogle69.1
51Nano Banana Pro (Gemini 3 Pro Image)Google69.1
52Gemini 3.1 Pro PreviewGoogle69.1
53Claude Opus 4.6Anthropic69.1
54GPT-5.4 Image 2OpenAI69
55Gemini 3.8 Flash (batch)Google68.9
56Gemini 3.7 Flash (batch)Google68.9
57Gemini 3.6 Flash (batch)Google68.9
58Gemini Flash Latest~google68.9
59Gemini 3.5 Flash Lite (batch)Google68.8
60GPT-5.5 (batch)OpenAI68.8
61Muse Spark 1.3 Contributormeta68.7
62Muse Spark 1.2 Contributormeta68.7
63Claude Opus 5 (batch)Anthropic68.7
64Claude Opus 4.8 (batch)Anthropic68.7
65GPT-5.6 Terra ProOpenAI68.6
66GPT-5.6 TerraOpenAI68.6
67Gemini 3.1 Flash LiteGoogle68.6
68Gemini 3.1 Flash Lite (batch)Google68.4
69GPT Chat LatestOpenAI68.3
70GPT-6.1 Sol ProOpenAI68.1
71GPT-6.1 SolOpenAI68.1
72GPT-6 Sol ProOpenAI68.1
73GPT-6 SolOpenAI68.1
74GPT Sol Latest~openai68.1
75GPT-5.6 Sol Pro (batch)OpenAI68.1
76GPT-5.6 Sol (batch)OpenAI68.1
77Claude Sonnet 5.5Anthropic68
78Claude Opus 5.5 (batch)Anthropic68
79Dots3-Note Preview (free)dots-studio68
80Claude Sonnet 5Anthropic68
81Claude Opus 4.7 (batch)Anthropic67.9
82Nano Banana 2.1Google67.6
83Claude Sonnet Latest~anthropic67.6
84Gemini 3.1 Pro Preview (batch)Google67.6
85Grok 4.20xAI67.5
86Kimi K3Moonshot AI67.4
87GPT-5.4OpenAI67.4
88Grok 4.7xAI67.2
89Grok 4.6xAI67.2
90Grok 4.5xAI67.2
91Grok Latest~x-ai67.2
92GPT-5.6 Terra Pro (batch)OpenAI67.1
93GPT-5.6 Terra (batch)OpenAI67.1
94Grok 4.3xAI67.1
95Fugu Maxsakana67
96Grok 4.3 (batch)xAI67
97Muse Spark Openmeta66.9
98Grok 4.7 (batch)xAI66.9
99Grok 4.6 (batch)xAI66.9
100Claude Sonnet 4.6Anthropic66.9
101GPT-6.1 Terra ProOpenAI66.8
102GPT-6.1 TerraOpenAI66.8
103GPT-6.1 Sol Pro (batch)OpenAI66.8
104GPT-6.1 Sol (batch)OpenAI66.8
105Claude Sonnet 5.5 (batch)Anthropic66.8
106GPT-6 Sol Pro (batch)OpenAI66.8
107GPT-6 Sol (batch)OpenAI66.8
108GPT Terra Latest~openai66.8
109Claude Sonnet 5 (batch)Anthropic66.8
110Gemini 3.1 Flash Lite PreviewGoogle66.8
111GPT-6.1 Terra Pro (batch)OpenAI66.2
112GPT-6.1 Terra (batch)OpenAI66.2
113Gemma 4 26B A4B (free)Google66
114Gemma 4 31B (free)Google66
115Kimi K3.1 ProMoonshot AI65.9
116MiMo-V2.6-Pro-UltraSpeedXiaomi65.9
117GPT-5.6 Luna ProOpenAI65.9
118GPT-5.6 LunaOpenAI65.9
119GPT-5.3-CodexOpenAI65.9
120Claude Opus 4.6 (batch)Anthropic65.9
121Claude Haiku 5.5Anthropic65.7
122GPT-6 Luna ProOpenAI65.7
123GPT-6 Luna Pro (batch)OpenAI65.7
124GPT-6 LunaOpenAI65.7
125GPT-6 Luna (batch)OpenAI65.7
126GPT Luna Latest~openai65.7
127GPT-5.6 Luna Pro (batch)OpenAI65.7
128GPT-5.6 Luna (batch)OpenAI65.7
129Kimi Latest~moonshotai65.7
130Claude Haiku 5.5 (batch)Anthropic65.6
131Ember-1fireworks65.5
132GPT-5.4 (batch)OpenAI65.5
133Nemotron 3 Nano Omni (free)NVIDIA65.2
134Claude Haiku Latest~anthropic65.2
135GPT Mini Latest~openai65.2
136Gemini 3 Flash PreviewGoogle65.1
137Qwen3.8 Max PrimeAlibaba65
138Grok Build 0.1xAI65
139Claude Sonnet 4.6 (batch)Anthropic65
140Claude Opus 4.5Anthropic65
141Gemini 3 Flash Preview (batch)Google64.8
142Sakana Namazusakana64.7
143Claude Opus 4.1 (batch)Anthropic64.6
144Inkling 2 Small (free)thinkingmachines64.3
145GPT-5.4 MiniOpenAI64.1
146MiMo-V2.6-ProXiaomi63.9
147Grok 4.20 Multi-AgentxAI63.9
148MiMo-V2.6-FlashXiaomi63.8
149Qwen3.8 Omni FlashAlibaba63.8
150GPT-5.2OpenAI63.8
151Nemotron 3.5 Super VLNVIDIA63.5
152Qwen3.8 Max (0902)Alibaba63.5
153GPT-5.4 Mini (batch)OpenAI63.5
154GLM 5.3 Flash (batch)Zhipu AI63.4
155Kimi K3 (batch)Moonshot AI63.4
156MiniMax M3MiniMax63.3
157GPT-5.4 NanoOpenAI63.3
158Nano Banana 2 (Gemini 3.1 Flash Image)Google63.2
159MiniMax M3.1 FlashMiniMax63.1
160GPT-5.4 Nano (batch)OpenAI63.1
161GPT-5.2-CodexOpenAI63.1
162MiMo-V2.5Xiaomi63
163GPT-5 ImageOpenAI63
164Qwen3.8 27BAlibaba62.9
165Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google62.6
166Claude Sonnet 4.5Anthropic62.6
167MiniMax M3 (batch)MiniMax62.5
168Mistral Medium 3.5Mistral AI62.4
169GLM 5.3 FlashX LegalZhipu AI62.3
170GLM 5.3 FlashXZhipu AI62.3
171Step 5 PreviewStepFun62.2
172GLM Flash Latest~z-ai62.1
173Qwen3.8 FlashAlibaba62.1
174GLM 5.3 FlashZhipu AI62.1
175DeepSeek V4 Flash Vision ExpDeepSeek62.1
176GPT-5.2 (batch)OpenAI62.1
177GPT-5.1OpenAI62.1
178DeepSeek V4.1 Flash 1017DeepSeek61.9
179DeepSeek Flash Latest~deepseek61.9
180DeepSeek V4.1 FlashDeepSeek61.9
181Gemini 2.5 ProGoogle61.9
182DeepSeek V4.1 Flash 1017 (batch)DeepSeek61.8
183Glimpseelorian61.8
184Claude Opus 4.5 (batch)Anthropic61.8
185Seed 2.1 TurboByteDance61.6
186Qwen3.8 Max (0902) (batch)Alibaba61.5
187Qwen3.8 27B (batch)Alibaba61.5
188Qwen3.7 FlashAlibaba61.5
189Mistral Medium 3.5 (batch)Mistral AI61.5
190Qwen3.5 Plus 2026-04-20Alibaba61.5
191Mistral Large 4Mistral AI61.4
192Seed-2.0-CodeByteDance61.4
193Step 3.7 FlashStepFun61.3
194Qwen3.6 FlashAlibaba61.3
195GPT-5.1-Codex-MaxOpenAI61
196GPT-5 Image MiniOpenAI61
197GPT-5.1 (batch)OpenAI60.9
198Qwen3.6 PlusAlibaba60.8
199Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google60.8
200Qwen3.6 35B A3BAlibaba60.7
201Lyria 3 Pro PreviewGoogle60.7
202Lyria 3 Clip PreviewGoogle60.7
203Claude Sonnet 4.5 (batch)Anthropic60.7
204Qwen3.7 PlusAlibaba60.6
205Qwen3.6 27BAlibaba60.6
206Particle-1particle-ai60.5
207DeepSeek V4.1 Flash (batch)DeepSeek60.5
208Gemini 2.5 Flash LiteGoogle60.5
209GPT-5.1-CodexOpenAI60.4
210Hy4Tencent60.2
211Kimi K2.7 CodeMoonshot AI60.2
212GLM 5V TurboZhipu AI60.1
213Nano Banana Pro (Gemini 3 Pro Image Preview)Google60
214Gemini 2.5 FlashGoogle60
215Gemini 2.5 Pro Preview 06-05Google59.9
216Gemini Omni 1.2 FlashGoogle59.8
217Gemini Omni 1.1 FlashGoogle59.8
218Inklingthinkingmachines59.7
219Kimi K2.6Moonshot AI59.5
220Gemma 4 26B A4B Google59.5
221Qwen3.5 Plus 2026-02-15Alibaba59.5
222Qwen3.5-FlashAlibaba59.4
223GPT-5OpenAI59.4
224Seed-2.0-LiteByteDance59.3
225Qwen3.5-9BAlibaba59.3
226Qwen3.7 Plus (batch)Alibaba59.2
227Ling 3.0 Flash VLinclusionai59
228Claude Haiku 4.5Anthropic58.9
229Qwen3.5-27BAlibaba58.8
230Perceptron Mk1.5perceptron58.7
231Seed-2.0-MiniByteDance58.6
232Qwen3.5 397B A17BAlibaba58.6
233Ternary Bonsai 2 9Bprism-ml58.5
234Command A+Cohere58.5
235Inkling Smallthinkingmachines58.5
236Inkling Small (batch)thinkingmachines58.5
237Qwen3.5-122B-A10BAlibaba58.5
238Qwen3.5-35B-A3BAlibaba58.4
239GPT-5.1-Codex-MiniOpenAI58.4
240Claude Haiku 4.5 (batch)Anthropic58.2
241GPT-5 (batch)OpenAI58.2
242Ternary Bonsai 2 27Bprism-ml58.1
243Gemma 4 31BGoogle58.1
244GPT-5.2 ChatOpenAI58.1
245Mistral Small 4Mistral AI57.8
246GPT-5 MiniOpenAI57.4
247Pareto 26.9unbiased57.2
248GPT-5 Mini (batch)OpenAI57.2
249Muse Glimmer 30Bmeta57.1
250Muse Glimmer 30B (batch)meta57
251GPT-5 NanoOpenAI57
252GPT-5 Nano (batch)OpenAI57
253Kimi K2.5Moonshot AI56.3
254Seed 1.6ByteDance56.2
255Seed 1.6 FlashByteDance55.8
256Nova 2 LiteAmazon55.8
257Sonar Pro SearchPerplexity55.1
258o3OpenAI55
259GLM 4.6VZhipu AI54.8
260Pareto 26.10unbiased54
261Pareto Latest~unbiased54
262o3 (batch)OpenAI54
263Qwen3 VL 30B A3B ThinkingAlibaba53.6
264o4 Mini (batch)OpenAI53.5
265Perceptron Mk1perceptron53.3
266Mistral Large 3 2512Mistral AI53.2
267GPT-4.1 NanoOpenAI52.7
268Extractscaledown52.6
269GPT-4.1OpenAI52.3
270Ministral 3 14B 2512Mistral AI51.3
271Ministral 3 8B 2512Mistral AI51.3
272GPT-4.1 (batch)OpenAI51.3
273Reka Edgerekaai51.2
274Nano Banana (Gemini 2.5 Flash Image)Google51.2
275Nemotron 3.5 Content SafetyNVIDIA51.1
276GPT-4.1 MiniOpenAI50.7
277GPT-4.1 Mini (batch)OpenAI50.5
278GPT-4.1 Nano (batch)OpenAI50.3
279Qwen3 VL 8B InstructAlibaba50.2
280Ministral 3 3B 2512Mistral AI50
281Nova Premier 1.0Amazon50
282Mistral Medium 3.1Mistral AI49.2
283GLM 4.5VZhipu AI49
284Summarizescaledown48.9
285Qwen3 VL 235B A22B InstructAlibaba48.5
286Qwen3 VL 30B A3B InstructAlibaba48.1
287Moondream 3 Previewmoondream47.8
288Moondream 3.1moondream47.8
289Mistral Medium 3Mistral AI46.5
290Mistral Small 3.2 24BMistral AI45.3
291Sonar Reasoning ProPerplexity44.7
292GPT-4o (batch)OpenAI44.7
293Llama 4 ScoutMeta44.6
294GPT-4 Turbo (batch)OpenAI44.5
295Llama 4 MaverickMeta44.3
296GPT-4o-mini (batch)OpenAI43.5
297Mistral Small 3.1 24BMistral AI43
298Gemma 3 27BGoogle43
299GPT-4o (2024-11-20)OpenAI42.6
300GPT-4o (2024-05-13)OpenAI42.6
301GPT-4o (2024-08-06)OpenAI42.3
302GPT-4oOpenAI42.3
303Gemma 3 12BGoogle41.6
304Sonar ProPerplexity41.5
305UI-TARS 7B ByteDance40.1
306GPT-4o-miniOpenAI40
307GPT-4o-mini (2024-07-18)OpenAI40
308Qwen2.5 VL 72B InstructAlibaba38.4
309SonarPerplexity38.3
310Gemma 3 4BGoogle38
311Nova Pro 1.0Amazon36.1
312Llama Guard 4 12BMeta36
313Nova Lite 1.0Amazon35.4
314Jev Routertypesafe0

What Else Can Vision Models Do?

Vision-capable models often support additional capabilities. Here is how the 314 vision models break down by other features.

Function Calling

91%

287 of 314 vision models

JSON Mode

93%

291 of 314 vision models

Streaming

100%

314 of 314 vision models

Reasoning

84%

264 of 314 vision models

Web Search

59%

185 of 314 vision models

Image Output

3%

10 of 314 vision models

Top Providers of Vision Models

Which providers offer the most AI models with image understanding capabilities.

OpenAI

87

vision models

Google

44

vision models

Anthropic

32

vision models

Alibaba

27

vision models

Mistral AI

12

vision models

meta

10

vision models

xAI

10

vision models

Zhipu AI

7

vision models

Top Vision Models - Full Capability Breakdown

Detailed capability matrix for the top 15 vision models by composite score.

Supported
Not supported

What Are Vision / Multimodal AI Models?

Vision-capable AI models (also called multimodal models) can process both text and images as input. Instead of being limited to text-only prompts, these models can understand photos, screenshots, charts, diagrams, handwritten notes, and other visual content.

How Vision Input Works

You send an image (as a URL or base64-encoded data) alongside your text prompt via the API. The model processes both together, allowing it to answer questions about the image, describe its contents, extract text (OCR), analyze charts, or reason about visual information.

Common Use Cases for Vision Models

Document analysis and OCR, screenshot-to-code generation, chart and graph interpretation, medical image analysis, accessibility (image descriptions), visual QA for customer support, UI/UX review, diagram-to-code conversion, and real-time visual understanding in agentic workflows.

Vision vs. Image Output

Vision (image input) and image output are distinct capabilities. Vision means the model can see and understand images you send to it. Image output means the model can generate new images. Some models support both, but many vision models are text-output only - they analyze images but respond with text.

Pricing Considerations

Image tokens typically cost more than text tokens. A single high-resolution image can consume thousands of tokens. Most providers charge for image input based on the image dimensions and detail level. Check each model's specific pricing for image token costs.

Explore More Model Comparisons

Dive deeper into model capabilities, rankings, and head-to-head comparisons to find the right vision model for your use case.

Frequently Asked Questions

Vision AI models (multimodal LLMs) can understand and analyze images alongside text. They accept image inputs and can describe photos, extract text from screenshots, analyze charts, and answer questions about visual content.

The top vision models include GPT-4o, Claude 3.5 Sonnet, and Gemini 2.0 Flash. Rankings change frequently as models improve — check our leaderboard for the latest scores.

Not all of them. Vision capabilities refer to understanding images (input). Some models like DALL-E and Stable Diffusion specialize in generating images (output). A few models like GPT-4o can both understand and generate images.

AI Models with Vision - Best Multimodal AI (2026) | LM Market Cap