Vision Arena | Overall

View rankings across multimodal, generative AI models capable of understanding and processing visual inputs

Feb 15, 2026

661,126 votes

95 models

/

Style Control

	Rank Spread
1	13	gemini-3-pro Google · Proprietary	1287±9	11,561
2	14	gemini-3-flash Google · Proprietary	1276±9	10,299
3	19	dola-seed-2.0-preview Bytedance · Proprietary	1267±16	1,491
4	29	gemini-3-flash (thinking-minimal) Google · Proprietary	1263±10	8,437
5	312	gpt-5.2-high OpenAI · Proprietary	1251±12	3,958
6	311	gpt-5.1-high OpenAI · Proprietary	1249±9	8,123
7	311	gemini-2.5-pro Google · Proprietary	1248±6	80,005
8	314	kimi-k2.5-thinking Moonshot · Modified MIT	1248±12	4,134
9	316	kimi-k2.5-instant Moonshot · Modified MIT	1242±13	2,970
10	516	gpt-5.1 OpenAI · Proprietary	1239±9	8,893
11	514	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1239±6	23,807
12	723	gpt-4.5-preview-2025-02-27 OpenAI · Proprietary	1228±11	2,925
13	823	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1227±10	4,759
14	823	gpt-5.2 OpenAI · Proprietary	1226±11	4,316
15	1022	gpt-5-chat OpenAI · Proprietary	1225±8	42,550
16	1025	ernie-5.0-preview-1220 Baidu · Proprietary	1221±12	3,328
17	1223	o3-2025-04-16 OpenAI · Proprietary	1218±7	48,482
18	1225	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1218±8	11,184
19	1226	gpt-4.1-2025-04-14 OpenAI · Proprietary	1215±7	43,960
20	1226	gemini-2.5-flash Google · Proprietary	1213±6	48,422
21	1328	gpt-5-high OpenAI · Proprietary	1209±8	36,696
22	1233	claude-sonnet-4-20250514-thinking-32k Anthropic · Proprietary	1207±16	1,338
23	1233	claude-opus-4-20250514-thinking-16k Anthropic · Proprietary	1207±15	1,480
24	1732	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1203±8	43,382
25	1932	o4-mini-2025-04-16 OpenAI · Proprietary	1202±7	43,855
26	1738	claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary	1195±15	1,651
27	2137	o1-2024-12-17 OpenAI · Proprietary	1195±10	3,694
28	2138	claude-opus-4-20250514 Anthropic · Proprietary	1193±12	2,552
29	2240	qwen3-vl-235b-a22b-thinking Alibaba · Apache 2.0	1188±13	2,423
30	2238	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1188±8	38,645
31	2240	claude-sonnet-4-20250514 Anthropic · Proprietary	1188±13	2,045
32	2240	qwen-vl-max-2025-08-13 Alibaba · Proprietary	1185±12	3,373
33	2440	gpt-5-mini-high OpenAI · Proprietary	1183±9	30,876
34	2640	grok-4-0709 xAI · Proprietary	1182±8	34,091
35	2640	gemini-1.5-pro-002 Google · Proprietary	1180±8	8,902
36	2642	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1179±9	4,667
37	2648	hunyuan-vision-1.5-thinking Tencent · Proprietary	1176±12	2,491
38	2748	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1173±10	4,799
39	3047	gemini-2.0-flash-001 Google · Proprietary	1172±7	10,043
40	3652	gpt-4o-2024-05-13 OpenAI · Proprietary	1164±8	23,273
41	3652	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1163±7	10,549
42	3054	glm-4.6v Z.ai · MIT	1163±14	2,430
43	3754	gemma-3-27b-it Google · Gemma	1158±8	18,105
44	3754	mistral-medium-2505 Mistral · Proprietary	1158±8	11,403
45	3854	mistral-medium-2508 Mistral · Proprietary	1156±7	42,345
46	3756	glm-4.5v Z.ai · MIT	1156±12	3,493
47	3756	step-1o-turbo-202506 StepFun · Proprietary	1155±14	2,027
48	3759	hunyuan-large-vision Tencent · Proprietary	1152±16	1,423
49	4056	claude-3-5-sonnet-20240620 Anthropic · Proprietary	1148±9	21,624
50	4058	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1147±9	7,298
51	4059	step-3 StepFun · Apache 2.0	1147±12	3,450
52	4059	gpt-5-nano-high OpenAI · Proprietary	1146±12	4,206
53	4262	gemini-1.5-flash-002 Google · Proprietary	1141±9	7,241
54	4262	mistral-small-2506 Mistral · Apache 2.0	1141±9	11,559
55	4663	gemini-2.0-flash-lite-preview-02-05 Google · Proprietary	1136±10	3,991
56	4664	claude-3-5-haiku-20241022 Anthropic · Proprietary	1132±15	1,565
57	4964	llama-4-scout-17b-16e-instruct Meta · Llama	1128±10	6,725
58	5064	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1128±9	30,781
59	4964	step-1o-vision-32k-highres StepFun · Proprietary	1126±12	2,833
60	5364	qwen2.5-vl-72b-instruct Alibaba · Qwen	1123±10	3,768
61	5364	gpt-4o-2024-08-06 OpenAI · Proprietary	1120±12	3,376
62	5564	gemini-1.5-pro-001 Google · Proprietary	1120±11	16,734
63	5367	qwen2.5-vl-32b-instruct Alibaba · Apache 2.0	1119±15	1,490
64	5667	gpt-4-turbo-2024-04-09 OpenAI · Proprietary	1114±11	13,391
65	6369	gpt-4o-mini-2024-07-18 OpenAI · Proprietary	1099±8	17,347
66	6369	pixtral-large-2411 Mistral · MRL	1096±9	5,423
67	6373	gpt-4.1-nano-2025-04-14 OpenAI · Proprietary	1090±18	1,211
68	6571	qwen2-vl-72b Alibaba · Qwen	1087±10	5,937
69	6573	qwen-vl-max-1119 Alibaba · Proprietary	1087±16	1,422
70	6774	gemini-1.5-flash-8b-001 Google · Proprietary	1072±10	6,243
71	6875	claude-3-opus-20240229 Anthropic · Proprietary	1066±10	15,565
72	6775	step-1v-32k StepFun · Proprietary	1065±16	1,534
73	6875	gemini-1.5-flash-001 Google · Proprietary	1062±11	13,260
74	7179	molmo-72b-0924 AI2 · Apache 2.0	1049±13	3,048
75	7082	hunyuan-standard-vision-2024-12-31 Tencent · Proprietary	1045±21	809
76	7482	llama-3.2-vision-90b-instruct Meta · Llama 3.2	1034±9	8,682
77	7483	qwen2-vl-7b-instruct Aliaba · Apache 2.0	1033±10	5,766
78	7584	pixtral-12b-2409 Mistral · Apache 2.0	1027±9	7,511
79	7485	internvl2-26b OpenGVLab · MIT	1026±12	5,148
80	7487	amazon-nova-lite-v1.0 Amazon · Proprietary	1022±15	1,854
81	7587	amazon-nova-pro-v1.0 Amazon · Proprietary	1021±13	2,335
82	7586	claude-3-sonnet-20240229 Anthropic · Proprietary	1021±11	12,314
83	7889	yi-vision 01 AI · Proprietary	1005±18	1,219
84	7989	claude-3-haiku-20240307 Anthropic · Proprietary	1004±12	13,380
85	7791	c4ai-aya-vision-32b Cohere · CC-BY-NC-4.0	1002±22	847
86	8089	molmo-7b-d-0924 AI2 · Apache 2.0	998±13	2,815
87	8389	llama-3.2-vision-11b-instruct Meta · Llama 3.2	994±11	4,817
88	8193	nvila-internal-15b-v1 Nvidia · -	989±20	1,077
89	8393	llava-onevision-qwen2-72b-ov LLaVA · Apache 2.0	982±18	1,321
90	8893	llava-v1.6-34b LLaVA · Apache 2.0	968±12	4,531
91	8793	minicpm-v-2_6 OpenBMB · Apache 2.0	966±15	1,987
92	8793	cogvlm2-llama3-chat-19b Zhipu AI · CogVLM2	966±15	1,991
93	8893	internvl2-4b OpenGVLab · MIT	960±12	3,703
94	9494	phi-3.5-vision-instruct Microsoft · MIT	923±15	2,592
95	9595	phi-3-vision-128k-instruct Microsoft · MIT	885±18	1,401

Vision Arena | Overall

Default Leaderboard Plots

Fraction of Model A Wins for All Non-tied A vs. B Battles

Confidence Intervals on Model Strength (via Bootstrapping)

Average Win Rate Against All Other Models (Uniform Sampling and No Ties)

Battle Count for Each Combination of Models (without Ties)