Vision Arena | Overall

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

Feb 20, 2026

668,987 votes

98 models

	Rank Spread
1	13	gemini-3-pro Google · Proprietary	1288±8	12,034
2	15	gemini-3.1-pro-preview Google · Proprietary	1277±12	3,503
3	15	gemini-3-flash Google · Proprietary	1274±9	10,908
4	212	dola-seed-2.0-preview Bytedance · Proprietary	1263±16	1,571
5	29	gemini-3-flash (thinking-minimal) Google · Proprietary	1262±10	8,927
6	413	gpt-5.1-high OpenAI · Proprietary	1250±9	8,640
7	414	gpt-5.2-high OpenAI · Proprietary	1250±11	4,511
8	414	kimi-k2.5-thinking Moonshot · Modified MIT	1250±11	4,662
9	413	gemini-2.5-pro Google · Proprietary	1248±6	80,509
10	518	gpt-5.1 OpenAI · Proprietary	1241±9	9,492
11	518	kimi-k2.5-instant Moonshot · Modified MIT	1239±12	3,552
12	617	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1239±6	24,033
13	522	qwen3.5-397b-a17b Alibaba · Apache 2.0	1237±15	1,614
14	1024	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1228±10	4,752
15	825	gpt-4.5-preview-2025-02-27 OpenAI · Proprietary	1228±11	2,925
16	1025	gpt-5.2 OpenAI · Proprietary	1227±11	4,882
17	1124	gpt-5-chat OpenAI · Proprietary	1225±8	42,547
18	1027	ernie-5.0-preview-1220 Baidu · Proprietary	1221±12	3,324
19	1326	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1218±8	11,697
20	1325	o3-2025-04-16 OpenAI · Proprietary	1218±7	48,659
21	1428	gpt-4.1-2025-04-14 OpenAI · Proprietary	1215±7	44,042
22	1428	gemini-2.5-flash Google · Proprietary	1212±6	48,908
23	1630	gpt-5-high OpenAI · Proprietary	1209±8	36,682
24	1335	claude-sonnet-4-20250514-thinking-32k Anthropic · Proprietary	1207±16	1,337
25	1335	claude-opus-4-20250514-thinking-16k Anthropic · Proprietary	1207±15	1,479
26	1934	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1203±8	43,406
27	2134	o4-mini-2025-04-16 OpenAI · Proprietary	1202±7	44,353
28	2040	claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary	1195±15	1,649
29	2339	o1-2024-12-17 OpenAI · Proprietary	1195±10	3,694
30	2340	claude-opus-4-20250514 Anthropic · Proprietary	1193±12	2,547
31	2442	qwen3-vl-235b-a22b-thinking Alibaba · Apache 2.0	1188±13	2,418
32	2440	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1188±8	38,638
33	2442	claude-sonnet-4-20250514 Anthropic · Proprietary	1188±13	2,043
34	2442	qwen-vl-max-2025-08-13 Alibaba · Proprietary	1185±12	3,373
35	2642	gpt-5-mini-high OpenAI · Proprietary	1183±9	30,876
36	2842	grok-4-0709 xAI · Proprietary	1182±8	34,084
37	2842	gemini-1.5-pro-002 Google · Proprietary	1180±8	8,902
38	2844	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1179±9	4,666
39	2849	hunyuan-vision-1.5-thinking Tencent · Proprietary	1176±12	2,488
40	2950	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1173±10	4,791
41	3249	gemini-2.0-flash-001 Google · Proprietary	1173±7	10,666
42	3854	gpt-4o-2024-05-13 OpenAI · Proprietary	1164±8	23,273
43	3854	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1163±7	10,548
44	3256	glm-4.6v Z.ai · MIT	1163±14	2,422
45	3956	gemma-3-27b-it Google · Gemma	1158±8	18,103
46	3956	mistral-medium-2505 Mistral · Proprietary	1158±8	11,422
47	4156	mistral-medium-2508 Mistral · Proprietary	1156±7	42,832
48	3958	glm-4.5v Z.ai · MIT	1156±12	3,492
49	3958	step-1o-turbo-202506 StepFun · Proprietary	1155±14	2,027
50	3961	hunyuan-large-vision Tencent · Proprietary	1152±16	1,423
51	4258	claude-3-5-sonnet-20240620 Anthropic · Proprietary	1148±9	21,624
52	4260	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1147±9	7,297
53	4261	step-3 StepFun · Apache 2.0	1147±12	3,447
54	4262	gpt-5-nano-high OpenAI · Proprietary	1146±12	4,202
55	4465	gemini-1.5-flash-002 Google · Proprietary	1141±9	7,241
56	4465	mistral-small-2506 Mistral · Apache 2.0	1141±9	11,563
57	4866	gemini-2.0-flash-lite-preview-02-05 Google · Proprietary	1136±10	3,991
58	4867	claude-3-5-haiku-20241022 Anthropic · Proprietary	1132±15	1,565
59	5167	llama-4-scout-17b-16e-instruct Meta · Llama	1128±10	6,724
60	5267	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1128±9	30,775
61	5167	step-1o-vision-32k-highres StepFun · Proprietary	1126±12	2,833
62	5567	qwen2.5-vl-72b-instruct Alibaba · Qwen	1123±10	3,768
63	5568	gpt-4o-2024-08-06 OpenAI · Proprietary	1120±12	3,376
64	5767	gemini-1.5-pro-001 Google · Proprietary	1120±11	16,734
65	5470	qwen2.5-vl-32b-instruct Alibaba · Apache 2.0	1119±15	1,490
66	5870	gpt-4-turbo-2024-04-09 OpenAI · Proprietary	1114±11	13,391
67	5572	molmo-2-8b AI2 · Apache 2.0	1114±20	1,202
68	6572	gpt-4o-mini-2024-07-18 OpenAI · Proprietary	1099±8	17,347
69	6572	pixtral-large-2411 Mistral · MRL	1096±9	5,423
70	6476	gpt-4.1-nano-2025-04-14 OpenAI · Proprietary	1090±18	1,211
71	6774	qwen2-vl-72b Alibaba · Qwen	1087±10	5,937
72	6776	qwen-vl-max-1119 Alibaba · Proprietary	1087±16	1,422
73	7077	gemini-1.5-flash-8b-001 Google · Proprietary	1072±10	6,243
74	7178	claude-3-opus-20240229 Anthropic · Proprietary	1065±10	15,565
75	7078	step-1v-32k StepFun · Proprietary	1065±16	1,534
76	7178	gemini-1.5-flash-001 Google · Proprietary	1062±11	13,260
77	7482	molmo-72b-0924 AI2 · Apache 2.0	1049±13	3,048
78	7385	hunyuan-standard-vision-2024-12-31 Tencent · Proprietary	1045±21	809
79	7785	llama-3.2-vision-90b-instruct Meta · Llama 3.2	1034±9	8,682
80	7786	qwen2-vl-7b-instruct Aliaba · Apache 2.0	1033±10	5,766
81	7887	pixtral-12b-2409 Mistral · Apache 2.0	1027±9	7,511
82	7788	internvl2-26b OpenGVLab · MIT	1027±12	5,148
83	7790	amazon-nova-lite-v1.0 Amazon · Proprietary	1022±15	1,854
84	7890	amazon-nova-pro-v1.0 Amazon · Proprietary	1021±13	2,335
85	7889	claude-3-sonnet-20240229 Anthropic · Proprietary	1020±11	12,314
86	8192	yi-vision 01 AI · Proprietary	1005±18	1,219
87	8292	claude-3-haiku-20240307 Anthropic · Proprietary	1004±12	13,380
88	7994	c4ai-aya-vision-32b Cohere · CC-BY-NC-4.0	1002±22	847
89	8392	molmo-7b-d-0924 AI2 · Apache 2.0	998±13	2,815
90	8692	llama-3.2-vision-11b-instruct Meta · Llama 3.2	994±11	4,817
91	8496	nvila-internal-15b-v1 Nvidia · -	989±20	1,077
92	8696	llava-onevision-qwen2-72b-ov LLaVA · Apache 2.0	982±18	1,321
93	9196	llava-v1.6-34b LLaVA · Apache 2.0	968±12	4,531
94	9096	minicpm-v-2_6 OpenBMB · Apache 2.0	966±16	1,987
95	9096	cogvlm2-llama3-chat-19b Zhipu AI · CogVLM2	966±15	1,991
96	9196	internvl2-4b OpenGVLab · MIT	960±12	3,703
97	9797	phi-3.5-vision-instruct Microsoft · MIT	923±15	2,592
98	9898	phi-3-vision-128k-instruct Microsoft · MIT	885±18	1,401

Vision Arena | Overall

Default Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

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

Confidence Intervals on Model Strength (via Bootstrapping)

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