Vision Arena🇨🇳Chinese

View overall rankings across multimodal AI models capable of reasoning over visual inputs.

Jun 5, 2026

41,646 votes

94 models

Rank by

	Rank Spread
1	115	claude-opus-4-6-thinking Anthropic · Proprietary	1360±27	712	$5 / $25	1M
2	116	gemini-3-pro Google · Proprietary	1351±21	1,403	$2 / $12	1M
3	123	claude-opus-4-6 Anthropic · Proprietary	1350±26	825	$5 / $25	1M
4	117	gemini-3.1-pro-preview Google · Proprietary	1350±21	1,440	$2 / $12	1M
5	126	claude-opus-4-7-thinking Anthropic · Proprietary	1345±28	638	$5 / $25	1M
6	131	muse-spark Meta · Proprietary	1340±32	430	N/A	N/A
7	130	claude-opus-4-7 Anthropic · Proprietary	1339±26	795	$5 / $25	1M
8	141	kimi-k2.5-instant Moonshot · Modified MIT	1326±44	172	$0.40 / $1.90	262.1K
9	136	kimi-k2.6 Moonshot · Modified MIT	1325±29	585	$0.95 / $4	262.1K
10	134	gemini-3-flash Google · Proprietary	1322±20	1,416	$0.50 / $3	1M
11	136	gemini-3-flash (thinking-minimal) Google · Proprietary	1317±21	1,289	$0.50 / $3	1M
12	138	gpt-5.5 OpenAI · Proprietary	1317±29	599	$5 / $30	1.1M
13	139	gpt-5.4-high OpenAI · Proprietary	1315±28	672	$2.50 / $15	1.1M
14	237	gemma-4-31b Google · Apache 2.0	1313±20	1,661	$0.14 / $0.40	262.1K
15	140	mimo-v2.5 Xiaomi · MIT	1312±28	638	$0.14 / $0.28	1M
16	144	gpt-5.5-high OpenAI · Proprietary	1303±31	479	$5 / $30	1.1M
17	443	gemma-4-26b-a4b Google · Apache 2.0	1302±24	988	N/A	N/A
18	443	qwen3.5-397b-a17b Alibaba · Apache 2.0	1301±25	810	$0.39 / $2.34	262.1K
19	443	claude-sonnet-4-6 Anthropic · Proprietary	1300±25	901	$3 / $15	1M
20	344	gpt-5.4 OpenAI · Proprietary	1300±30	600	$2.50 / $15	1.1M
21	543	kimi-k2.5-thinking Moonshot · Modified MIT	1300±23	974	$0.60 / $3	N/A
22	444	dola-seed-2.0-pro Bytedance · Proprietary	1299±28	589	N/A	N/A
23	443	glm-5v-turbo Z.ai · Proprietary	1299±25	878	$1.20 / $4	202.8K
24	544	gpt-5.4-mini-high OpenAI · Proprietary	1297±26	819	$0.75 / $4.50	400K
25	544	grok-4.20-beta-0309-reasoning xAI · Proprietary	1295±25	860	$2 / $6	2M
26	644	gpt-5.2-high OpenAI · Proprietary	1293±23	955	$1.75 / $14	400K
27	647	grok-4.20-multi-agent-beta-0309 xAI · Proprietary	1289±25	805	$2 / $6	2M
28	647	qwen3.5-27b Alibaba · Apache 2.0	1289±26	772	$0.20 / $1.56	262.1K
29	453	qwen3.7-plus-preview Alibaba · Proprietary	1284±43	241	$0.40 / $1.60	1M
30	749	grok-4.3 xAI · Proprietary	1280±32	464	$1.25 / $2.50	1M
31	849	qwen3.5-122b-a10b Alibaba · Apache 2.0	1279±26	720	$0.26 / $2.08	262.1K
32	949	gemini-3.1-flash-lite-preview Google · Proprietary	1278±23	1,138	$0.25 / $1.50	1M
33	850	gpt-5.1-high OpenAI · Proprietary	1274±29	460	$1.25 / $10	400K
34	854	gpt-5.5-instant OpenAI · Proprietary	1272±34	430	$5 / $30	1.1M
35	952	mimo-v2-omni Xiaomi · Proprietary	1271±29	534	$0.40 / $2	262.1K
36	1251	gpt-5.2 OpenAI · Proprietary	1267±23	1,032	$1.75 / $14	400K
37	1153	gpt-5.2-chat-latest-20260210 OpenAI · Proprietary	1266±26	826	$1.75 / $14	128K
38	1549	gemini-2.5-pro Google · Proprietary	1266±17	3,037	$1.25 / $10	1M
39	659	o1-2024-12-17 OpenAI · Proprietary	1259±57	99	$15 / $60	200K
40	1654	gpt-5-chat OpenAI · Proprietary	1258±21	1,281	$1.25 / $10	128K
41	1357	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1258±30	391	$0.30 / $2.50	1M
42	1656	gpt-5.1 OpenAI · Proprietary	1255±26	564	$1.25 / $10	400K
43	2154	gemini-2.5-flash Google · Proprietary	1254±17	2,524	$0.30 / $2.50	1M
44	2757	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1249±21	1,095	$5 / $15	128K
45	2758	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1244±24	722	$0.20 / $0.88	262.1K
46	2758	gpt-5.4-nano-high OpenAI · Proprietary	1243±26	845	$0.20 / $1.25	400K
47	1462	ernie-5.0-preview-1220 Baidu · Proprietary	1240±46	173	N/A	N/A
48	2958	gpt-4.1-2025-04-14 OpenAI · Proprietary	1237±20	1,382	$2 / $8	1M
49	3359	gpt-5-high OpenAI · Proprietary	1224±22	1,352	$1.25 / $10	400K
50	3459	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1224±21	1,145	$0.40 / $1.60	1M
51	3559	o3-2025-04-16 OpenAI · Proprietary	1223±20	1,619	$2 / $8	200K
52	3664	grok-4-1-fast-reasoning xAI · Proprietary	1215±26	761	$0.20 / $0.50	2M
53	4164	grok-4-0709 xAI · Proprietary	1212±22	1,186	$3 / $15	256K
54	4265	o4-mini-2025-04-16 OpenAI · Proprietary	1207±21	1,292	$1.10 / $4.40	200K
55	4166	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1206±29	406	$0.10 / $0.40	1M
56	3871	gemini-1.5-pro-002 Google · Proprietary	1197±42	395	$3.50 / $10.50	2.1M
57	2976	gpt-4.5-preview-2025-02-27 OpenAI · Proprietary	1196±61	77	$75 / $150	128K
58	4770	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1188±23	1,007	$0.10 / $0.40	1M
59	5172	gpt-5-mini-high OpenAI · Proprietary	1174±24	1,012	$0.25 / $2	400K
60	4476	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1172±48	153	$3 / $15	200K
61	5272	mistral-medium-2508 Mistral · Proprietary	1171±20	1,413	$2.70 / $8.10	32K
62	5173	gemma-3-27b-it Google · Gemma	1169±25	735	$0.08 / $0.16	131.1K
63	5176	gemini-2.0-flash-001 Google · Proprietary	1164±33	338	$0.10 / $0.40	1M
64	5278	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1156±37	513	$3 / $15	200K
65	5478	gpt-4o-2024-05-13 OpenAI · Proprietary	1151±36	1,472	$5 / $15	128K
66	5577	mistral-medium-2505 Mistral · Proprietary	1149±29	477	$0.40 / $2	131.1K
67	5678	mistral-small-2506 Mistral · Apache 2.0	1144±30	481	$0.10 / $0.30	32K
68	5779	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1134±26	719	$0.10 / $0.30	32K
69	5681	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1130±38	232	$0.63 / $1.80	131.1K
70	5681	gemini-1.5-flash-002 Google · Proprietary	1127±42	370	$0.07 / $0.30	1M
71	5682	qwen2.5-vl-72b-instruct Alibaba · Qwen	1120±54	119	$0.25 / $0.75	131.1K
72	5882	claude-3-5-sonnet-20240620 Anthropic · Proprietary	1115±37	1,564	$3 / $15	200K
73	6083	qwen2-vl-72b Alibaba · Qwen	1105±44	291	$0.90 / $0.90	32.8K
74	6185	llama-4-scout-17b-16e-instruct Meta · Llama	1096±40	236	$0.40 / $0.70	8.2K
75	6186	pixtral-large-2411 Mistral · MRL	1092±51	156	$2 / $6	128K
76	6189	gemini-2.0-flash-lite-preview-02-05 Google · Proprietary	1075±60	98	$0.07 / $0.30	1M
77	6886	gpt-4o-mini-2024-07-18 OpenAI · Proprietary	1075±36	952	$0.15 / $0.60	128K
78	6487	internvl2-26b OpenGVLab · MIT	1075±47	287	N/A	N/A
79	6588	gpt-4o-2024-08-06 OpenAI · Proprietary	1069±50	186	$2.50 / $10	128K
80	6987	gemini-1.5-pro-001 Google · Proprietary	1069±38	1,168	$3.50 / $10.50	2.1M
81	6988	gpt-4-turbo-2024-04-09 OpenAI · Proprietary	1058±39	937	$10 / $30	128K
82	7194	qwen2-vl-7b-instruct Alibaba · Apache 2.0	1033±45	298	$0.20 / $0.20	32.8K
83	7394	gemini-1.5-flash-001 Google · Proprietary	1025±39	950	$0.07 / $0.30	1M
84	7494	claude-3-opus-20240229 Anthropic · Proprietary	1021±39	1,038	$15 / $75	200K
85	7494	gemini-1.5-flash-8b-001 Google · Proprietary	1016±43	332	$0.07 / $0.30	1M
86	7594	llama-3.2-vision-90b-instruct Meta · Llama 3.2	1001±42	393	N/A	N/A
87	7794	molmo-72b-0924 Ai2 · Apache 2.0	979±54	182	N/A	N/A
88	8194	claude-3-sonnet-20240229 Anthropic · Proprietary	976±39	915	$3 / $15	200K
89	8294	claude-3-haiku-20240307 Anthropic · Proprietary	971±39	1,019	$0.25 / $1.25	200K
90	7994	internvl2-4b OpenGVLab · MIT	966±55	177	N/A	N/A
91	8294	pixtral-12b-2409 Mistral · Apache 2.0	961±43	335	$0.15 / $0.15	128K
92	8294	molmo-7b-d-0924 Ai2 · Apache 2.0	950±55	171	N/A	N/A
93	8294	llama-3.2-vision-11b-instruct Meta · Llama 3.2	948±49	266	N/A	N/A
94	8294	llava-v1.6-34b LLaVA · Apache 2.0	948±45	415	N/A	N/A

Vision Arena🇨🇳Chinese

Default Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

Confidence Intervals on Model Strength (via Bootstrapping)

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

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