Vision Arena📊Diagram

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

Jun 5, 2026

135,824 votes

86 models

Rank by

	Rank Spread
1	16	claude-opus-4-7-thinking Anthropic · Proprietary	1345±12	3,221	$5 / $25	1M
2	18	claude-opus-4-7 Anthropic · Proprietary	1339±12	3,395	$5 / $25	1M
3	112	claude-opus-4-6 Anthropic · Proprietary	1330±11	4,030	$5 / $25	1M
4	116	gpt-5.5 OpenAI · Proprietary	1329±13	2,614	$5 / $30	1.1M
5	116	claude-opus-4-6-thinking Anthropic · Proprietary	1328±12	3,146	$5 / $25	1M
6	120	claude-opus-4-8-thinking Anthropic · Proprietary	1317±23	740	$5 / $25	1M
7	218	gpt-5.4-high OpenAI · Proprietary	1315±13	2,995	$2.50 / $15	1.1M
8	320	gpt-5.5-high OpenAI · Proprietary	1312±13	2,403	$5 / $30	1.1M
9	220	muse-spark Meta · Proprietary	1312±16	1,457	N/A	N/A
10	320	gpt-5.5-instant OpenAI · Proprietary	1311±15	2,051	$5 / $30	1.1M
11	320	gpt-5.2-chat-latest-20260210 OpenAI · Proprietary	1310±11	3,854	$1.75 / $14	128K
12	418	gemini-3.1-pro-preview Google · Proprietary	1309±9	6,336	$2 / $12	1M
13	320	gpt-5.4 OpenAI · Proprietary	1307±12	2,936	$2.50 / $15	1.1M
14	420	claude-sonnet-4-6 Anthropic · Proprietary	1307±11	4,280	$3 / $15	1M
15	622	gemini-3-pro Google · Proprietary	1301±12	2,880	$2 / $12	1M
16	431	qwen3.7-plus-preview Alibaba · Proprietary	1297±19	1,055	$0.40 / $1.60	1M
17	434	claude-opus-4-8 Anthropic · Proprietary	1296±22	823	$5 / $25	1M
18	625	gemini-3-flash Google · Proprietary	1296±8	6,551	$0.50 / $3	1M
19	833	dola-seed-2.0-pro Bytedance · Proprietary	1288±12	2,604	N/A	N/A
20	834	kimi-k2.6 Moonshot · Modified MIT	1287±13	2,616	$0.95 / $4	262.1K
21	1535	gemini-3-flash (thinking-minimal) Google · Proprietary	1283±9	6,443	$0.50 / $3	1M
22	1540	gpt-5.4-mini-high OpenAI · Proprietary	1280±11	3,786	$0.75 / $4.50	400K
23	1637	gemma-4-31b Google · Apache 2.0	1280±9	6,524	$0.14 / $0.40	262.1K
24	1640	kimi-k2.5-thinking Moonshot · Modified MIT	1279±10	4,805	$0.60 / $3	N/A
25	1646	gpt-5.1-high OpenAI · Proprietary	1276±13	2,171	$1.25 / $10	400K
26	1742	qwen3.5-397b-a17b Alibaba · Apache 2.0	1275±10	4,221	$0.39 / $2.34	262.1K
27	1742	gpt-5.2-high OpenAI · Proprietary	1274±10	4,481	$1.75 / $14	400K
28	1747	grok-4.20-beta-0309-reasoning xAI · Proprietary	1271±11	3,927	$2 / $6	2M
29	1749	grok-4.3 xAI · Proprietary	1267±14	2,290	$1.25 / $2.50	1M
30	1747	mimo-v2.5 Xiaomi · MIT	1267±12	3,399	$0.14 / $0.28	1M
31	2247	gemini-2.5-pro Google · Proprietary	1266±7	9,471	$1.25 / $10	1M
32	1849	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1265±10	3,727	$5 / $15	128K
33	1949	grok-4.20-multi-agent-beta-0309 xAI · Proprietary	1264±11	3,547	$2 / $6	2M
34	1850	gpt-5.1 OpenAI · Proprietary	1264±13	2,344	$1.25 / $10	400K
35	2150	gpt-5-chat OpenAI · Proprietary	1261±13	2,551	$1.25 / $10	128K
36	2250	glm-5v-turbo Z.ai · Proprietary	1259±11	3,898	$1.20 / $4	202.8K
37	2350	gemma-4-26b-a4b Google · Apache 2.0	1259±11	4,055	N/A	N/A
38	2550	gpt-5.2 OpenAI · Proprietary	1257±10	4,754	$1.75 / $14	400K
39	2555	mimo-v2-omni Xiaomi · Proprietary	1254±13	2,614	$0.40 / $2	262.1K
40	2754	gemini-3.1-flash-lite-preview Google · Proprietary	1254±10	5,021	$0.25 / $1.50	1M
41	2756	gpt-5-high OpenAI · Proprietary	1251±13	3,002	$1.25 / $10	400K
42	2359	kimi-k2.5-instant Moonshot · Modified MIT	1251±19	910	$0.40 / $1.90	262.1K
43	1765	qwen-vl-max-2025-08-13 Alibaba · Proprietary	1250±30	354	$0.52 / $2.08	131.1K
44	2263	minimax-m3 MiniMax · Proprietary	1248±23	736	$0.60 / $2.40	N/A
45	2763	mistral-medium-3.5 Mistral · Modified MIT	1245±19	1,133	$1.50 / $7.50	262.1K
46	3158	qwen3.5-27b Alibaba · Apache 2.0	1244±11	3,579	$0.20 / $1.56	262.1K
47	3158	qwen3.5-122b-a10b Alibaba · Apache 2.0	1244±11	3,162	$0.26 / $2.08	262.1K
48	2863	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1243±18	972	$0.30 / $2.50	1M
49	3460	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1241±12	2,687	$0.20 / $0.88	262.1K
50	4060	gemini-2.5-flash Google · Proprietary	1236±7	8,294	$0.30 / $2.50	1M
51	3965	gpt-4.1-2025-04-14 OpenAI · Proprietary	1234±13	2,824	$2 / $8	1M
52	3965	o3-2025-04-16 OpenAI · Proprietary	1232±12	3,643	$2 / $8	200K
53	4165	gpt-5.4-nano-high OpenAI · Proprietary	1228±11	3,738	$0.20 / $1.25	400K
54	2774	claude-sonnet-4-20250514-thinking-32k Anthropic · Proprietary	1227±37	229	$3 / $15	1M
55	3970	ernie-5.0-preview-1220 Baidu · Proprietary	1226±22	702	N/A	N/A
56	4468	o4-mini-2025-04-16 OpenAI · Proprietary	1219±12	2,882	$1.10 / $4.40	200K
57	4770	grok-4-1-fast-reasoning xAI · Proprietary	1216±12	3,131	$0.20 / $0.50	2M
58	3977	claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary	1213±33	304	$3 / $15	200K
59	4772	gpt-5-mini-high OpenAI · Proprietary	1212±15	1,985	$0.25 / $2	400K
60	4275	qwen3-vl-235b-a22b-thinking Alibaba · Apache 2.0	1212±26	479	$0.26 / $2.60	131.1K
61	5072	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1209±13	2,414	$0.40 / $1.60	1M
62	4280	claude-opus-4-20250514-thinking-16k Anthropic · Proprietary	1202±34	285	$15 / $75	200K
63	4579	claude-sonnet-4-20250514 Anthropic · Proprietary	1202±28	397	$3 / $15	1M
64	4779	claude-opus-4-20250514 Anthropic · Proprietary	1202±25	471	$15 / $75	200K
65	5578	grok-4-0709 xAI · Proprietary	1193±13	2,528	$3 / $15	256K
66	5082	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1191±32	305	$3 / $15	200K
67	5779	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1188±13	2,500	$0.10 / $0.40	1M
68	5482	hunyuan-vision-1.5-thinking Tencent · Proprietary	1188±26	496	N/A	N/A
69	5580	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1186±18	983	$0.10 / $0.40	1M
70	5482	glm-4.6v Z.ai · MIT	1186±24	549	$0.30 / $0.90	131.1K
71	5484	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1181±32	318	$3 / $15	200K
72	6080	mistral-medium-2508 Mistral · Proprietary	1179±10	3,705	$2.70 / $8.10	32K
73	5983	gemini-2.0-flash-001 Google · Proprietary	1176±18	1,134	$0.10 / $0.40	1M
74	5786	glm-4.5v Z.ai · MIT	1170±29	376	$0.60 / $1.80	65.5K
75	6183	mistral-medium-2505 Mistral · Proprietary	1167±16	1,445	$0.40 / $2	131.1K
76	6183	gemma-3-27b-it Google · Gemma	1166±15	1,761	$0.08 / $0.16	131.1K
77	5986	step-1o-turbo-202506 StepFun · Proprietary	1164±29	393	N/A	N/A
78	6286	gpt-5-nano-high OpenAI · Proprietary	1154±26	528	$0.05 / $0.40	400K
79	6686	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1151±19	970	$0.63 / $1.80	131.1K
80	6386	step-3 StepFun · Apache 2.0	1147±30	364	$0.57 / $1.42	65.5K
81	6986	llama-4-scout-17b-16e-instruct Meta · Llama	1147±20	866	$0.40 / $0.70	8.2K
82	7286	mistral-small-2506 Mistral · Apache 2.0	1141±18	1,180	$0.10 / $0.30	32K
83	6986	claude-3-5-haiku-20241022 Anthropic · Proprietary	1131±33	325	$0.80 / $4	200K
84	7686	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1130±15	1,664	$0.10 / $0.30	32K
85	7586	hunyuan-large-vision Tencent · Proprietary	1115±35	263	N/A	N/A
86	7686	molmo-2-8b Ai2 · Apache 2.0	1106±39	281	$0.20 / $0.20	36.9K

Vision Arena📊Diagram

Default Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

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

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