Vision Arena📝OCR

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

May 17, 2026

322,502 votes

82 models

Rank by

	Rank Spread
1	16	claude-opus-4-7 Anthropic · Proprietary	1319±9	4,788	$5 / $25	1M
2	16	claude-opus-4-7-thinking Anthropic · Proprietary	1319±10	4,541	$5 / $25	1M
3	17	claude-opus-4-6-thinking Anthropic · Proprietary	1317±9	4,936	$5 / $25	1M
4	110	claude-opus-4-6 Anthropic · Proprietary	1309±9	6,052	$5 / $25	1M
5	112	gemini-3-pro Google · Proprietary	1303±8	8,135	$2 / $12	1M
6	115	muse-spark Meta · Proprietary	1303±11	3,176	N/A	N/A
7	415	gemini-3.1-pro-preview Google · Proprietary	1297±7	11,404	$2 / $12	1M
8	317	gpt-5.5 OpenAI · Proprietary	1296±11	3,327	$5 / $30	1.1M
9	417	gpt-5.4-high OpenAI · Proprietary	1292±10	4,194	$2.50 / $15	1.1M
10	419	gpt-5.5-high OpenAI · Proprietary	1291±11	2,990	$5 / $30	1.1M
11	517	gpt-5.2-chat-latest-20260210 OpenAI · Proprietary	1289±8	8,488	$1.75 / $14	128K
12	518	claude-sonnet-4-6 Anthropic · Proprietary	1289±8	6,267	$3 / $15	1M
13	618	gemini-3-flash Google · Proprietary	1286±6	14,158	$0.50 / $3	1M
14	619	gpt-5.4 OpenAI · Proprietary	1284±10	3,939	$2.50 / $15	1.1M
15	623	gpt-5.5-instant OpenAI · Proprietary	1283±12	2,689	$5 / $30	1.1M
16	827	kimi-k2.6 Moonshot · Modified MIT	1275±10	3,983	$0.95 / $4	262.1K
17	1325	gemini-3-flash (thinking-minimal) Google · Proprietary	1273±6	12,906	$0.50 / $3	1M
18	830	qwen3.7-plus-preview Alibaba · Proprietary	1273±12	2,684	N/A	N/A
19	1128	dola-seed-2.0-pro Bytedance · Proprietary	1273±9	6,203	N/A	N/A
20	1533	gpt-5.4-mini-high OpenAI · Proprietary	1265±9	5,900	$0.75 / $4.50	400K
21	1533	qwen3.5-397b-a17b Alibaba · Apache 2.0	1264±8	7,963	$0.39 / $2.34	262.1K
22	1533	kimi-k2.5-thinking Moonshot · Modified MIT	1263±7	9,690	$0.60 / $3	N/A
23	1636	gemma-4-31b Google · Apache 2.0	1261±7	11,943	$0.14 / $0.40	262.1K
24	1736	gpt-5.2-high OpenAI · Proprietary	1260±7	10,236	$1.75 / $14	400K
25	1539	grok-4.3 xAI · Proprietary	1259±12	2,750	$1.25 / $2.50	1M
26	1637	gpt-5.1-high OpenAI · Proprietary	1259±9	5,746	$1.25 / $10	400K
27	1737	grok-4.20-beta-0309-reasoning xAI · Proprietary	1259±8	6,616	$2 / $6	2M
28	1838	gemma-4-26b-a4b Google · Apache 2.0	1257±8	7,345	N/A	N/A
29	1937	gemini-2.5-pro Google · Proprietary	1256±5	30,750	$1.25 / $10	1M
30	1940	grok-4.20-multi-agent-beta-0309 xAI · Proprietary	1254±8	6,099	$2 / $6	2M
31	2041	gemini-3.1-flash-lite-preview Google · Proprietary	1252±8	9,484	$0.25 / $1.50	1M
32	2041	gpt-5.1 OpenAI · Proprietary	1252±9	6,463	$1.25 / $10	400K
33	2342	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1249±7	11,197	$5 / $15	128K
34	2045	kimi-k2.5-instant Moonshot · Modified MIT	1248±12	2,596	$0.40 / $1.90	262.1K
35	2345	mimo-v2.5 Xiaomi · MIT	1245±9	4,919	$0.40 / $2	1M
36	2345	gpt-5-chat OpenAI · Proprietary	1245±9	10,825	$1.25 / $10	128K
37	2948	gpt-5.2 OpenAI · Proprietary	1241±7	10,908	$1.75 / $14	400K
38	2850	glm-5v-turbo Z.ai · Proprietary	1241±9	5,220	$1.20 / $4	202.8K
39	2550	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1240±12	2,794	$0.30 / $2.50	1M
40	3150	qwen3.5-122b-a10b Alibaba · Apache 2.0	1236±8	6,872	$0.26 / $2.08	262.1K
41	3352	qwen3.5-27b Alibaba · Apache 2.0	1235±8	6,460	$0.20 / $1.56	262.1K
42	3054	ernie-5.0-preview-1220 Baidu · Proprietary	1232±14	1,894	N/A	N/A
43	3453	gpt-5-high OpenAI · Proprietary	1231±9	10,884	$1.25 / $10	400K
44	3453	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1230±8	7,620	$0.20 / $0.88	262.1K
45	3453	mimo-v2-omni Xiaomi · Proprietary	1228±9	5,180	$0.40 / $2	262.1K
46	3754	gpt-4.1-2025-04-14 OpenAI · Proprietary	1226±9	11,615	$2 / $8	1M
47	3855	o3-2025-04-16 OpenAI · Proprietary	1224±8	14,706	$2 / $8	200K
48	4154	gemini-2.5-flash Google · Proprietary	1223±5	24,952	$0.30 / $2.50	1M
49	3860	qwen-vl-max-2025-08-13 Alibaba · Proprietary	1216±18	1,150	$0.52 / $2.08	131.1K
50	3762	claude-opus-4-20250514-thinking-16k Anthropic · Proprietary	1215±20	852	$15 / $75	200K
51	4259	gpt-5.4-nano-high OpenAI · Proprietary	1214±9	5,887	$0.20 / $1.25	400K
52	3764	claude-sonnet-4-20250514-thinking-32k Anthropic · Proprietary	1214±21	744	$3 / $15	1M
53	4560	o4-mini-2025-04-16 OpenAI · Proprietary	1210±9	12,075	$1.10 / $4.40	200K
54	4164	claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary	1209±19	887	$3 / $15	200K
55	4961	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1206±9	10,687	$0.40 / $1.60	1M
56	4865	qwen3-vl-235b-a22b-thinking Alibaba · Apache 2.0	1201±16	1,363	$0.26 / $2.60	131.1K
57	4965	gpt-5-mini-high OpenAI · Proprietary	1198±10	8,180	$0.25 / $2	400K
58	4966	claude-opus-4-20250514 Anthropic · Proprietary	1196±16	1,363	$15 / $75	200K
59	4973	claude-sonnet-4-20250514 Anthropic · Proprietary	1188±17	1,141	$3 / $15	1M
60	5368	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1188±9	10,720	$0.10 / $0.40	1M
61	5468	grok-4-1-fast-reasoning xAI · Proprietary	1187±8	7,259	$0.20 / $0.50	2M
62	5270	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1186±11	2,812	$0.10 / $0.40	1M
63	5075	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1184±19	915	$3 / $15	200K
64	5477	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1176±19	967	$3 / $15	200K
65	5875	grok-4-0709 xAI · Proprietary	1175±9	10,006	$3 / $15	256K
66	5975	mistral-medium-2508 Mistral · Proprietary	1173±7	13,456	$2.70 / $8.10	32K
67	5677	glm-4.6v Z.ai · MIT	1171±17	1,431	$0.30 / $0.90	131.1K
68	6177	gemini-2.0-flash-001 Google · Proprietary	1165±11	3,759	$0.10 / $0.40	1M
69	5978	hunyuan-vision-1.5-thinking Tencent · Proprietary	1164±15	1,408	N/A	N/A
70	6277	gemma-3-27b-it Google · Gemma	1162±10	6,359	$0.08 / $0.16	131.1K
71	6378	mistral-medium-2505 Mistral · Proprietary	1158±10	4,669	$0.40 / $2	131.1K
72	6280	gpt-5-nano-high OpenAI · Proprietary	1158±15	1,714	$0.05 / $0.40	400K
73	6181	glm-4.5v Z.ai · MIT	1158±17	1,223	$0.60 / $1.80	65.5K
74	6281	step-1o-turbo-202506 StepFun · Proprietary	1155±17	1,278	N/A	N/A
75	6681	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1153±11	3,165	$0.63 / $1.80	131.1K
76	6381	step-3 StepFun · Apache 2.0	1152±17	1,248	$0.57 / $1.42	65.5K
77	6681	hunyuan-large-vision Tencent · Proprietary	1145±20	815	N/A	N/A
78	7081	mistral-small-2506 Mistral · Apache 2.0	1141±11	4,184	$0.10 / $0.30	32K
79	7281	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1133±10	7,377	$0.10 / $0.30	32K
80	7381	llama-4-scout-17b-16e-instruct Meta · Llama	1129±12	2,864	$0.40 / $0.70	8.2K
81	7282	claude-3-5-haiku-20241022 Anthropic · Proprietary	1127±20	934	$0.80 / $4	200K
82	8182	molmo-2-8b Ai2 · Apache 2.0	1087±25	791	$0.20 / $0.20	36.9K

Vision Arena📝OCR

Default Leaderboard Plots

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

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)