Vision Arena📝OCR

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

Mar 31, 2026

223,150 votes

66 models

	Rank Spread
1	16	claude-opus-4-6 Anthropic · Proprietary	1314±20	905	$5 / $25	1M
2	16	gemini-3-pro Google · Proprietary	1302±8	8,342	$2 / $12	1M
3	17	gemini-3.1-pro-preview Google · Proprietary	1299±9	6,000	$2 / $12	1M
4	19	claude-opus-4-6-thinking Anthropic · Proprietary	1297±20	869	$5 / $25	1M
5	111	claude-sonnet-4-6 Anthropic · Proprietary	1288±18	1,128	$3 / $15	1M
6	19	gpt-5.2-chat-latest-20260210 OpenAI · Proprietary	1287±10	3,806	$1.75 / $14	128K
7	39	gemini-3-flash Google · Proprietary	1282±8	9,885	$0.50 / $3	1M
8	415	gemini-3-flash (thinking-minimal) Google · Proprietary	1269±8	8,665	$0.50 / $3	1M
9	418	dola-seed-2.0-preview Bytedance · Proprietary	1267±11	3,190	N/A	N/A
10	720	gpt-5.2-high OpenAI · Proprietary	1263±9	5,824	$1.75 / $14	400K
11	721	kimi-k2.5-thinking Moonshot · Modified MIT	1262±9	5,719	$0.60 / $3	N/A
12	821	gemini-2.5-pro Google · Proprietary	1259±6	27,177	$1.25 / $10	1M
13	823	qwen3.5-397b-a17b Alibaba · Apache 2.0	1258±10	4,059	$0.39 / $2.34	262.1K
14	823	gpt-5.1-high OpenAI · Proprietary	1258±9	5,883	$1.25 / $10	400K
15	926	gpt-5.1 OpenAI · Proprietary	1249±9	6,620	$1.25 / $10	400K
16	834	gpt-5.4-mini-high OpenAI · Proprietary	1249±17	1,304	$0.75 / $4.50	400K
17	929	kimi-k2.5-instant Moonshot · Modified MIT	1248±12	2,666	$0.38 / $1.72	262.1K
18	1026	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1248±7	11,426	$5 / $15	128K
19	1029	gemini-3.1-flash-lite-preview Google · Proprietary	1245±10	5,126	$0.25 / $1.50	1M
20	1129	gpt-5-chat OpenAI · Proprietary	1245±9	11,091	$1.25 / $10	128K
21	933	qwen3.5-27b Alibaba · Apache 2.0	1245±12	2,568	$0.20 / $1.56	262.1K
22	1335	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1240±11	2,868	$0.30 / $2.50	1M
23	1336	grok-4.20-beta-0309-reasoning xAI · Proprietary	1239±14	1,942	$2 / $6	2M
24	1536	gpt-5.2 OpenAI · Proprietary	1237±9	6,323	$1.75 / $14	400K
25	1536	qwen3.5-122b-a10b Alibaba · Apache 2.0	1236±12	2,704	$0.26 / $2.08	262.1K
26	1536	ernie-5.0-preview-1220 Baidu · Proprietary	1234±14	1,930	N/A	N/A
27	1736	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1232±8	7,770	$0.20 / $0.88	262.1K
28	1736	gpt-5-high OpenAI · Proprietary	1231±9	11,121	$1.25 / $10	400K
29	2237	gemini-2.5-flash Google · Proprietary	1225±6	21,110	$0.30 / $2.50	1M
30	2038	gpt-4.1-2025-04-14 OpenAI · Proprietary	1225±8	11,908	$2 / $8	1M
31	2138	o3-2025-04-16 OpenAI · Proprietary	1224±8	15,020	$2 / $8	200K
32	1742	grok-4.20-multi-agent-beta-0309 xAI · Proprietary	1222±15	1,665	$2 / $6	2M
33	2044	qwen-vl-max-2025-08-13 Alibaba · Proprietary	1218±17	1,165	$0.52 / $2.08	131.1K
34	2046	claude-opus-4-20250514-thinking-16k Anthropic · Proprietary	1216±20	873	$15 / $75	200K
35	2047	claude-sonnet-4-20250514-thinking-32k Anthropic · Proprietary	1214±21	766	$3 / $15	1M
36	3044	o4-mini-2025-04-16 OpenAI · Proprietary	1210±9	12,408	$1.10 / $4.40	200K
37	2347	claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary	1209±19	905	$3 / $15	200K
38	3246	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1205±9	10,944	$0.40 / $1.60	1M
39	2947	qwen3-vl-235b-a22b-thinking Alibaba · Apache 2.0	1204±15	1,391	$0.26 / $2.60	131.1K
40	3247	gpt-5-mini-high OpenAI · Proprietary	1201±10	8,392	$0.25 / $2	400K
41	3251	gpt-5.4-nano-high OpenAI · Proprietary	1197±18	1,234	$0.20 / $1.25	400K
42	3250	claude-opus-4-20250514 Anthropic · Proprietary	1196±16	1,397	$15 / $75	200K
43	3551	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1188±9	10,958	$0.10 / $0.40	1M
44	3357	claude-sonnet-4-20250514 Anthropic · Proprietary	1188±17	1,158	$3 / $15	1M
45	3552	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1186±11	2,886	$0.10 / $0.40	1M
46	3360	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1184±19	939	$3 / $15	200K
47	4159	grok-4-0709 xAI · Proprietary	1177±9	10,248	$3 / $15	256K
48	3761	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1175±19	995	$6 / $30	200K
49	4260	mistral-medium-2508 Mistral · Proprietary	1173±7	13,769	$2.70 / $8.10	32K
50	4161	glm-4.6v Z.ai · MIT	1171±16	1,455	$0.30 / $0.90	131.1K
51	4162	hunyuan-vision-1.5-thinking Tencent · Proprietary	1166±15	1,433	N/A	N/A
52	4461	gemini-2.0-flash-001 Google · Proprietary	1164±11	3,834	$0.10 / $0.40	1M
53	4561	gemma-3-27b-it Google · Gemma	1162±10	6,503	$0.08 / $0.16	131.1K
54	4562	grok-4-1-fast-reasoning xAI · Proprietary	1160±12	2,990	$0.20 / $0.50	2M
55	4662	mistral-medium-2505 Mistral · Proprietary	1159±10	4,761	$0.40 / $2	131.1K
56	4564	gpt-5-nano-high OpenAI · Proprietary	1159±15	1,748	$0.05 / $0.40	400K
57	4564	glm-4.5v Z.ai · MIT	1157±17	1,244	$0.60 / $1.80	65.5K
58	4565	step-1o-turbo-202506 StepFun · Proprietary	1156±17	1,307	N/A	N/A
59	4665	step-3 StepFun · Apache 2.0	1153±17	1,276	$0.57 / $1.42	65.5K
60	4964	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1152±11	3,237	$0.63 / $1.80	131.1K
61	4765	hunyuan-large-vision Tencent · Proprietary	1146±20	835	N/A	N/A
62	5365	mistral-small-2506 Mistral · Apache 2.0	1141±11	4,283	$0.10 / $0.30	32K
63	5665	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1134±10	7,548	$0.10 / $0.30	32K
64	5965	llama-4-scout-17b-16e-instruct Meta · Llama	1129±12	2,927	$0.40 / $0.70	8.2K
65	5666	claude-3-5-haiku-20241022 Anthropic · Proprietary	1125±19	951	$0.80 / $4	200K
66	6566	molmo-2-8b Ai2 · Apache 2.0	1081±24	813	$0.20 / $0.20	36.9K

Vision Arena📝OCR

Default Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

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)