Vision Arena😄Humor

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

Jun 5, 2026

23,604 votes

63 models

Rank by

	Rank Spread
1	116	muse-spark Meta · Proprietary	1320±41	223	N/A	N/A
2	112	gemini-3-pro Google · Proprietary	1315±25	564	$2 / $12	1M
3	116	claude-opus-4-7-thinking Anthropic · Proprietary	1308±29	457	$5 / $25	1M
4	115	gemini-3.1-pro-preview Google · Proprietary	1305±20	916	$2 / $12	1M
5	122	claude-opus-4-6 Anthropic · Proprietary	1299±27	527	$5 / $25	1M
6	125	claude-opus-4-6-thinking Anthropic · Proprietary	1297±30	413	$5 / $25	1M
7	134	gpt-5.5-instant OpenAI · Proprietary	1294±41	244	$5 / $30	1.1M
8	125	claude-opus-4-7 Anthropic · Proprietary	1293±29	434	$5 / $25	1M
9	137	gpt-5.5-high OpenAI · Proprietary	1277±34	306	$5 / $30	1.1M
10	137	gpt-5.5 OpenAI · Proprietary	1275±34	328	$5 / $30	1.1M
11	236	gemini-3-flash Google · Proprietary	1266±20	916	$0.50 / $3	1M
12	139	kimi-k2.6 Moonshot · Modified MIT	1263±33	324	$0.95 / $4	262.1K
13	238	grok-4.20-beta-0309-reasoning xAI · Proprietary	1261±27	483	$2 / $6	2M
14	140	gpt-5.4 OpenAI · Proprietary	1259±32	370	$2.50 / $15	1.1M
15	338	kimi-k2.5-thinking Moonshot · Modified MIT	1259±23	644	$0.60 / $3	N/A
16	240	dola-seed-2.0-pro Bytedance · Proprietary	1257±31	371	N/A	N/A
17	539	gemini-3.1-flash-lite-preview Google · Proprietary	1254±23	662	$0.25 / $1.50	1M
18	639	gemma-4-31b Google · Apache 2.0	1251±19	981	$0.14 / $0.40	262.1K
19	540	qwen3.5-397b-a17b Alibaba · Apache 2.0	1249±26	519	$0.39 / $2.34	262.1K
20	640	gemma-4-26b-a4b Google · Apache 2.0	1245±24	625	N/A	N/A
21	840	gemini-3-flash (thinking-minimal) Google · Proprietary	1245±20	859	$0.50 / $3	1M
22	542	grok-4.20-multi-agent-beta-0309 xAI · Proprietary	1244±28	468	$2 / $6	2M
23	839	gemini-2.5-pro Google · Proprietary	1244±14	3,085	$1.25 / $10	1M
24	642	glm-5v-turbo Z.ai · Proprietary	1243±28	485	$1.20 / $4	202.8K
25	545	gpt-5.1 OpenAI · Proprietary	1242±33	333	$1.25 / $10	400K
26	544	gpt-5.4-mini-high OpenAI · Proprietary	1242±30	435	$0.75 / $4.50	400K
27	548	grok-4.3 xAI · Proprietary	1238±36	279	$1.25 / $2.50	1M
28	849	gpt-5.4-high OpenAI · Proprietary	1231±33	355	$2.50 / $15	1.1M
29	847	gpt-5.2-chat-latest-20260210 OpenAI · Proprietary	1231±27	493	$1.75 / $14	128K
30	848	qwen3.5-122b-a10b Alibaba · Apache 2.0	1231±29	407	$0.26 / $2.08	262.1K
31	847	mimo-v2.5 Xiaomi · MIT	1231±28	463	$0.14 / $0.28	1M
32	849	gpt-5.1-high OpenAI · Proprietary	1229±32	290	$1.25 / $10	400K
33	847	claude-sonnet-4-6 Anthropic · Proprietary	1229±27	518	$3 / $15	1M
34	947	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1228±22	773	$5 / $15	128K
35	851	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1226±37	216	$0.30 / $2.50	1M
36	951	grok-4-1-fast-reasoning xAI · Proprietary	1218±30	428	$0.20 / $0.50	2M
37	1053	qwen3.5-27b Alibaba · Apache 2.0	1215±28	454	$0.20 / $1.56	262.1K
38	1251	gpt-5.2-high OpenAI · Proprietary	1215±25	609	$1.75 / $14	400K
39	1449	o3-2025-04-16 OpenAI · Proprietary	1213±19	1,682	$2 / $8	200K
40	1853	gpt-5-high OpenAI · Proprietary	1206±22	1,323	$1.25 / $10	400K
41	2351	gemini-2.5-flash Google · Proprietary	1205±15	2,140	$0.30 / $2.50	1M
42	2353	gpt-5-chat OpenAI · Proprietary	1200±19	1,479	$1.25 / $10	128K
43	2553	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1193±20	1,441	$0.40 / $1.60	1M
44	2655	o4-mini-2025-04-16 OpenAI · Proprietary	1192±19	1,499	$1.10 / $4.40	200K
45	2555	gpt-5-mini-high OpenAI · Proprietary	1189±24	1,078	$0.25 / $2	400K
46	2755	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1188±19	1,431	$0.10 / $0.40	1M
47	3356	gpt-4.1-2025-04-14 OpenAI · Proprietary	1180±19	1,408	$2 / $8	1M
48	3159	gpt-5.2 OpenAI · Proprietary	1177±25	583	$1.75 / $14	400K
49	3659	grok-4-0709 xAI · Proprietary	1171±20	1,223	$3 / $15	256K
50	2763	gemini-2.0-flash-001 Google · Proprietary	1167±41	228	$0.10 / $0.40	1M
51	4062	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1160±27	456	$0.20 / $0.88	262.1K
52	3663	mimo-v2-omni Xiaomi · Proprietary	1158±34	328	$0.40 / $2	262.1K
53	4463	gemma-3-27b-it Google · Gemma	1149±23	781	$0.08 / $0.16	131.1K
54	4063	ernie-5.0-preview-1220 Baidu · Proprietary	1145±43	169	N/A	N/A
55	4863	mistral-medium-2508 Mistral · Proprietary	1142±18	1,501	$2.70 / $8.10	32K
56	4463	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1136±37	214	$0.10 / $0.40	1M
57	4763	gpt-5.4-nano-high OpenAI · Proprietary	1136±30	457	$0.20 / $1.25	400K
58	4863	mistral-small-2506 Mistral · Apache 2.0	1126±28	499	$0.10 / $0.30	32K
59	4863	mistral-medium-2505 Mistral · Proprietary	1123±29	448	$0.40 / $2	131.1K
60	5063	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1115±22	965	$0.10 / $0.30	32K
61	5063	llama-4-scout-17b-16e-instruct Meta · Llama	1097±43	195	$0.40 / $0.70	8.2K
62	5063	gpt-5-nano-high OpenAI · Proprietary	1095±47	179	$0.05 / $0.40	400K
63	5163	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1090±39	223	$0.63 / $1.80	131.1K

Vision Arena😄Humor

Default Leaderboard Plots

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

Battle Count for Each Combination of Models (without Ties)