Vision Arena📚Homework

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

Jun 5, 2026

78,605 votes

83 models

Rank by

	Rank Spread
1	111	gpt-5.5-high OpenAI · Proprietary	1341±17	1,433	$5 / $30	1.1M
2	114	claude-opus-4-7 Anthropic · Proprietary	1333±14	1,985	$5 / $25	1M
3	117	gpt-5.5 OpenAI · Proprietary	1330±17	1,487	$5 / $30	1.1M
4	128	claude-opus-4-8-thinking Anthropic · Proprietary	1326±31	366	$5 / $25	1M
5	118	claude-opus-4-7-thinking Anthropic · Proprietary	1323±15	1,867	$5 / $25	1M
6	120	claude-opus-4-6-thinking Anthropic · Proprietary	1322±15	1,840	$5 / $25	1M
7	120	gpt-5.4-high OpenAI · Proprietary	1321±15	1,762	$2.50 / $15	1.1M
8	122	claude-opus-4-6 Anthropic · Proprietary	1316±13	2,380	$5 / $25	1M
9	124	gpt-5.4 OpenAI · Proprietary	1314±15	1,789	$2.50 / $15	1.1M
10	221	gemini-3-flash Google · Proprietary	1314±10	3,999	$0.50 / $3	1M
11	223	gemini-3.1-pro-preview Google · Proprietary	1311±11	3,684	$2 / $12	1M
12	125	gemini-3-pro Google · Proprietary	1311±14	1,797	$2 / $12	1M
13	230	kimi-k2.6 Moonshot · Modified MIT	1306±16	1,539	$0.95 / $4	262.1K
14	331	claude-sonnet-4-6 Anthropic · Proprietary	1302±13	2,410	$3 / $15	1M
15	334	muse-spark Meta · Proprietary	1299±20	910	N/A	N/A
16	531	gemma-4-31b Google · Apache 2.0	1297±10	4,477	$0.14 / $0.40	262.1K
17	144	claude-opus-4-8 Anthropic · Proprietary	1296±28	441	$5 / $25	1M
18	533	gpt-5.2-chat-latest-20260210 OpenAI · Proprietary	1294±13	2,394	$1.75 / $14	128K
19	833	gemini-3-flash (thinking-minimal) Google · Proprietary	1293±10	3,732	$0.50 / $3	1M
20	736	gpt-5.4-mini-high OpenAI · Proprietary	1291±14	2,201	$0.75 / $4.50	400K
21	353	minimax-m3 MiniMax · Proprietary	1288±30	422	$0.60 / $2.40	N/A
22	1036	kimi-k2.5-thinking Moonshot · Modified MIT	1288±12	2,633	$0.60 / $3	N/A
23	448	qwen3.7-plus-preview Alibaba · Proprietary	1288±24	642	$0.40 / $1.60	1M
24	1243	gemma-4-26b-a4b Google · Apache 2.0	1283±12	2,744	N/A	N/A
25	1343	gpt-5.2-high OpenAI · Proprietary	1283±12	2,810	$1.75 / $14	400K
26	1243	qwen3.5-397b-a17b Alibaba · Apache 2.0	1283±13	2,279	$0.39 / $2.34	262.1K
27	950	gpt-5.5-instant OpenAI · Proprietary	1282±19	1,129	$5 / $30	1.1M
28	1147	gpt-5.1-high OpenAI · Proprietary	1282±16	1,211	$1.25 / $10	400K
29	1246	dola-seed-2.0-pro Bytedance · Proprietary	1281±15	1,746	N/A	N/A
30	1352	gpt-5-chat OpenAI · Proprietary	1276±16	1,348	$1.25 / $10	128K
31	1650	gemini-3.1-flash-lite-preview Google · Proprietary	1275±12	3,014	$0.25 / $1.50	1M
32	1849	gemini-2.5-pro Google · Proprietary	1272±9	5,410	$1.25 / $10	1M
33	1654	grok-4.20-multi-agent-beta-0309 xAI · Proprietary	1270±14	2,180	$2 / $6	2M
34	1955	gpt-5.2 OpenAI · Proprietary	1267±12	2,919	$1.75 / $14	400K
35	1462	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1266±22	624	$0.30 / $2.50	1M
36	1960	grok-4.3 xAI · Proprietary	1262±17	1,356	$1.25 / $2.50	1M
37	2158	grok-4.20-beta-0309-reasoning xAI · Proprietary	1262±13	2,302	$2 / $6	2M
38	2158	mimo-v2.5 Xiaomi · MIT	1261±14	2,073	$0.14 / $0.28	1M
39	2160	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1260±14	1,614	$0.20 / $0.88	262.1K
40	2162	glm-5v-turbo Z.ai · Proprietary	1259±14	2,152	$1.20 / $4	202.8K
41	2162	gpt-5-high OpenAI · Proprietary	1257±16	1,486	$1.25 / $10	400K
42	2562	qwen3.5-122b-a10b Alibaba · Apache 2.0	1253±14	1,856	$0.26 / $2.08	262.1K
43	2462	gpt-5.1 OpenAI · Proprietary	1253±15	1,401	$1.25 / $10	400K
44	2163	kimi-k2.5-instant Moonshot · Modified MIT	1250±24	563	$0.40 / $1.90	262.1K
45	2863	o4-mini-2025-04-16 OpenAI · Proprietary	1249±15	1,656	$1.10 / $4.40	200K
46	2763	mimo-v2-omni Xiaomi · Proprietary	1248±16	1,561	$0.40 / $2	262.1K
47	2963	gpt-4.1-2025-04-14 OpenAI · Proprietary	1248±16	1,538	$2 / $8	1M
48	3263	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1247±13	2,170	$5 / $15	128K
49	3163	o3-2025-04-16 OpenAI · Proprietary	1247±14	2,023	$2 / $8	200K
50	2166	ernie-5.0-preview-1220 Baidu · Proprietary	1242±29	361	N/A	N/A
51	3563	qwen3.5-27b Alibaba · Apache 2.0	1241±14	1,979	$0.20 / $1.56	262.1K
52	3763	gemini-2.5-flash Google · Proprietary	1237±9	4,866	$0.30 / $2.50	1M
53	2570	claude-opus-4-20250514 Anthropic · Proprietary	1235±31	334	$15 / $75	200K
54	2670	hunyuan-vision-1.5-thinking Tencent · Proprietary	1234±32	312	N/A	N/A
55	3964	gpt-5.4-nano-high OpenAI · Proprietary	1232±14	2,177	$0.20 / $1.25	400K
56	3566	gpt-5-mini-high OpenAI · Proprietary	1231±19	1,013	$0.25 / $2	400K
57	3371	qwen3-vl-235b-a22b-thinking Alibaba · Apache 2.0	1227±31	311	$0.26 / $2.60	131.1K
58	3474	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1221±35	240	$3 / $15	200K
59	4470	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1220±16	1,351	$0.40 / $1.60	1M
60	3771	mistral-medium-3.5 Mistral · Modified MIT	1220±27	564	$1.50 / $7.50	262.1K
61	3576	claude-sonnet-4-20250514 Anthropic · Proprietary	1219±35	244	$3 / $15	1M
62	3182	claude-opus-4-20250514-thinking-16k Anthropic · Proprietary	1216±44	170	$15 / $75	200K
63	3982	claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary	1205±40	183	$3 / $15	200K
64	5280	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1197±22	620	$0.10 / $0.40	1M
65	5582	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1188±16	1,378	$0.10 / $0.40	1M
66	5582	gemini-2.0-flash-001 Google · Proprietary	1187±21	789	$0.10 / $0.40	1M
67	5382	gpt-5-nano-high OpenAI · Proprietary	1181±34	271	$0.05 / $0.40	400K
68	5382	step-3 StepFun · Apache 2.0	1179±38	226	$0.57 / $1.42	65.5K
69	5882	mistral-small-2506 Mistral · Apache 2.0	1174±23	632	$0.10 / $0.30	32K
70	6082	grok-4-0709 xAI · Proprietary	1171±18	1,124	$3 / $15	256K
71	6182	grok-4-1-fast-reasoning xAI · Proprietary	1170±15	1,950	$0.20 / $0.50	2M
72	6082	gemma-3-27b-it Google · Gemma	1169±18	1,068	$0.08 / $0.16	131.1K
73	5583	glm-4.5v Z.ai · MIT	1169±38	222	$0.60 / $1.80	65.5K
74	6282	mistral-medium-2508 Mistral · Proprietary	1168±13	2,183	$2.70 / $8.10	32K
75	5583	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1167±38	224	$3 / $15	200K
76	6282	mistral-medium-2505 Mistral · Proprietary	1163±20	843	$0.40 / $2	131.1K
77	6183	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1161±24	549	$0.63 / $1.80	131.1K
78	6283	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1157±20	840	$0.10 / $0.30	32K
79	6083	glm-4.6v Z.ai · MIT	1153±36	283	$0.30 / $0.90	131.1K
80	6383	llama-4-scout-17b-16e-instruct Meta · Llama	1149±25	496	$0.40 / $0.70	8.2K
81	6283	claude-3-5-haiku-20241022 Anthropic · Proprietary	1142±38	232	$0.80 / $4	200K
82	6383	step-1o-turbo-202506 StepFun · Proprietary	1138±35	250	N/A	N/A
83	7583	molmo-2-8b Ai2 · Apache 2.0	1089±51	186	$0.20 / $0.20	36.9K

Vision Arena📚Homework

Default Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

Confidence Intervals on Model Strength (via Bootstrapping)

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)