Vision Arena✍️Creative Writing

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

Jun 5, 2026

33,813 votes

67 models

Rank by

	Rank Spread
1	16	gemini-3-pro Google · Proprietary	1333±19	1,038	$2 / $12	1M
2	113	claude-opus-4-6-thinking Anthropic · Proprietary	1319±24	697	$5 / $25	1M
3	114	claude-opus-4-7-thinking Anthropic · Proprietary	1311±24	679	$5 / $25	1M
4	126	muse-spark Meta · Proprietary	1304±34	333	N/A	N/A
5	119	claude-opus-4-6 Anthropic · Proprietary	1300±21	905	$5 / $25	1M
6	124	claude-opus-4-7 Anthropic · Proprietary	1297±24	661	$5 / $25	1M
7	220	gemini-3.1-pro-preview Google · Proprietary	1292±17	1,418	$2 / $12	1M
8	228	gemini-3-flash (thinking-minimal) Google · Proprietary	1283±15	1,569	$0.50 / $3	1M
9	330	gemini-3-flash Google · Proprietary	1280±15	1,761	$0.50 / $3	1M
10	231	grok-4.20-beta-0309-reasoning xAI · Proprietary	1278±21	875	$2 / $6	2M
11	231	grok-4.20-multi-agent-beta-0309 xAI · Proprietary	1278±22	837	$2 / $6	2M
12	238	gpt-5.5-high OpenAI · Proprietary	1273±28	506	$5 / $30	1.1M
13	438	claude-sonnet-4-6 Anthropic · Proprietary	1266±21	855	$3 / $15	1M
14	438	qwen3.5-397b-a17b Alibaba · Apache 2.0	1264±20	943	$0.39 / $2.34	262.1K
15	438	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1263±18	1,158	$5 / $15	128K
16	249	gpt-5.5-instant OpenAI · Proprietary	1261±34	330	$5 / $30	1.1M
17	838	gemini-2.5-pro Google · Proprietary	1257±12	3,504	$1.25 / $10	1M
18	447	gpt-5.5 OpenAI · Proprietary	1256±27	537	$5 / $30	1.1M
19	741	gemma-4-31b Google · Apache 2.0	1254±16	1,486	$0.14 / $0.40	262.1K
20	449	kimi-k2.6 Moonshot · Modified MIT	1253±27	483	$0.95 / $4	262.1K
21	549	gpt-5.4 OpenAI · Proprietary	1253±25	601	$2.50 / $15	1.1M
22	649	gpt-5.1 OpenAI · Proprietary	1251±23	696	$1.25 / $10	400K
23	257	claude-opus-4-20250514 Anthropic · Proprietary	1249±46	106	$15 / $75	200K
24	651	gpt-5.4-high OpenAI · Proprietary	1248±26	578	$2.50 / $15	1.1M
25	652	grok-4.3 xAI · Proprietary	1244±29	474	$1.25 / $2.50	1M
26	952	grok-4-1-fast-reasoning xAI · Proprietary	1243±23	743	$0.20 / $0.50	2M
27	952	gpt-5.1-high OpenAI · Proprietary	1243±23	636	$1.25 / $10	400K
28	655	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1240±33	294	$0.30 / $2.50	1M
29	853	dola-seed-2.0-pro Bytedance · Proprietary	1240±29	462	N/A	N/A
30	1051	kimi-k2.5-thinking Moonshot · Modified MIT	1240±18	1,040	$0.60 / $3	N/A
31	758	kimi-k2.5-instant Moonshot · Modified MIT	1236±36	247	$0.40 / $1.90	262.1K
32	1253	gpt-5.2-chat-latest-20260210 OpenAI · Proprietary	1235±21	885	$1.75 / $14	128K
33	1253	gpt-5.4-mini-high OpenAI · Proprietary	1234±22	834	$0.75 / $4.50	400K
34	1253	gemma-4-26b-a4b Google · Apache 2.0	1233±20	941	N/A	N/A
35	1253	gemini-3.1-flash-lite-preview Google · Proprietary	1231±18	1,202	$0.25 / $1.50	1M
36	1752	gemini-2.5-flash Google · Proprietary	1228±12	2,724	$0.30 / $2.50	1M
37	1254	gpt-4.1-2025-04-14 OpenAI · Proprietary	1227±19	1,279	$2 / $8	1M
38	1257	glm-5v-turbo Z.ai · Proprietary	1226±22	786	$1.20 / $4	202.8K
39	1758	gpt-5.2 OpenAI · Proprietary	1220±19	1,059	$1.75 / $14	400K
40	1858	gpt-5-chat OpenAI · Proprietary	1218±19	1,291	$1.25 / $10	128K
41	1858	gpt-5.2-high OpenAI · Proprietary	1216±18	1,115	$1.75 / $14	400K
42	1859	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1214±20	1,187	$0.40 / $1.60	1M
43	1859	grok-4-0709 xAI · Proprietary	1212±19	1,263	$3 / $15	256K
44	1860	mimo-v2.5 Xiaomi · MIT	1212±25	636	$0.14 / $0.28	1M
45	1860	qwen3.5-122b-a10b Alibaba · Apache 2.0	1210±22	734	$0.26 / $2.08	262.1K
46	1763	ernie-5.0-preview-1220 Baidu · Proprietary	1208±31	383	N/A	N/A
47	2359	o3-2025-04-16 OpenAI · Proprietary	1208±18	1,603	$2 / $8	200K
48	1961	qwen3.5-27b Alibaba · Apache 2.0	1206±22	773	$0.20 / $1.56	262.1K
49	1265	mistral-medium-3.5 Mistral · Modified MIT	1204±43	209	$1.50 / $7.50	262.1K
50	2562	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1200±21	819	$0.20 / $0.88	262.1K
51	2365	mistral-small-2506 Mistral · Apache 2.0	1197±29	461	$0.10 / $0.30	32K
52	3464	mistral-medium-2508 Mistral · Proprietary	1193±17	1,505	$2.70 / $8.10	32K
53	1966	gemini-2.0-flash-001 Google · Proprietary	1189±39	246	$0.10 / $0.40	1M
54	3565	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1188±20	1,207	$0.10 / $0.40	1M
55	3665	gpt-5-high OpenAI · Proprietary	1185±20	1,439	$1.25 / $10	400K
56	2966	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1182±32	316	$0.10 / $0.40	1M
57	3666	mimo-v2-omni Xiaomi · Proprietary	1179±26	573	$0.40 / $2	262.1K
58	3866	gemma-3-27b-it Google · Gemma	1176±25	630	$0.08 / $0.16	131.1K
59	4265	o4-mini-2025-04-16 OpenAI · Proprietary	1176±19	1,257	$1.10 / $4.40	200K
60	4767	gpt-5-mini-high OpenAI · Proprietary	1162±23	1,007	$0.25 / $2	400K
61	4867	gpt-5.4-nano-high OpenAI · Proprietary	1160±23	780	$0.20 / $1.25	400K
62	5067	mistral-medium-2505 Mistral · Proprietary	1149±28	487	$0.40 / $2	131.1K
63	4567	llama-4-scout-17b-16e-instruct Meta · Llama	1148±41	234	$0.40 / $0.70	8.2K
64	4967	glm-4.6v Z.ai · MIT	1135±44	195	$0.30 / $0.90	131.1K
65	5167	hunyuan-vision-1.5-thinking Tencent · Proprietary	1129±44	192	N/A	N/A
66	6067	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1119±24	783	$0.10 / $0.30	32K
67	5667	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1113±42	212	$0.63 / $1.80	131.1K

Vision Arena✍️Creative Writing

Default Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

Confidence Intervals on Model Strength (via Bootstrapping)

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