Design Arena Leaderboard

432 models across 23 categories · 8.0M+ votes · Updated Sep 23, 2026

Crowdsourced design benchmark from designarena.ai — ELO ratings based on real user preferences

Full-Stack

47 models · 58,172 votes

#	Model	Provider	ELO ▼	Win%	Battles	CI 95%	Avg Time
1	GPT-6 Astra (xhigh)	openai	1360	59.9%	516	±16.0	nullms
2	Claude Fable 5.1	anthropic	1336	57.3%	520	±15.8	nullms
3	Kimi K3	moonshot	1328	62.2%	1,248	±10.6	nullms
4	Muse Spark 1.3 Max	meta	1319	60.1%	4,808	±5.9	nullms
5	Qwen3.8 Max	alibaba	1317	62.3%	1,305	±10.3	nullms
6	Claude Opus 5	anthropic	1312	56.5%	1,138	±11.0	nullms
7	Muse Spark 1.3 (xhigh)	meta	1305	56.0%	3,984	±6.4	nullms
8	Claude Fable 5	anthropic	1289	58.3%	2,070	±8.3	nullms
9	Grok 4.6	xai	1274	54.9%	4,598	±5.9	nullms
10	GPT-5.6 Sol (xhigh)	openai	1272	54.7%	1,886	±8.7	nullms
11	Claude Sonnet 5	anthropic	1260	54.0%	3,431	±6.6	nullms
12	Grok 4.5	xai	1259	61.0%	2,671	±7.6	nullms
13	Claude Opus 4.8	anthropic	1257	55.1%	2,616	±7.4	nullms
14	GLM 5.2	zhipu	1252	61.0%	2,674	±7.4	nullms
15	Gemini 3.8 Flash	google	1251	47.9%	1,107	±11.0	nullms
16	Claude Opus 4.6	anthropic	1230	60.1%	2,454	±7.7	nullms
17	Claude Sonnet 4.6	anthropic	1223	64.3%	2,030	±8.6	nullms
18	Muse Spark 1.2	meta	1219	47.9%	1,813	±8.6	nullms
19	Gemini 3.7 Flash	google	1217	43.4%	618	±14.4	nullms
20	Gemini 3.5 Flash	google	1208	56.5%	3,959	±6.2	nullms
21	Muse Spark 1.1	meta	1205	45.1%	1,407	±9.8	nullms
22	MiniMax M3	minimax	1204	47.2%	3,108	±6.8	nullms
23	Qwen3.7 Max	alibaba	1202	48.2%	1,337	±10.0	nullms
24	Gemini 3.6 Flash	google	1191	44.3%	2,836	±7.1	nullms
25	Kimi K2.7 Code	moonshot	1186	51.1%	2,733	±7.2	nullms
26	GLM 5.1	zhipu	1177	53.3%	3,851	±6.1	nullms
27	GPT-5.6 Sol (Medium)	openai	1169	49.8%	1,612	±9.2	nullms
28	Claude Opus 4.5	anthropic	1167	60.2%	1,395	±10.0	nullms
29	Kimi K2.6	moonshot	1165	49.8%	5,727	±5.2	nullms
30	GLM 5V Turbo	zhipu	1159	52.1%	3,941	±6.3	nullms
31	GLM 5	zhipu	1133	51.7%	4,764	±5.7	nullms
32	Kimi K2.5 (Thinking)	moonshot	1124	54.5%	1,787	±8.8	nullms
33	GPT-5.5	openai	1100	43.0%	3,537	±6.5	nullms
34	Gemini 3 Pro Preview	google	1084	48.7%	2,259	±7.9	nullms
35	Gemini 3.1 Pro Preview	google	1079	41.1%	4,744	±5.7	nullms
36	Gemini 3 Flash Preview	google	1073	47.4%	2,358	±7.8	nullms
37	GPT-5.6 Terra	openai	1072	31.1%	2,511	±8.1	nullms
38	Grok 4.20 Reasoning	xai	1064	41.0%	2,424	±7.7	nullms
39	Claude Sonnet 4.5	anthropic	1060	43.7%	629	±14.3	nullms
40	GLM 4.7	zhipu	1060	45.1%	1,638	±9.2	nullms
41	GPT 5.2	openai	1053	44.3%	2,165	±8.1	nullms
42	GLM 4.6	zhipu	1039	42.3%	1,885	±8.6	nullms
43	GPT-5.4	openai	1027	40.8%	2,151	±8.2	nullms
44	Grok Code Fast 1	xai	1019	39.7%	2,004	±8.5	nullms
45	Grok 4.3	xai	1016	28.2%	3,357	±7.1	nullms
46	GPT-5.2 Codex	openai	1003	37.2%	2,157	±8.3	nullms
47	GPT-5.3 Codex	openai	993	36.5%	1,109	±11.3	nullms