Design Arena Leaderboard

312 models across 17 categories · 5.3M+ votes · Updated Jul 25, 2026

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

Full-Stack

31 models · 33,879 votes

#	Model	Provider	ELO ▼	Win%	Battles	CI 95%	Avg Time
1	Claude Fable 5	anthropic	1311	64.3%	820	±0.0	nullms
2	Claude Opus 4.8	anthropic	1307	63.4%	1,215	±0.0	nullms
3	Grok 4.5	xai	1298	62.2%	985	±0.0	nullms
4	GLM 5.2	zhipu	1288	63.8%	1,887	±0.0	nullms
5	Claude Sonnet 5	anthropic	1283	59.3%	773	±0.0	nullms
6	Claude Opus 4.6	anthropic	1279	68.6%	1,529	±0.0	nullms
7	Claude Sonnet 4.6	anthropic	1268	63.9%	2,004	±0.0	nullms
8	Gemini 3.5 Flash	google	1252	57.0%	3,534	±0.0	nullms
9	Kimi K2.7 Code	moonshot	1236	54.9%	1,956	±0.0	nullms
10	GLM 5.1	zhipu	1223	56.0%	3,084	±0.0	nullms
11	Kimi K2.6	moonshot	1219	55.9%	3,754	±0.0	nullms
12	Claude Opus 4.5	anthropic	1214	59.9%	1,410	±0.0	nullms
13	GPT-5.6 Sol	openai	1210	49.8%	1,416	±0.0	nullms
14	GLM 5V Turbo	zhipu	1209	52.9%	3,647	±0.0	nullms
15	GLM 5	zhipu	1179	51.8%	4,648	±0.0	nullms
16	Kimi K2.5 (Thinking)	moonshot	1173	54.2%	1,811	±0.0	nullms
17	GPT-5.5	openai	1140	43.3%	3,018	±0.0	nullms
18	Gemini 3 Pro Preview	google	1132	48.6%	2,272	±0.0	nullms
19	Gemini 3.1 Pro Preview	google	1126	43.4%	3,898	±0.0	nullms
20	Gemini 3 Flash Preview	google	1121	47.1%	2,377	±0.0	nullms
21	GPT-5.6 Terra	openai	1114	34.5%	911	±0.0	nullms
22	Grok 4.20 Reasoning	xai	1111	41.1%	2,430	±0.0	nullms
23	Claude Sonnet 4.5	anthropic	1110	43.5%	644	±0.0	nullms
24	GLM 4.7	zhipu	1108	44.9%	1,650	±0.0	nullms
25	GPT 5.2	openai	1100	44.0%	2,180	±0.0	nullms
26	GLM 4.6	zhipu	1089	42.3%	1,909	±0.0	nullms
27	GPT-5.4	openai	1076	40.8%	2,166	±0.0	nullms
28	Grok 4.3	xai	1068	31.4%	2,219	±0.0	nullms
29	Grok Code Fast 1	xai	1067	39.7%	2,005	±0.0	nullms
30	GPT-5.2 Codex	openai	1050	37.0%	2,169	±0.0	nullms
31	GPT-5.3 Codex	openai	1041	36.4%	1,117	±0.0	nullms