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

Mobile (React Native)

46 models · 33,198 votes

#	Model	Provider	ELO ▼	Win%	Battles	CI 95%	Avg Time
1	Claude Fable 5	anthropic	1292	60.8%	687	±13.8	nullms
2	Kimi K3	moonshot	1281	57.6%	779	±12.9	nullms
3	GPT-6 Astra (xhigh)	openai	1273	56.0%	343	±19.1	nullms
4	Grok 4.6	xai	1267	57.4%	2,164	±8.1	nullms
5	GPT-5.6 Sol (xhigh)	openai	1264	55.4%	748	±13.1	nullms
6	Gemini 3.7 Flash	google	1262	53.5%	477	±16.2	nullms
7	Gemini 3.8 Flash	google	1257	55.4%	3,602	±6.7	nullms
8	Qwen3.8 Max	alibaba	1255	55.5%	1,406	±9.7	nullms
9	Claude Opus 4.8	anthropic	1254	56.3%	1,068	±10.9	nullms
10	Claude Sonnet 5	anthropic	1245	53.3%	1,392	±9.8	nullms
11	Grok 4.5	xai	1245	53.1%	881	±12.1	nullms
12	Claude Sonnet 4.6	anthropic	1242	63.6%	1,558	±9.8	nullms
13	Claude Opus 4.6	anthropic	1239	59.8%	2,015	±8.2	nullms
14	Gemini 3.6 Flash	google	1228	50.8%	1,568	±9.2	nullms
15	Muse Spark 1.3 (xhigh)	meta	1228	46.4%	336	±19.7	nullms
16	GLM-5.3	zhipu	1224	53.2%	263	±21.6	nullms
17	Claude Opus 4.5	anthropic	1219	60.7%	1,542	±9.8	nullms
18	Muse Spark 1.3 Max	meta	1217	44.8%	279	±21.5	nullms
19	Muse Spark 1.1	meta	1205	46.9%	887	±12.0	nullms
20	Gemini 3.5 Flash	google	1201	51.4%	1,177	±10.4	nullms
21	Muse Spark 1.2	meta	1198	47.0%	1,044	±11.1	nullms
22	MiniMax M3	minimax	1196	46.4%	1,740	±8.8	nullms
23	GLM 5.1	zhipu	1194	51.5%	3,038	±6.6	nullms
24	GLM 5.2	zhipu	1191	50.4%	1,559	±9.1	nullms
25	Kimi K2.6	moonshot	1185	48.2%	2,506	±7.3	nullms
26	Qwen3.7 Max	alibaba	1178	45.2%	1,007	±11.3	nullms
27	Kimi K2.5 (Thinking)	moonshot	1177	54.6%	1,389	±10.0	nullms
28	Kimi K2.7 Code	moonshot	1175	47.0%	1,270	±10.0	nullms
29	GPT-5.5	openai	1172	50.4%	843	±12.2	nullms
30	Claude Sonnet 4.5	anthropic	1168	52.9%	414	±17.4	nullms
31	GLM 5	zhipu	1166	51.6%	2,853	±7.1	nullms
32	GLM 5V Turbo	zhipu	1164	50.4%	1,599	±9.0	nullms
33	GLM 4.7	zhipu	1136	48.9%	1,550	±9.5	nullms
34	GPT-5.6 Sol (Medium)	openai	1133	42.5%	228	±23.5	nullms
35	GLM 4.6	zhipu	1127	47.2%	1,660	±9.3	nullms
36	GPT 5.2	openai	1124	46.8%	1,813	±8.9	nullms
37	GPT-5.6 Terra	openai	1123	36.3%	858	±12.7	nullms
38	Gemini 3.1 Pro Preview	google	1122	43.3%	2,809	±7.0	nullms
39	Gemini 3 Flash Preview	google	1120	46.6%	2,015	±8.6	nullms
40	GPT-5.2 Codex	openai	1120	46.6%	1,767	±9.0	nullms
41	Grok 4.20 Reasoning	xai	1120	45.4%	2,027	±8.3	nullms
42	GPT-5.4	openai	1117	46.1%	1,928	±8.8	nullms
43	Gemini 3 Pro Preview	google	1106	44.5%	1,867	±8.9	nullms
44	Grok 4.3	xai	1092	34.6%	1,459	±9.8	nullms
45	GPT-5.3 Codex	openai	1084	41.4%	954	±11.9	nullms
46	Grok Code Fast 1	xai	1064	38.7%	1,602	±9.6	nullms