Text Arena

View rankings across various LLMs on their versatility, linguistic precision, and cultural context across text.

Last Updated

Nov 9, 2025

Total Votes

83,100

Total Models

164

/

Style Control


1	gemini-2.5-pro	1455	±19	1,398	Google	Proprietary
1	gpt-5-high	1442	±23	886	OpenAI	Proprietary
1	gpt-4.5-preview-2025-02-27	1440	±38	274	OpenAI	Proprietary
1	o3-2025-04-16	1438	±18	1,348	OpenAI	Proprietary
1	gpt-5-chat	1427	±31	419	OpenAI	Proprietary
1	gemini-2.5-flash-preview-09-2025	1416	±52	128	Google	Proprietary
1	claude-opus-4-1-20250805-thinking-16k	1409	±29	390	Anthropic	Proprietary
2	chatgpt-4o-latest-20250326	1408	±21	927	OpenAI	Proprietary
1	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1400	±55	115	Google	Proprietary
2	claude-opus-4-1-20250805	1399	±23	755	Anthropic	Proprietary
1	deepseek-v3.2-exp	1397	±62	108	DeepSeek AI	MIT
4	grok-4-0709	1392	±21	897	xAI	Proprietary
4	gemini-2.5-flash	1390	±17	1,455	Google	Proprietary
4	glm-4.5	1386	±24	743	Z.ai	MIT
4	claude-opus-4-20250514-thinking-16k	1384	±22	835	Anthropic	Proprietary
4	o1-2024-12-17	1379	±25	589	OpenAI	Proprietary
5	qwen3-235b-a22b-instruct-2507	1379	±21	887	Alibaba	Apache 2.0
4	gpt-5-mini-high	1377	±32	376	OpenAI	Proprietary
5	claude-opus-4-20250514	1377	±19	1,087	Anthropic	Proprietary
4	qwen3-max-preview	1376	±33	332	Alibaba	Proprietary
5	grok-3-preview-02-24	1376	±21	834	xAI	Proprietary
5	deepseek-r1-0528	1376	±25	610	DeepSeek	MIT
6	kimi-k2-0711-preview	1375	±20	948	Moonshot	Modified MIT
4	deepseek-v3.1-thinking	1374	±37	259	DeepSeek	MIT
4	deepseek-v3.1	1374	±32	314	DeepSeek	MIT
6	qwen3-235b-a22b-no-thinking	1367	±21	865	Alibaba	Apache 2.0
6	qwen3-235b-a22b-thinking-2507	1364	±29	450	Alibaba	Apache 2.0
5	qwen3-next-80b-a3b-instruct	1362	±37	241	Alibaba	Apache 2.0
4	kimi-k2-0905-preview	1361	±47	161	Moonshot	Modified MIT
6	mistral-medium-2508	1360	±28	478	Mistral	Proprietary
7	gemini-2.5-flash-lite-preview-06-17-thinking	1360	±22	795	Google	Proprietary
8	o1-preview	1355	±23	686	OpenAI	Proprietary
5	claude-sonnet-4-5-20250929-thinking-32k	1353	±50	121	Anthropic	Proprietary
11	gpt-4.1-2025-04-14	1351	±19	1,067	OpenAI	Proprietary
11	o4-mini-2025-04-16	1347	±19	1,062	OpenAI	Proprietary
7	mai-1-preview	1346	±35	299	Microsoft AI	Proprietary
12	claude-3-7-sonnet-20250219-thinking-32k	1343	±19	1,031	Anthropic	Proprietary
9	hunyuan-turbos-20250416	1343	±32	364	Tencent	Proprietary
14	claude-sonnet-4-20250514	1341	±20	967	Anthropic	Proprietary
11	deepseek-r1	1341	±25	474	DeepSeek	MIT
16	deepseek-v3-0324	1338	±19	1,033	DeepSeek	MIT
14	claude-sonnet-4-20250514-thinking-32k	1338	±22	811	Anthropic	Proprietary
18	grok-3-mini-beta	1331	±24	657	xAI	Proprietary
19	qwen3-30b-a3b-instruct-2507	1330	±24	712	Alibaba	Apache 2.0
20	glm-4.5-air	1328	±22	795	Z.ai	MIT
20	qwen3-coder-480b-a35b-instruct	1327	±20	926	Alibaba	Apache 2.0
23	gpt-4.1-mini-2025-04-14	1325	±20	1,001	OpenAI	Proprietary
20	gemini-2.0-flash-lite-preview-02-05	1324	±25	553	Google	Proprietary
25	Gemini-1.5-Pro-002	1322	±17	1,225	Google	Proprietary
26	mistral-medium-2505	1317	±20	898	Mistral	Proprietary
26	qwen2.5-max	1317	±21	747	Alibaba	Proprietary
20	o3-mini-high	1316	±30	378	OpenAI	Proprietary
25	grok-3-mini-high	1314	±27	494	xAI	Proprietary
29	gemma-3-27b-it	1314	±19	1,018	Google	Gemma
33	Claude 3.5 Sonnet (10/22)	1313	±13	2,060	Anthropic	Proprietary
32	command-a-03-2025	1313	±19	1,167	Cohere	CC-BY-NC-4.0
25	gpt-oss-120b	1312	±28	489	OpenAI	Apache 2.0
35	gpt-4o-2024-05-13	1310	±13	2,697	OpenAI	Proprietary
32	qwen3-235b-a22b	1308	±23	736	Alibaba	Apache 2.0
37	o3-mini	1302	±16	1,416	OpenAI	Proprietary
40	GPT-4o (08/06)	1297	±17	1,131	OpenAI	Proprietary
36	gemma-3n-e4b-it	1297	±23	728	Google	Gemma
36	mistral-small-2506	1295	±25	545	Mistral	Apache 2.0
40	gemini-advanced-0514	1294	±19	1,217	Google	Proprietary
37	deepseek-v3	1294	±23	540	DeepSeek	DeepSeek
45	Claude 3.5 Sonnet (06/20)	1291	±15	2,139	Anthropic	Proprietary
46	gemini-1.5-pro-001	1290	±15	1,941	Google	Proprietary
29	qwen3-next-80b-a3b-thinking	1289	±44	189	Alibaba	Apache 2.0
40	nvidia-llama-3.3-nemotron-super-49b-v1.5	1282	±30	417	Nvidia	Nvidia Open
51	o1-mini	1282	±17	1,114	OpenAI	Proprietary
37	qwen-plus-0125	1280	±38	208	Alibaba	Proprietary
51	llama-3.1-405b-instruct-bf16	1278	±20	861	Meta	Llama 3.1 Community
56	grok-2-2024-08-13	1275	±15	1,502	xAI	Proprietary
58	gpt-4-1106-preview	1269	±17	1,434	OpenAI	Proprietary
61	claude-3-opus-20240229	1267	±12	3,698	Anthropic	Proprietary
56	Gemini-1.5-Flash-002	1267	±21	766	Google	Proprietary
42	longcat-flash-chat	1265	±45	154	Meituan	MIT
48	gpt-oss-20b	1264	±40	230	OpenAI	Apache 2.0
59	yi-lightning	1262	±23	586	01 AI	Proprietary
61	llama-4-maverick-17b-128e-instruct	1261	±21	925	Meta	Llama 4
61	llama-4-scout-17b-16e-instruct	1260	±22	776	Meta	Llama
65	gpt-4-0125-preview	1257	±17	1,488	OpenAI	Proprietary
66	gpt-4-turbo-2024-04-09	1257	±15	2,128	OpenAI	Proprietary
51	step-1o-turbo-202506	1256	±42	202	StepFun	Proprietary
68	GPT-4o-mini (07/18)	1255	±14	1,809	OpenAI	Proprietary
54	deepseek-v2.5-1210	1255	±41	165	DeepSeek	DeepSeek
63	qwen3-30b-a3b	1254	±23	730	Alibaba	Apache 2.0
68	claude-3-5-haiku-20241022	1251	±16	1,539	Anthropic	Propretary
61	qwen-max-0919	1248	±32	312	Alibaba	Qwen
68	qwq-32b	1244	±25	607	Alibaba	Apache 2.0
68	mistral-small-3.1-24b-instruct-2503	1244	±22	789	Mistral	Apache 2.0
71	llama-3.1-405b-instruct-fp8	1243	±15	1,633	Meta	Llama 3.1 Community
71	grok-2-mini-2024-08-13	1241	±16	1,233	xAI	Proprietary
68	glm-4-plus	1240	±26	501	Zhipu AI	Proprietary
66	magistral-medium-2506	1238	±33	365	Mistral	Proprietary
68	qwen2.5-plus-1127	1237	±32	304	Alibaba	Proprietary
70	athene-v2-chat	1237	±22	590	NexusFlow	NexusFlow
72	mistral-large-2407	1237	±16	1,280	Mistral	Mistral Research
61	gpt-4.1-nano-2025-04-14	1235	±45	161	OpenAI	Proprietary
71	minimax-m1	1234	±22	879	MiniMax	Apache 2.0
70	deepseek-v2.5	1234	±26	492	DeepSeek	DeepSeek
74	gemma-2-27b-it	1233	±14	1,823	Google	Gemma license
71	amazon-nova-pro-v1.0	1232	±25	524	Amazon	Proprietary
68	glm-4-plus-0111	1229	±38	204	Zhipu	Proprietary
76	gemini-1.5-flash-001	1227	±16	1,527	Google	Proprietary
77	command-r-plus	1225	±18	1,495	Cohere	CC-BY-NC-4.0
74	gpt-4-0314	1223	±25	622	OpenAI	Proprietary
81	llama-3.3-70b-instruct	1221	±18	1,201	Meta	Llama-3.3
70	command-r-plus-08-2024	1221	±37	211	Cohere	CC-BY-NC-4.0
74	command-r-08-2024	1218	±33	255	Cohere	CC-BY-NC-4.0
80	mistral-large-2411	1218	±22	643	Mistral	MRL
84	qwen2.5-72b-instruct	1215	±20	803	Alibaba	Qwen
84	c4ai-aya-expanse-32b	1212	±22	680	Cohere	CC-BY-NC-4.0
86	gpt-4-0613	1206	±18	1,256	OpenAI	Proprietary
91	claude-3-sonnet-20240229	1203	±17	1,770	Anthropic	Proprietary
85	deepseek-coder-v2	1200	±30	346	DeepSeek AI	DeepSeek License
95	gemma-2-9b-it	1199	±16	1,318	Google	Gemma license
86	phi-4	1198	±26	506	Microsoft	MIT
86	gemma-2-9b-it-simpo	1193	±32	291	Princeton	MIT
99	athene-70b-0725	1189	±22	684	NexusFlow	CC-BY-NC-4.0
94	amazon-nova-lite-v1.0	1188	±27	415	Amazon	Proprietary
98	amazon-nova-micro-v1.0	1187	±26	456	Amazon	Proprietary
97	nemotron-4-340b-instruct	1186	±28	438	Nvidia	NVIDIA Open Model
106	qwen2-72b-instruct	1182	±20	910	Alibaba	Qianwen LICENSE
93	jamba-1.5-large	1182	±36	245	AI21 Labs	Jamba Open
107	Meta-Llama-3.1-70B-Instruct	1181	±15	1,463	Meta	Llama 3.1 Community
109	claude-3-haiku-20240307	1178	±15	2,086	Anthropic	Proprietary
106	gemini-1.5-flash-8b-001	1177	±21	709	Google	Proprietary
112	command-r	1169	±21	866	Cohere	CC-BY-NC-4.0
109	c4ai-aya-expanse-8b	1160	±34	240	Cohere	CC-BY-NC-4.0
110	mistral-small-24b-instruct-2501	1154	±36	275	Mistral	Apache 2.0
119	gpt-3.5-turbo-0125	1147	±21	977	OpenAI	Proprietary
117	reka-flash-21b-20240226-online	1144	±35	276	Reka AI	Proprietary
119	qwen1.5-110b-chat	1142	±26	606	Alibaba	Qianwen LICENSE
121	qwen1.5-72b-chat	1136	±27	502	Alibaba	Qianwen LICENSE
130	gemma-2-2b-it	1125	±17	1,241	Google	Gemma license
128	reka-flash-21b-20240226	1124	±29	444	Reka AI	Proprietary
130	phi-3-medium-4k-instruct	1121	±23	690	Microsoft	MIT
130	mixtral-8x22b-instruct-v0.1	1114	±20	988	Mistral	Apache 2.0
128	gemini-pro-dev-api	1110	±45	173	Google	Proprietary
130	qwen1.5-32b-chat	1106	±33	325	Alibaba	Qianwen LICENSE
134	llama-3.1-8b-instruct	1093	±18	1,259	Meta	Llama 3.1 Community
130	qwen1.5-14b-chat	1091	±40	219	Alibaba	Qianwen LICENSE
137	llama-3-70b-instruct	1088	±14	3,319	Meta	Llama 3 Community
136	mistral-large-2402	1086	±21	956	Mistral	Proprietary
134	dbrx-instruct-preview	1084	±30	433	Databricks	DBRX LICENSE
134	yi-1.5-34b-chat	1083	±27	512	01 AI	Apache-2.0
133	jamba-1.5-mini	1083	±35	274	AI21 Labs	Jamba Open
134	mistral-medium	1078	±33	340	Mistral	Proprietary
137	yi-34b-chat	1063	±43	201	01 AI	Yi License
140	gemma-1.1-7b-it	1054	±29	456	Google	Gemma license
143	snowflake-arctic-instruct	1049	±24	670	Snowflake	Apache 2.0
140	starling-lm-7b-beta	1047	±44	183	Nexusflow	Apache-2.0
145	llama-3-8b-instruct	1041	±16	2,007	Meta	Llama 3 Community
143	phi-3-small-8k-instruct	1040	±31	391	Microsoft	MIT
143	phi-3-mini-4k-instruct-june-2024	1033	±33	360	Microsoft	MIT
143	vicuna-33b	1030	±41	198	LMSYS	Non-commercial
150	mixtral-8x7b-instruct-v0.1	1009	±21	968	Mistral	Apache 2.0
145	vicuna-13b	1008	±53	125	LMSYS	Llama 2 Community
150	phi-3-mini-4k-instruct	1006	±33	391	Microsoft	MIT
150	llama-2-70b-chat	996	±33	344	Meta	Llama 2 Community
154	phi-3-mini-128k-instruct	987	±31	387	Microsoft	MIT
154	llama-2-13b-chat	967	±49	175	Meta	Llama 2 Community
157	mistral-7b-instruct-v0.2	950	±46	167	Mistral	Apache-2.0

Take your chats anywhere

Text Arena

Default Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

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

Confidence Intervals on Model Strength (via Bootstrapping)