Text Arena

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

Last Updated

Dec 15, 2025

Total Votes

51,497

Total Models

176

/

Style Control

	Rank Spread (Upper-Lower)
1	1◄─►23	grok-4.1-thinking	1518	±33	377	xAI	Proprietary
2	1◄─►30	gemini-3-pro	1511	±32	397	Google	Proprietary
3	1◄─►44	claude-opus-4-5-20251101-thinking-32k	1497	±44	209	Anthropic	Proprietary
4	1◄─►43	grok-4.1	1489	±35	351	xAI	Proprietary
5	1◄─►50	claude-opus-4-5-20251101	1487	±42	235	Anthropic	Proprietary
6	1◄─►48	gpt-5.1-high	1482	±36	323	OpenAI	Proprietary
7	1◄─►43	claude-opus-4-1-20250805-thinking-16k	1481	±26	661	Anthropic	Proprietary
8	1◄─►43	o3-2025-04-16	1479	±24	763	OpenAI	Proprietary
9	1◄─►47	claude-opus-4-1-20250805	1473	±23	893	Anthropic	Proprietary
10	1◄─►50	qwen3-235b-a22b-instruct-2507	1469	±24	786	Alibaba	Apache 2.0
11	1◄─►62	gpt-5.1	1469	±38	288	OpenAI	Proprietary
12	1◄─►50	chatgpt-4o-latest-20250326	1468	±23	869	OpenAI	Proprietary
13	1◄─►50	gemini-2.5-pro	1467	±22	1,086	Google	Proprietary
14	1◄─►58	claude-sonnet-4-5-20250929-thinking-32k	1467	±30	482	Anthropic	Proprietary
15	1◄─►59	qwen3-max-preview	1467	±32	393	Alibaba	Proprietary
16	1◄─►60	claude-opus-4-20250514-thinking-16k	1463	±29	471	Anthropic	Proprietary
17	1◄─►65	claude-sonnet-4-5-20250929	1460	±33	389	Anthropic	Proprietary
18	1◄─►65	glm-4.6	1460	±33	402	Z.ai	MIT
19	1◄─►65	gemini-2.5-flash-preview-09-2025	1457	±30	464	Google	Proprietary
20	1◄─►75	deepseek-v3.1	1454	±39	241	DeepSeek	MIT
21	2◄─►72	gpt-5-chat	1454	±31	396	OpenAI	Proprietary
22	2◄─►74	grok-3-preview-02-24	1451	±33	366	xAI	Proprietary
23	2◄─►75	kimi-k2-thinking-turbo	1450	±36	320	Moonshot	Modified MIT
24	2◄─►76	qwen3-coder-480b-a35b-instruct	1449	±36	278	Alibaba	Apache 2.0
25	1◄─►85	gpt-4.5-preview-2025-02-27	1449	±57	121	OpenAI	Proprietary
26	1◄─►81	grok-4-1-fast-reasoning	1449	±47	175	xAI	Proprietary
27	3◄─►74	mistral-medium-2508	1446	±26	701	Mistral	Proprietary
28	1◄─►84	deepseek-v3.2-exp	1442	±45	184	DeepSeek AI	MIT
29	3◄─►76	gpt-5-high	1442	±32	442	OpenAI	Proprietary
30	2◄─►81	grok-4-fast-reasoning	1441	±38	256	xAI	Proprietary
31	3◄─►76	claude-sonnet-4-20250514	1440	±27	529	Anthropic	Proprietary
32	3◄─►79	claude-sonnet-4-20250514-thinking-32k	1434	±29	430	Anthropic	Proprietary
33	3◄─►84	mai-1-preview	1432	±37	295	Microsoft AI	Proprietary
34	2◄─►93	deepseek-v3.2	1432	±49	153	DeepSeek AI	MIT
35	3◄─►88	kimi-k2-0905-preview	1432	±45	167	Moonshot	Modified MIT
36	3◄─►83	kimi-k2-0711-preview	1432	±33	373	Moonshot	Modified MIT
37	3◄─►78	gpt-4.1-2025-04-14	1431	±25	671	OpenAI	Proprietary
38	2◄─►93	longcat-flash-chat	1430	±49	156	Meituan	MIT
39	3◄─►81	grok-4-0709	1429	±28	557	xAI	Proprietary
40	3◄─►85	glm-4.5	1428	±35	309	Z.ai	MIT
41	3◄─►88	deepseek-r1-0528	1427	±40	220	DeepSeek	MIT
42	7◄─►83	deepseek-v3-0324	1424	±27	557	DeepSeek	MIT
43	7◄─►84	claude-opus-4-20250514	1423	±27	573	Anthropic	Proprietary
44	3◄─►99	deepseek-v3.2-exp-thinking	1421	±50	135	DeepSeek AI	MIT
45	13◄─►83	gemini-2.5-flash	1420	±21	1,087	Google	Proprietary
46	3◄─►106	mistral-large-3	1417	±50	159	Mistral	Apache 2.0
47	13◄─►85	o4-mini-2025-04-16	1416	±27	578	OpenAI	Proprietary
48	7◄─►93	qwen3-next-80b-a3b-instruct	1416	±34	345	Alibaba	Apache 2.0
49	8◄─►93	qwen2.5-max	1415	±32	329	Alibaba	Proprietary
50	9◄─►93	claude-haiku-4-5-20251001	1414	±32	421	Anthropic	Proprietary
51	9◄─►96	gpt-5-mini-high	1412	±34	367	OpenAI	Proprietary
52	13◄─►93	gpt-4.1-mini-2025-04-14	1410	±28	541	OpenAI	Proprietary
53	14◄─►93	gemini-2.0-flash-001	1409	±27	514	Google	Proprietary
54	13◄─►95	glm-4.5-air	1409	±30	460	Z.ai	MIT
55	13◄─►99	qwen3-30b-a3b-instruct-2507	1408	±35	300	Alibaba	Apache 2.0
56	13◄─►96	minimax-m1	1407	±30	437	MiniMax	Apache 2.0
57	15◄─►99	gemini-2.5-flash-lite-preview-06-17-thinking	1403	±31	402	Google	Proprietary
58	6◄─►115	deepseek-v3.2-thinking	1402	±52	146	DeepSeek AI	MIT
59	21◄─►95	claude-3-5-sonnet-20241022	1401	±21	825	Anthropic	Proprietary
60	17◄─►99	claude-3-7-sonnet-20250219	1401	±28	508	Anthropic	Proprietary
61	16◄─►107	o1-preview	1399	±34	291	OpenAI	Proprietary
62	17◄─►100	mistral-medium-2505	1398	±29	459	Mistral	Proprietary
63	20◄─►99	gemma-3-27b-it	1398	±25	630	Google	Gemma
64	20◄─►107	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1396	±31	447	Google	Proprietary
65	13◄─►115	deepseek-r1	1395	±42	188	DeepSeek	MIT
66	20◄─►106	qwen3-235b-a22b-no-thinking	1394	±29	477	Alibaba	Apache 2.0
67	17◄─►113	o1-2024-12-17	1394	±36	253	OpenAI	Proprietary
68	16◄─►115	qwen3-next-80b-a3b-thinking	1391	±41	203	Alibaba	Apache 2.0
69	23◄─►106	command-a-03-2025	1391	±25	702	Cohere	CC-BY-NC-4.0
70	13◄─►117	hunyuan-turbos-20250416	1389	±49	147	Tencent	Proprietary
71	20◄─►115	gemini-2.0-flash-lite-preview-02-05	1386	±38	256	Google	Proprietary
72	20◄─►116	qwen-max-0919	1384	±41	183	Alibaba	Qwen
73	21◄─►116	mistral-large-2411	1382	±40	204	Mistral	MRL
74	28◄─►115	claude-3-7-sonnet-20250219-thinking-32k	1380	±29	486	Anthropic	Proprietary
75	20◄─►119	o3-mini-high	1380	±44	204	OpenAI	Proprietary
76	20◄─►121	amazon-nova-experimental-chat-10-20	1379	±48	174	Amazon	Proprietary
77	25◄─►117	deepseek-v3	1378	±36	243	DeepSeek	DeepSeek
78	33◄─►115	gemini-advanced-0514	1376	±24	757	Google	Proprietary
79	36◄─►115	claude-3-5-sonnet-20240620	1375	±22	938	Anthropic	Proprietary
80	28◄─►117	qwen3-30b-a3b	1374	±33	327	Alibaba	Apache 2.0
81	39◄─►115	o3-mini	1371	±24	654	OpenAI	Proprietary
82	42◄─►115	gpt-4o-2024-05-13	1370	±19	1,356	OpenAI	Proprietary
83	30◄─►118	qwen3-235b-a22b	1370	±33	334	Alibaba	Apache 2.0
84	30◄─►123	grok-3-mini-beta	1366	±37	281	xAI	Proprietary
85	29◄─►125	mistral-small-2506	1366	±40	224	Mistral	Apache 2.0
86	33◄─►124	athene-v2-chat	1364	±36	228	NexusFlow	NexusFlow
87	44◄─►119	grok-2-2024-08-13	1359	±25	605	xAI	Proprietary
88	42◄─►129	glm-4-plus	1353	±35	286	Zhipu AI	Proprietary
89	51◄─►125	gemini-1.5-pro-002	1353	±27	460	Google	Proprietary
90	44◄─►126	gpt-oss-120b	1352	±31	404	OpenAI	Apache 2.0
91	60◄─►121	gpt-4-1106-preview	1351	±19	1,737	OpenAI	Proprietary
92	44◄─►129	qwq-32b	1351	±34	294	Alibaba	Apache 2.0
93	51◄─►126	llama-3.1-405b-instruct-bf16	1351	±30	365	Meta	Llama 3.1 Community
94	44◄─►129	gemma-3n-e4b-it	1351	±35	307	Google	Gemma
95	55◄─►124	claude-3-5-haiku-20241022	1351	±23	788	Anthropic	Proprietary
96	61◄─►119	claude-3-opus-20240229	1351	±17	2,850	Anthropic	Proprietary
97	61◄─►122	gpt-4-0125-preview	1349	±20	1,522	OpenAI	Proprietary
98	44◄─►131	yi-lightning	1347	±36	272	01 AI	Proprietary
99	64◄─►125	gpt-4-turbo-2024-04-09	1346	±20	1,402	OpenAI	Proprietary
100	42◄─►136	grok-3-mini-high	1345	±45	166	xAI	Proprietary
101	61◄─►125	gpt-4o-mini-2024-07-18	1344	±23	654	OpenAI	Proprietary
102	55◄─►131	llama-4-scout-17b-16e-instruct	1342	±31	394	Meta	Llama
103	61◄─►129	llama-3.1-405b-instruct-fp8	1342	±26	549	Meta	Llama 3.1 Community
104	66◄─►127	gemini-1.5-pro-001	1341	±21	1,081	Google	Proprietary
105	66◄─►130	llama-3.3-70b-instruct	1338	±26	541	Meta	Llama-3.3
106	66◄─►131	gpt-4o-2024-08-06	1338	±27	459	OpenAI	Proprietary
107	66◄─►134	mistral-large-2407	1337	±28	443	Mistral	Mistral Research
108	55◄─►136	athene-70b-0725	1336	±41	206	NexusFlow	CC-BY-NC-4.0
109	61◄─►137	deepseek-v2.5	1330	±37	223	DeepSeek	DeepSeek
110	66◄─►136	o1-mini	1330	±29	424	OpenAI	Proprietary
111	53◄─►143	magistral-medium-2506	1328	±50	164	Mistral	Proprietary
112	67◄─►136	grok-2-mini-2024-08-13	1327	±28	472	xAI	Proprietary
113	67◄─►137	qwen2.5-72b-instruct	1325	±32	343	Alibaba	Qwen
114	66◄─►142	amazon-nova-pro-v1.0	1324	±38	224	Amazon	Proprietary
115	76◄─►136	gpt-4-0314	1321	±24	843	OpenAI	Proprietary
116	78◄─►136	gemma-2-27b-it	1321	±21	795	Google	Gemma license
117	85◄─►136	claude-3-sonnet-20240229	1314	±19	1,826	Anthropic	Proprietary
118	61◄─►150	nova-2-lite	1313	±55	142	Amazon	Proprietary
119	81◄─►143	llama-3.1-70b-instruct	1310	±27	501	Meta	Llama 3.1 Community
120	91◄─►143	gemini-1.5-flash-001	1305	±22	922	Google	Proprietary
121	82◄─►147	c4ai-aya-expanse-32b	1302	±34	274	Cohere	CC-BY-NC-4.0
122	88◄─►143	llama-4-maverick-17b-128e-instruct	1302	±27	565	Meta	Llama 4
123	98◄─►142	llama-3-70b-instruct	1302	±17	2,514	Meta	Llama 3 Community
124	85◄─►147	mistral-small-3.1-24b-instruct-2503	1301	±32	413	Mistral	Apache 2.0
125	97◄─►143	mistral-large-2402	1298	±22	1,055	Mistral	Proprietary
126	89◄─►148	gemini-1.5-flash-002	1294	±34	297	Google	Proprietary
127	107◄─►147	claude-3-haiku-20240307	1289	±19	1,777	Anthropic	Proprietary
128	106◄─►147	command-r-plus	1288	±21	1,234	Cohere	CC-BY-NC-4.0
129	98◄─►151	gemini-1.5-flash-8b-001	1286	±32	334	Google	Proprietary
130	87◄─►156	amazon-nova-micro-v1.0	1285	±44	164	Amazon	Proprietary
131	107◄─►148	gpt-4-0613	1285	±20	1,551	OpenAI	Proprietary
132	95◄─►158	amazon-nova-lite-v1.0	1276	±45	171	Amazon	Proprietary
133	106◄─►155	nemotron-4-340b-instruct	1276	±33	356	Nvidia	NVIDIA Open Model
134	102◄─►157	phi-4	1275	±40	206	Microsoft	MIT
135	114◄─►153	gemma-2-9b-it	1269	±25	592	Google	Gemma license
136	106◄─►159	deepseek-coder-v2	1268	±41	207	DeepSeek AI	DeepSeek License
137	116◄─►155	mixtral-8x22b-instruct-v0.1	1267	±24	775	Mistral	Apache 2.0
138	116◄─►156	qwen2-72b-instruct	1265	±25	597	Alibaba	Qianwen LICENSE
139	103◄─►163	mistral-small-24b-instruct-2501	1261	±50	142	Mistral	Apache 2.0
140	116◄─►157	mistral-medium	1261	±26	723	Mistral	Proprietary
141	116◄─►159	gemini-pro-dev-api	1259	±31	462	Google	Proprietary
142	116◄─►159	reka-flash-21b-20240226	1258	±30	432	Reka AI	Proprietary
143	123◄─►158	mixtral-8x7b-instruct-v0.1	1253	±21	1,258	Mistral	Apache 2.0
144	123◄─►159	qwen1.5-72b-chat	1250	±23	862	Alibaba	Qianwen LICENSE
145	123◄─►160	command-r	1247	±24	841	Cohere	CC-BY-NC-4.0
146	127◄─►159	gpt-3.5-turbo-0125	1246	±21	1,293	OpenAI	Proprietary
147	118◄─►165	reka-flash-21b-20240226-online	1244	±40	231	Reka AI	Proprietary
148	123◄─►164	qwen1.5-110b-chat	1239	±31	378	Alibaba	Qianwen LICENSE
149	130◄─►162	llama-3-8b-instruct	1234	±19	1,640	Meta	Llama 3 Community
150	129◄─►165	snowflake-arctic-instruct	1230	±29	529	Snowflake	Apache 2.0
151	129◄─►167	phi-3-small-8k-instruct	1224	±35	271	Microsoft	MIT
152	131◄─►167	yi-1.5-34b-chat	1218	±31	403	01 AI	Apache-2.0
153	131◄─►167	gemma-2-2b-it	1217	±29	469	Google	Gemma license
154	132◄─►167	llama-3.1-8b-instruct	1215	±28	482	Meta	Llama 3.1 Community
155	132◄─►171	qwen1.5-14b-chat	1206	±38	278	Alibaba	Qianwen LICENSE
156	134◄─►171	gpt-3.5-turbo-1106	1203	±38	310	OpenAI	Proprietary
157	138◄─►171	phi-3-medium-4k-instruct	1201	±33	352	Microsoft	MIT
158	140◄─►171	dbrx-instruct-preview	1201	±29	544	Databricks	DBRX LICENSE
159	136◄─►174	openchat-3.5-0106	1196	±43	212	OpenChat	Apache-2.0
160	145◄─►174	qwen1.5-32b-chat	1190	±34	310	Alibaba	Qianwen LICENSE
161	146◄─►174	gemma-1.1-7b-it	1186	±31	407	Google	Gemma license
162	147◄─►174	vicuna-33b	1177	±37	295	LMSYS	Non-commercial
163	146◄─►174	starling-lm-7b-alpha	1175	±43	211	UC Berkeley	CC-BY-NC-4.0
164	148◄─►174	starling-lm-7b-beta	1172	±39	248	Nexusflow	Apache-2.0
165	149◄─►174	yi-34b-chat	1166	±40	236	01 AI	Yi License
166	151◄─►174	llama-2-70b-chat	1164	±27	683	Meta	Llama 2 Community
167	151◄─►174	phi-3-mini-4k-instruct	1162	±35	310	Microsoft	MIT
168	155◄─►175	phi-3-mini-128k-instruct	1145	±35	372	Microsoft	MIT
169	155◄─►175	gemma-7b-it	1138	±46	201	Google	Gemma license
170	155◄─►176	stripedhyena-nous-7b	1133	±49	170	Together AI	Apache 2.0
171	155◄─►176	vicuna-13b	1127	±45	200	LMSYS	Llama 2 Community
172	159◄─►175	mistral-7b-instruct-v0.2	1127	±31	479	Mistral	Apache-2.0
173	159◄─►176	llama-2-13b-chat	1121	±39	265	Meta	Llama 2 Community
174	159◄─►176	zephyr-7b-beta	1113	±49	154	HuggingFace	MIT
175	168◄─►176	mistral-7b-instruct	1070	±48	175	Mistral	Apache 2.0
176	171◄─►176	llama-2-7b-chat	1050	±42	257	Meta	Llama 2 Community

Text Arena

Default Leaderboard Plots

Average Win Rate Against All Other Models (Uniform Sampling and No Ties)

Battle Count for Each Combination of Models (without Ties)

Confidence Intervals on Model Strength (via Bootstrapping)

Fraction of Model A Wins for All Non-tied A vs. B Battles