Text Arena

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

Last Updated

Dec 23, 2025

Total Votes

84,963

Total Models

179

/

Style Control

	Rank Spread
1	1◄─►13	gemini-3-pro	1482	±45	209	Google	Proprietary
2	1◄─►16	grok-4.1-thinking	1472	±43	191	xAI	Proprietary
3	1◄─►13	gemini-2.5-pro	1457	±18	1,552	Google	Proprietary
4	1◄─►27	gpt-5.1-high	1452	±45	178	OpenAI	Proprietary
5	1◄─►36	gpt-5.1	1443	±46	165	OpenAI	Proprietary
6	1◄─►32	gpt-4.5-preview-2025-02-27	1441	±38	274	OpenAI	Proprietary
7	1◄─►19	gpt-5-high	1438	±22	924	OpenAI	Proprietary
8	1◄─►19	o3-2025-04-16	1436	±18	1,378	OpenAI	Proprietary
9	1◄─►41	grok-4.1	1430	±43	190	xAI	Proprietary
10	1◄─►36	gpt-5-chat	1427	±30	460	OpenAI	Proprietary
11	1◄─►55	claude-opus-4-5-20251101	1412	±56	107	Anthropic	Proprietary
12	3◄─►41	claude-opus-4-1-20250805-thinking-16k	1411	±25	528	Anthropic	Proprietary
13	3◄─►39	chatgpt-4o-latest-20250326	1410	±20	1,073	OpenAI	Proprietary
14	1◄─►60	claude-opus-4-5-20251101-thinking-32k	1408	±60	96	Anthropic	Proprietary
15	4◄─►43	claude-opus-4-1-20250805	1405	±21	903	Anthropic	Proprietary
16	3◄─►53	gemini-2.5-flash-preview-09-2025	1396	±36	278	Google	Proprietary
17	1◄─►60	kimi-k2-thinking-turbo	1395	±48	164	Moonshot	Modified MIT
18	7◄─►46	gemini-2.5-flash	1391	±17	1,593	Google	Proprietary
19	6◄─►50	glm-4.5	1388	±24	739	Z.ai	MIT
20	7◄─►51	grok-4-0709	1385	±20	951	xAI	Proprietary
21	6◄─►56	gpt-5-mini-high	1384	±31	407	OpenAI	Proprietary
22	7◄─►51	claude-opus-4-20250514-thinking-16k	1384	±22	830	Anthropic	Proprietary
23	4◄─►61	claude-sonnet-4-5-20250929	1384	±38	237	Anthropic	Proprietary
24	8◄─►51	qwen3-235b-a22b-instruct-2507	1383	±20	1,025	Alibaba	Apache 2.0
25	6◄─►56	qwen3-max-preview	1383	±31	381	Alibaba	Proprietary
26	4◄─►63	glm-4.6	1382	±40	216	Z.ai	MIT
27	7◄─►56	o1-2024-12-17	1380	±25	589	OpenAI	Proprietary
28	8◄─►53	claude-opus-4-20250514	1380	±19	1,075	Anthropic	Proprietary
29	8◄─►57	deepseek-r1-0528	1377	±25	606	DeepSeek	MIT
30	6◄─►62	claude-sonnet-4-5-20250929-thinking-32k	1376	±34	282	Anthropic	Proprietary
31	8◄─►56	grok-3-preview-02-24	1376	±21	821	xAI	Proprietary
32	6◄─►65	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1376	±37	268	Google	Proprietary
33	6◄─►62	deepseek-v3.1	1376	±32	312	DeepSeek	MIT
34	6◄─►66	deepseek-v3.1-thinking	1375	±37	256	DeepSeek	MIT
35	10◄─►56	kimi-k2-0711-preview	1375	±20	946	Moonshot	Modified MIT
36	11◄─►61	qwen3-235b-a22b-no-thinking	1367	±21	860	Alibaba	Apache 2.0
37	11◄─►64	mistral-medium-2508	1365	±25	626	Mistral	Proprietary
38	6◄─►76	grok-4-fast-reasoning	1364	±44	182	xAI	Proprietary
39	10◄─►68	qwen3-235b-a22b-thinking-2507	1363	±29	442	Alibaba	Apache 2.0
40	7◄─►80	kimi-k2-0905-preview	1361	±44	180	Moonshot	Modified MIT
41	10◄─►73	qwen3-next-80b-a3b-instruct	1360	±35	272	Alibaba	Apache 2.0
42	14◄─►67	gemini-2.5-flash-lite-preview-06-17-thinking	1358	±22	786	Google	Proprietary
43	14◄─►68	o1-preview	1356	±23	686	OpenAI	Proprietary
44	15◄─►71	gpt-4.1-2025-04-14	1350	±19	1,099	OpenAI	Proprietary
45	15◄─►71	o4-mini-2025-04-16	1346	±19	1,060	OpenAI	Proprietary
46	14◄─►84	mai-1-preview	1345	±35	305	Microsoft AI	Proprietary
47	16◄─►73	claude-3-7-sonnet-20250219-thinking-32k	1345	±19	1,022	Anthropic	Proprietary
48	13◄─►87	claude-haiku-4-5-20251001	1345	±39	239	Anthropic	Proprietary
49	15◄─►84	hunyuan-turbos-20250416	1342	±32	359	Tencent	Proprietary
50	15◄─►80	deepseek-r1	1341	±25	474	DeepSeek	MIT
51	19◄─►76	claude-sonnet-4-20250514	1341	±20	955	Anthropic	Proprietary
52	19◄─►78	claude-sonnet-4-20250514-thinking-32k	1340	±22	802	Anthropic	Proprietary
53	21◄─►76	claude-3-7-sonnet-20250219	1339	±19	1,010	Anthropic	Proprietary
54	21◄─►77	deepseek-v3-0324	1338	±19	1,029	DeepSeek	MIT
55	22◄─►84	grok-3-mini-beta	1332	±24	649	xAI	Proprietary
56	13◄─►100	deepseek-v3.2-exp	1330	±54	120	DeepSeek AI	MIT
57	28◄─►84	qwen3-coder-480b-a35b-instruct	1329	±21	910	Alibaba	Apache 2.0
58	27◄─►87	qwen3-30b-a3b-instruct-2507	1328	±24	709	Alibaba	Apache 2.0
59	28◄─►87	glm-4.5-air	1327	±21	828	Z.ai	MIT
60	28◄─►88	gemini-2.0-flash-lite-preview-02-05	1325	±25	553	Google	Proprietary
61	32◄─►87	gpt-4.1-mini-2025-04-14	1324	±20	994	OpenAI	Proprietary
62	37◄─►87	gemini-1.5-pro-002	1322	±17	1,225	Google	Proprietary
63	36◄─►90	qwen2.5-max	1319	±21	740	Alibaba	Proprietary
64	30◄─►93	o3-mini-high	1317	±30	378	OpenAI	Proprietary
65	38◄─►91	mistral-medium-2505	1317	±20	889	Mistral	Proprietary
66	34◄─►92	gpt-oss-120b	1315	±27	524	OpenAI	Apache 2.0
67	41◄─►91	gemma-3-27b-it	1314	±19	1,012	Google	Gemma
68	43◄─►87	claude-3-5-sonnet-20241022	1314	±13	2,055	Anthropic	Proprietary
69	41◄─►91	command-a-03-2025	1313	±18	1,206	Cohere	CC-BY-NC-4.0
70	35◄─►94	grok-3-mini-high	1313	±27	486	xAI	Proprietary
71	45◄─►90	gpt-4o-2024-05-13	1311	±14	2,697	OpenAI	Proprietary
72	41◄─►94	qwen3-235b-a22b	1309	±23	727	Alibaba	Apache 2.0
73	45◄─►96	gemini-2.0-flash-001	1303	±19	1,029	Google	Proprietary
74	50◄─►95	o3-mini	1301	±16	1,416	OpenAI	Proprietary
75	45◄─►100	gemma-3n-e4b-it	1298	±23	721	Google	Gemma
76	52◄─►99	gpt-4o-2024-08-06	1298	±18	1,131	OpenAI	Proprietary
77	52◄─►100	gemini-advanced-0514	1295	±19	1,217	Google	Proprietary
78	50◄─►103	deepseek-v3	1294	±23	540	DeepSeek	DeepSeek
79	48◄─►107	mistral-small-2506	1293	±25	542	Mistral	Apache 2.0
80	55◄─►100	claude-3-5-sonnet-20240620	1293	±15	2,139	Anthropic	Proprietary
81	56◄─►100	gemini-1.5-pro-001	1291	±15	1,941	Google	Proprietary
82	63◄─►111	o1-mini	1282	±17	1,114	OpenAI	Proprietary
83	43◄─►126	qwen3-next-80b-a3b-thinking	1282	±44	190	Alibaba	Apache 2.0
84	52◄─►120	nvidia-llama-3.3-nemotron-super-49b-v1.5	1281	±31	402	Nvidia	Nvidia Open
85	49◄─►124	qwen-plus-0125	1281	±38	208	Alibaba	Proprietary
86	63◄─►114	llama-3.1-405b-instruct-bf16	1279	±20	861	Meta	Llama 3.1 Community
87	68◄─►111	grok-2-2024-08-13	1276	±15	1,502	xAI	Proprietary
88	39◄─►139	amazon-nova-experimental-chat-10-20	1270	±64	87	Amazon	Proprietary
89	70◄─►119	gpt-4-1106-preview	1270	±17	1,434	OpenAI	Proprietary
90	74◄─►118	claude-3-opus-20240229	1268	±13	3,698	Anthropic	Proprietary
91	69◄─►122	gemini-1.5-flash-002	1267	±21	766	Google	Proprietary
92	52◄─►132	longcat-flash-chat	1267	±45	156	Meituan	MIT
93	56◄─►130	gpt-oss-20b	1266	±40	233	OpenAI	Apache 2.0
94	73◄─►124	llama-4-scout-17b-16e-instruct	1263	±22	769	Meta	Llama
95	72◄─►126	yi-lightning	1262	±23	586	01 AI	Proprietary
96	74◄─►126	llama-4-maverick-17b-128e-instruct	1261	±21	919	Meta	Llama 4
97	79◄─►124	gpt-4-0125-preview	1258	±17	1,488	OpenAI	Proprietary
98	62◄─►134	step-1o-turbo-202506	1258	±42	197	StepFun	Proprietary
99	80◄─►124	gpt-4-turbo-2024-04-09	1258	±15	2,128	OpenAI	Proprietary
100	81◄─►124	gpt-4o-mini-2024-07-18	1256	±14	1,809	OpenAI	Proprietary
101	65◄─►137	deepseek-v2.5-1210	1255	±41	165	DeepSeek	DeepSeek
102	80◄─►129	qwen3-30b-a3b	1253	±23	723	Alibaba	Apache 2.0
103	82◄─►126	claude-3-5-haiku-20241022	1252	±16	1,531	Anthropic	Proprietary
104	75◄─►134	qwen-max-0919	1248	±32	312	Alibaba	Qwen
105	82◄─►132	mistral-small-3.1-24b-instruct-2503	1246	±22	781	Mistral	Apache 2.0
106	85◄─►129	llama-3.1-405b-instruct-fp8	1244	±15	1,633	Meta	Llama 3.1 Community
107	81◄─►134	qwq-32b	1244	±25	599	Alibaba	Apache 2.0
108	85◄─►132	grok-2-mini-2024-08-13	1241	±17	1,233	xAI	Proprietary
109	82◄─►137	glm-4-plus	1240	±26	501	Zhipu AI	Proprietary
110	81◄─►139	qwen2.5-plus-1127	1238	±32	304	Alibaba	Proprietary
111	81◄─►139	magistral-medium-2506	1238	±34	361	Mistral	Proprietary
112	86◄─►132	mistral-large-2407	1237	±16	1,280	Mistral	Mistral Research
113	84◄─►137	athene-v2-chat	1237	±22	590	NexusFlow	NexusFlow
114	74◄─►146	gpt-4.1-nano-2025-04-14	1236	±45	161	OpenAI	Proprietary
115	85◄─►138	minimax-m1	1236	±22	872	MiniMax	Apache 2.0
116	84◄─►139	deepseek-v2.5	1235	±26	492	DeepSeek	DeepSeek
117	88◄─►133	gemma-2-27b-it	1234	±14	1,823	Google	Gemma license
118	85◄─►139	amazon-nova-pro-v1.0	1232	±25	524	Amazon	Proprietary
119	82◄─►145	glm-4-plus-0111	1229	±38	204	Zhipu	Proprietary
120	89◄─►139	gemini-1.5-flash-001	1228	±17	1,527	Google	Proprietary
121	89◄─►139	command-r-plus	1226	±18	1,495	Cohere	CC-BY-NC-4.0
122	88◄─►140	gpt-4-0314	1224	±25	622	OpenAI	Proprietary
123	94◄─►139	llama-3.3-70b-instruct	1223	±18	1,196	Meta	Llama-3.3
124	84◄─►146	command-r-plus-08-2024	1222	±37	211	Cohere	CC-BY-NC-4.0
125	87◄─►146	command-r-08-2024	1219	±33	255	Cohere	CC-BY-NC-4.0
126	94◄─►142	mistral-large-2411	1218	±22	643	Mistral	MRL
127	98◄─►142	qwen2.5-72b-instruct	1216	±20	803	Alibaba	Qwen
128	98◄─►146	c4ai-aya-expanse-32b	1213	±22	680	Cohere	CC-BY-NC-4.0
129	100◄─►146	gpt-4-0613	1208	±19	1,256	OpenAI	Proprietary
130	105◄─►146	claude-3-sonnet-20240229	1204	±17	1,770	Anthropic	Proprietary
131	98◄─►147	deepseek-coder-v2	1201	±30	346	DeepSeek AI	DeepSeek License
132	109◄─►146	gemma-2-9b-it	1199	±16	1,318	Google	Gemma license
133	101◄─►147	phi-4	1199	±26	506	Microsoft	MIT
134	101◄─►150	gemma-2-9b-it-simpo	1193	±32	291	Princeton	MIT
135	113◄─►149	athene-70b-0725	1190	±22	684	NexusFlow	CC-BY-NC-4.0
136	109◄─►150	amazon-nova-lite-v1.0	1189	±27	415	Amazon	Proprietary
137	112◄─►150	amazon-nova-micro-v1.0	1187	±27	456	Amazon	Proprietary
138	109◄─►150	nemotron-4-340b-instruct	1187	±28	438	Nvidia	NVIDIA Open Model
139	121◄─►150	qwen2-72b-instruct	1183	±20	910	Alibaba	Qianwen LICENSE
140	106◄─►152	jamba-1.5-large	1183	±36	245	AI21 Labs	Jamba Open
141	122◄─►149	llama-3.1-70b-instruct	1181	±16	1,463	Meta	Llama 3.1 Community
142	124◄─►150	claude-3-haiku-20240307	1179	±15	2,086	Anthropic	Proprietary
143	122◄─►151	gemini-1.5-flash-8b-001	1177	±22	709	Google	Proprietary
144	125◄─►152	command-r	1170	±22	866	Cohere	CC-BY-NC-4.0
145	124◄─►157	c4ai-aya-expanse-8b	1161	±34	240	Cohere	CC-BY-NC-4.0
146	124◄─►157	mistral-small-24b-instruct-2501	1155	±36	275	Mistral	Apache 2.0
147	134◄─►157	gpt-3.5-turbo-0125	1149	±21	977	OpenAI	Proprietary
148	132◄─►162	reka-flash-21b-20240226-online	1145	±35	276	Reka AI	Proprietary
149	134◄─►158	qwen1.5-110b-chat	1143	±26	606	Alibaba	Qianwen LICENSE
150	136◄─►162	qwen1.5-72b-chat	1137	±27	502	Alibaba	Qianwen LICENSE
151	145◄─►163	gemma-2-2b-it	1125	±17	1,241	Google	Gemma license
152	143◄─►165	reka-flash-21b-20240226	1125	±29	444	Reka AI	Proprietary
153	145◄─►165	phi-3-medium-4k-instruct	1122	±23	690	Microsoft	MIT
154	145◄─►165	mixtral-8x22b-instruct-v0.1	1116	±20	988	Mistral	Apache 2.0
155	142◄─►171	gemini-pro-dev-api	1111	±45	173	Google	Proprietary
156	145◄─►168	qwen1.5-32b-chat	1107	±33	325	Alibaba	Qianwen LICENSE
157	149◄─►167	llama-3.1-8b-instruct	1093	±18	1,259	Meta	Llama 3.1 Community
158	145◄─►173	qwen1.5-14b-chat	1092	±40	219	Alibaba	Qianwen LICENSE
159	152◄─►167	llama-3-70b-instruct	1089	±14	3,319	Meta	Llama 3 Community
160	151◄─►171	mistral-large-2402	1087	±22	956	Mistral	Proprietary
161	149◄─►173	dbrx-instruct-preview	1085	±30	433	Databricks	DBRX LICENSE
162	149◄─►173	yi-1.5-34b-chat	1083	±27	512	01 AI	Apache-2.0
163	148◄─►173	jamba-1.5-mini	1083	±35	274	AI21 Labs	Jamba Open
164	149◄─►173	mistral-medium	1079	±33	340	Mistral	Proprietary
165	152◄─►176	yi-34b-chat	1064	±43	201	01 AI	Yi License
166	155◄─►176	gemma-1.1-7b-it	1055	±29	456	Google	Gemma license
167	157◄─►176	snowflake-arctic-instruct	1050	±24	670	Snowflake	Apache 2.0
168	155◄─►178	starling-lm-7b-beta	1048	±44	183	Nexusflow	Apache-2.0
169	160◄─►176	llama-3-8b-instruct	1042	±17	2,007	Meta	Llama 3 Community
170	158◄─►178	phi-3-small-8k-instruct	1041	±31	391	Microsoft	MIT
171	158◄─►178	phi-3-mini-4k-instruct-june-2024	1034	±33	360	Microsoft	MIT
172	158◄─►179	vicuna-33b	1031	±41	198	LMSYS	Non-commercial
173	165◄─►179	mixtral-8x7b-instruct-v0.1	1010	±22	968	Mistral	Apache 2.0
174	160◄─►179	vicuna-13b	1009	±53	125	LMSYS	Llama 2 Community
175	165◄─►179	phi-3-mini-4k-instruct	1007	±33	391	Microsoft	MIT
176	165◄─►179	llama-2-70b-chat	997	±33	344	Meta	Llama 2 Community
177	169◄─►179	phi-3-mini-128k-instruct	988	±31	387	Microsoft	MIT
178	169◄─►179	llama-2-13b-chat	968	±49	175	Meta	Llama 2 Community
179	172◄─►179	mistral-7b-instruct-v0.2	951	±46	167	Mistral	Apache-2.0

Text Arena

Default Leaderboard Plots

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

Battle Count for Each Combination of Models (without Ties)

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

Confidence Intervals on Model Strength (via Bootstrapping)