Text Arena

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

Last Updated

Dec 15, 2025

Total Votes

59,858

Total Models

181

/

Style Control

	Rank Spread (Upper-Lower)
1	1◄─►12	grok-4.1-thinking	1504	±33	402	xAI	Proprietary
2	1◄─►19	gemini-3-pro	1494	±31	427	Google	Proprietary
3	1◄─►30	claude-opus-4-5-20251101	1479	±38	261	Anthropic	Proprietary
4	1◄─►30	claude-sonnet-4-5-20250929	1469	±26	599	Anthropic	Proprietary
5	1◄─►39	claude-opus-4-1-20250805-thinking-16k	1457	±22	1,021	Anthropic	Proprietary
6	1◄─►63	grok-4-1-fast-reasoning	1454	±45	202	xAI	Proprietary
7	2◄─►41	gemini-2.5-pro	1453	±18	1,625	Google	Proprietary
8	2◄─►45	claude-opus-4-1-20250805	1450	±19	1,445	Anthropic	Proprietary
9	1◄─►56	gpt-5.1-high	1449	±33	352	OpenAI	Proprietary
10	2◄─►50	qwen3-max-preview	1447	±24	716	Alibaba	Proprietary
11	2◄─►48	chatgpt-4o-latest-20250326	1445	±20	1,158	OpenAI	Proprietary
12	1◄─►70	ernie-5.0-preview-1103	1445	±43	201	Baidu	Proprietary
13	1◄─►59	gpt-5.1	1444	±32	380	OpenAI	Proprietary
14	1◄─►59	grok-4.1	1443	±31	383	xAI	Proprietary
15	1◄─►68	claude-opus-4-5-20251101-thinking-32k	1443	±37	282	Anthropic	Proprietary
16	2◄─►55	claude-sonnet-4-5-20250929-thinking-32k	1441	±23	806	Anthropic	Proprietary
17	1◄─►75	grok-4-fast-chat	1434	±40	245	xAI	Proprietary
18	3◄─►69	glm-4.5	1430	±26	611	Z.ai	MIT
19	3◄─►69	qwen3-235b-a22b-instruct-2507	1425	±20	1,211	Alibaba	Apache 2.0
20	3◄─►72	glm-4.6	1424	±26	643	Z.ai	MIT
21	3◄─►72	claude-opus-4-20250514-thinking-16k	1421	±23	752	Anthropic	Proprietary
22	3◄─►76	qwen3-next-80b-a3b-instruct	1419	±27	601	Alibaba	Apache 2.0
23	2◄─►93	deepseek-v3.2-thinking	1419	±46	166	DeepSeek AI	MIT
24	3◄─►76	claude-haiku-4-5-20251001	1418	±26	634	Anthropic	Proprietary
25	2◄─►96	mistral-large-3	1417	±48	164	Mistral	Apache 2.0
26	5◄─►76	gpt-5-high	1416	±24	779	OpenAI	Proprietary
27	5◄─►76	gpt-5-chat	1416	±24	714	OpenAI	Proprietary
28	3◄─►84	kimi-k2-0905-preview	1415	±36	311	Moonshot	Modified MIT
29	3◄─►87	deepseek-v3.2-exp	1413	±36	294	DeepSeek AI	MIT
30	6◄─►77	grok-4-0709	1413	±22	904	xAI	Proprietary
31	7◄─►77	o3-2025-04-16	1412	±21	1,038	OpenAI	Proprietary
32	3◄─►86	kimi-k2-thinking-turbo	1411	±33	369	Moonshot	Modified MIT
33	3◄─►88	deepseek-v3.1-thinking	1409	±34	323	DeepSeek	MIT
34	8◄─►81	claude-sonnet-4-20250514	1407	±23	777	Anthropic	Proprietary
35	7◄─►82	qwen3-235b-a22b-no-thinking	1407	±25	649	Alibaba	Apache 2.0
36	5◄─►92	longcat-flash-chat	1407	±33	350	Meituan	MIT
37	5◄─►87	grok-3-preview-02-24	1407	±31	345	xAI	Proprietary
38	5◄─►94	qwen3-vl-235b-a22b-instruct	1405	±34	309	Alibaba	Apache 2.0
39	5◄─►93	qwen3-max-2025-09-23	1405	±32	364	Alibaba	Proprietary
40	7◄─►87	grok-4-fast-reasoning	1405	±27	513	xAI	Proprietary
41	5◄─►96	deepseek-v3.2-exp-thinking	1404	±36	277	DeepSeek AI	MIT
42	9◄─►82	mistral-medium-2508	1403	±21	1,161	Mistral	Proprietary
43	5◄─►96	deepseek-v3.1	1402	±34	345	DeepSeek	MIT
44	10◄─►85	gpt-4.1-2025-04-14	1400	±21	968	OpenAI	Proprietary
45	11◄─►82	gemini-2.5-flash	1399	±18	1,529	Google	Proprietary
46	10◄─►87	claude-opus-4-20250514	1398	±22	851	Anthropic	Proprietary
47	10◄─►93	claude-sonnet-4-20250514-thinking-32k	1396	±24	709	Anthropic	Proprietary
48	7◄─►99	deepseek-r1-0528	1395	±39	232	DeepSeek	MIT
49	3◄─►107	deepseek-r1	1392	±51	115	DeepSeek	MIT
50	12◄─►96	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1390	±23	840	Google	Proprietary
51	6◄─►106	gpt-5-nano-high	1390	±45	193	OpenAI	Proprietary
52	9◄─►100	qwen3-vl-235b-a22b-thinking	1389	±35	315	Alibaba	Apache 2.0
53	12◄─►97	mai-1-preview	1389	±27	540	Microsoft AI	Proprietary
54	5◄─►107	o1-2024-12-17	1389	±48	143	OpenAI	Proprietary
55	14◄─►97	gemini-2.5-flash-preview-09-2025	1388	±24	818	Google	Proprietary
56	15◄─►97	o4-mini-2025-04-16	1387	±22	867	OpenAI	Proprietary
57	12◄─►99	grok-3-mini-beta	1386	±30	390	xAI	Proprietary
58	15◄─►99	qwen3-30b-a3b-instruct-2507	1383	±26	612	Alibaba	Apache 2.0
59	14◄─►100	kimi-k2-0711-preview	1382	±29	507	Moonshot	Modified MIT
60	15◄─►100	claude-3-7-sonnet-20250219-thinking-32k	1382	±27	531	Anthropic	Proprietary
61	14◄─►100	qwen3-coder-480b-a35b-instruct	1381	±29	467	Alibaba	Apache 2.0
62	14◄─►103	mistral-medium-2505	1380	±29	490	Mistral	Proprietary
63	8◄─►117	deepseek-v3.2	1379	±48	145	DeepSeek AI	MIT
64	10◄─►107	ling-flash-2.0	1379	±39	242	Ant Group	MIT
65	8◄─►117	deepseek-v3	1379	±49	127	DeepSeek	DeepSeek
66	15◄─►104	qwen3-235b-a22b	1378	±30	410	Alibaba	Apache 2.0
67	18◄─►100	gpt-5-mini-high	1377	±25	725	OpenAI	Proprietary
68	10◄─►118	step-3	1375	±46	185	StepFun	Apache 2.0
69	14◄─►108	qwen2.5-max	1374	±36	258	Alibaba	Proprietary
70	19◄─►105	gemini-2.0-flash-001	1372	±27	506	Google	Proprietary
71	21◄─►104	gpt-oss-120b	1372	±24	735	OpenAI	Apache 2.0
72	19◄─►110	mistral-small-2506	1368	±33	357	Mistral	Apache 2.0
73	22◄─►107	claude-3-7-sonnet-20250219	1368	±26	557	Anthropic	Proprietary
74	26◄─►107	gemini-2.5-flash-lite-preview-06-17-thinking	1367	±25	680	Google	Proprietary
75	16◄─►119	ring-flash-2.0	1367	±39	258	Ant Group	MIT
76	28◄─►106	claude-3-5-sonnet-20241022	1365	±20	897	Anthropic	Proprietary
77	28◄─►108	glm-4.5-air	1362	±25	694	Z.ai	MIT
78	28◄─►123	qwen3-next-80b-a3b-thinking	1357	±31	393	Alibaba	Apache 2.0
79	32◄─►117	minimax-m1	1355	±24	695	MiniMax	Apache 2.0
80	35◄─►117	gpt-4.1-mini-2025-04-14	1354	±24	711	OpenAI	Proprietary
81	41◄─►115	command-a-03-2025	1353	±20	1,025	Cohere	CC-BY-NC-4.0
82	40◄─►116	claude-3-5-sonnet-20240620	1353	±21	1,127	Anthropic	Proprietary
83	29◄─►123	o1-preview	1352	±30	348	OpenAI	Proprietary
84	39◄─►117	deepseek-v3-0324	1352	±22	867	DeepSeek	MIT
85	40◄─►118	gemma-3-27b-it	1352	±23	793	Google	Gemma
86	28◄─►127	grok-3-mini-high	1352	±36	283	xAI	Proprietary
87	33◄─►123	gemini-1.5-pro-002	1350	±28	408	Google	Proprietary
88	21◄─►134	glm-4.5v	1348	±46	176	Z.ai	MIT
89	32◄─►128	qwq-32b	1347	±32	344	Alibaba	Apache 2.0
90	21◄─►136	o3-mini-high	1346	±50	127	OpenAI	Proprietary
91	52◄─►123	gpt-4o-2024-05-13	1342	±18	1,724	OpenAI	Proprietary
92	44◄─►133	yi-lightning	1341	±31	341	01 AI	Proprietary
93	45◄─►133	glm-4-plus	1340	±31	335	Zhipu AI	Proprietary
94	34◄─►138	gemini-2.0-flash-lite-preview-02-05	1334	±45	159	Google	Proprietary
95	52◄─►134	o1-mini	1333	±27	426	OpenAI	Proprietary
96	40◄─►138	magistral-medium-2506	1332	±42	218	Mistral	Proprietary
97	55◄─►134	gpt-4o-2024-08-06	1329	±25	551	OpenAI	Proprietary
98	60◄─►134	o3-mini	1329	±22	822	OpenAI	Proprietary
99	49◄─►138	qwen-max-0919	1327	±38	222	Alibaba	Qwen
100	64◄─►134	claude-3-5-haiku-20241022	1324	±22	876	Anthropic	Proprietary
101	63◄─►134	llama-4-maverick-17b-128e-instruct	1323	±24	723	Meta	Llama 4
102	45◄─►146	minimax-m2	1322	±48	180	MiniMax	Apache 2.0
103	60◄─►138	qwen3-30b-a3b	1321	±31	400	Alibaba	Apache 2.0
104	40◄─►147	nova-2-lite	1319	±56	128	Amazon	Proprietary
105	71◄─►135	gpt-4-1106-preview	1318	±20	1,484	OpenAI	Proprietary
106	74◄─►135	gpt-4-turbo-2024-04-09	1316	±19	1,448	OpenAI	Proprietary
107	66◄─►140	llama-3.1-405b-instruct-bf16	1315	±29	350	Meta	Llama 3.1 Community
108	74◄─►140	llama-3.1-405b-instruct-fp8	1312	±24	656	Meta	Llama 3.1 Community
109	83◄─►136	claude-3-opus-20240229	1312	±17	2,603	Anthropic	Proprietary
110	74◄─►140	grok-2-2024-08-13	1311	±23	671	xAI	Proprietary
111	76◄─►140	gpt-4o-mini-2024-07-18	1310	±22	744	OpenAI	Proprietary
112	73◄─►141	llama-4-scout-17b-16e-instruct	1310	±27	617	Meta	Llama
113	74◄─►140	grok-2-mini-2024-08-13	1310	±24	577	xAI	Proprietary
114	61◄─►147	amazon-nova-experimental-chat-10-20	1309	±41	232	Amazon	Proprietary
115	84◄─►140	gpt-4-0125-preview	1307	±21	1,226	OpenAI	Proprietary
116	60◄─►147	mistral-large-2411	1307	±44	156	Mistral	MRL
117	81◄─►144	llama-3.3-70b-instruct	1304	±25	574	Meta	Llama-3.3
118	84◄─►146	mistral-small-3.1-24b-instruct-2503	1302	±25	684	Mistral	Apache 2.0
119	75◄─►147	gemma-3n-e4b-it	1301	±31	404	Google	Gemma
120	88◄─►146	gemini-advanced-0514	1297	±23	907	Google	Proprietary
121	74◄─►150	athene-v2-chat	1296	±39	182	NexusFlow	NexusFlow
122	89◄─►146	gemini-1.5-pro-001	1296	±20	1,317	Google	Proprietary
123	73◄─►152	gpt-oss-20b	1295	±42	244	OpenAI	Apache 2.0
124	90◄─►146	llama-3-70b-instruct	1294	±17	2,789	Meta	Llama 3 Community
125	88◄─►148	qwen2.5-72b-instruct	1292	±30	348	Alibaba	Qwen
126	84◄─►150	athene-70b-0725	1291	±35	271	NexusFlow	CC-BY-NC-4.0
127	90◄─►147	gemma-2-27b-it	1291	±21	848	Google	Gemma license
128	90◄─►147	llama-3.1-70b-instruct	1290	±24	609	Meta	Llama 3.1 Community
129	90◄─►147	mistral-large-2407	1287	±24	586	Mistral	Mistral Research
130	90◄─►150	gpt-4-0314	1285	±26	661	OpenAI	Proprietary
131	88◄─►154	deepseek-v2.5	1284	±34	293	DeepSeek	DeepSeek
132	100◄─►150	gemini-1.5-flash-001	1276	±21	1,090	Google	Proprietary
133	92◄─►156	gemini-1.5-flash-002	1276	±33	284	Google	Proprietary
134	102◄─►152	claude-3-sonnet-20240229	1273	±20	1,471	Anthropic	Proprietary
135	84◄─►159	amazon-nova-lite-v1.0	1272	±54	108	Amazon	Proprietary
136	102◄─►154	gpt-4-0613	1270	±21	1,386	OpenAI	Proprietary
137	88◄─►161	phi-4	1269	±51	128	Microsoft	MIT
138	106◄─►156	mistral-large-2402	1265	±23	900	Mistral	Proprietary
139	106◄─►156	gemma-2-9b-it	1264	±24	619	Google	Gemma license
140	114◄─►157	command-r-plus	1256	±21	1,197	Cohere	CC-BY-NC-4.0
141	112◄─►159	nemotron-4-340b-instruct	1255	±31	367	Nvidia	NVIDIA Open Model
142	98◄─►165	amazon-nova-micro-v1.0	1254	±45	146	Amazon	Proprietary
143	113◄─►159	qwen2-72b-instruct	1253	±26	602	Alibaba	Qianwen LICENSE
144	113◄─►159	gemini-1.5-flash-8b-001	1252	±31	326	Google	Proprietary
145	113◄─►165	c4ai-aya-expanse-32b	1245	±36	256	Cohere	CC-BY-NC-4.0
146	127◄─►159	claude-3-haiku-20240307	1242	±19	1,719	Anthropic	Proprietary
147	131◄─►165	mixtral-8x22b-instruct-v0.1	1232	±24	846	Mistral	Apache 2.0
148	131◄─►165	gpt-3.5-turbo-0125	1231	±23	910	OpenAI	Proprietary
149	135◄─►164	llama-3-8b-instruct	1229	±19	1,763	Meta	Llama 3 Community
150	119◄─►174	gemini-pro-dev-api	1229	±42	214	Google	Proprietary
151	114◄─►177	amazon-nova-pro-v1.0	1228	±50	151	Amazon	Proprietary
152	133◄─►168	command-r	1227	±25	708	Cohere	CC-BY-NC-4.0
153	127◄─►173	deepseek-coder-v2	1224	±36	247	DeepSeek AI	DeepSeek License
154	126◄─►177	reka-flash-21b-20240226-online	1221	±41	225	Reka AI	Proprietary
155	135◄─►173	qwen1.5-110b-chat	1217	±29	503	Alibaba	Qianwen LICENSE
156	133◄─►178	gpt-3.5-turbo-1106	1213	±39	261	OpenAI	Proprietary
157	138◄─►177	mistral-medium	1208	±31	446	Mistral	Proprietary
158	139◄─►178	reka-flash-21b-20240226	1204	±31	412	Reka AI	Proprietary
159	139◄─►178	llama-2-70b-chat	1200	±28	511	Meta	Llama 2 Community
160	145◄─►178	llama-3.1-8b-instruct	1191	±26	566	Meta	Llama 3.1 Community
161	144◄─►178	qwen1.5-72b-chat	1190	±29	507	Alibaba	Qianwen LICENSE
162	145◄─►178	gemma-2-2b-it	1189	±26	545	Google	Gemma license
163	150◄─►178	mixtral-8x7b-instruct-v0.1	1183	±22	1,082	Mistral	Apache 2.0
164	146◄─►178	snowflake-arctic-instruct	1181	±29	507	Snowflake	Apache 2.0
165	145◄─►179	phi-3-small-8k-instruct	1180	±37	273	Microsoft	MIT
166	150◄─►179	qwen1.5-32b-chat	1173	±30	380	Alibaba	Qianwen LICENSE
167	151◄─►180	yi-1.5-34b-chat	1171	±29	472	01 AI	Apache-2.0
168	144◄─►181	vicuna-13b	1170	±48	161	LMSYS	Llama 2 Community
169	151◄─►180	phi-3-medium-4k-instruct	1168	±30	420	Microsoft	MIT
170	151◄─►180	qwen1.5-14b-chat	1161	±35	297	Alibaba	Qianwen LICENSE
171	151◄─►180	dbrx-instruct-preview	1159	±31	413	Databricks	DBRX LICENSE
172	154◄─►181	gemma-1.1-7b-it	1152	±31	424	Google	Gemma license
173	151◄─►181	llama-2-13b-chat	1151	±39	264	Meta	Llama 2 Community
174	154◄─►181	phi-3-mini-4k-instruct	1151	±31	416	Microsoft	MIT
175	153◄─►181	vicuna-33b	1150	±37	278	LMSYS	Non-commercial
176	154◄─►181	phi-3-mini-128k-instruct	1148	±34	368	Microsoft	MIT
177	150◄─►181	zephyr-7b-beta	1148	±55	129	HuggingFace	MIT
178	157◄─►181	yi-34b-chat	1136	±41	223	01 AI	Yi License
179	165◄─►181	mistral-7b-instruct-v0.2	1103	±44	205	Mistral	Apache-2.0
180	167◄─►181	gemma-1.1-2b-it	1093	±50	200	Google	Gemma license
181	171◄─►181	llama-2-7b-chat	1073	±51	146	Meta	Llama 2 Community

Text Arena

Default Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

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