Text Arena

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

Last Updated

Dec 21, 2025

Total Votes

52,096

Total Models

178

/

Style Control

	Rank Spread
1	1◄─►38	ernie-5.0-preview-1103	1503	±47	179	Baidu	Proprietary
2	1◄─►27	gemini-3-pro	1502	±31	425	Google	Proprietary
3	1◄─►37	gemini-2.5-pro	1482	±21	1,111	Google	Proprietary
4	1◄─►43	glm-4.6	1481	±32	426	Z.ai	MIT
5	1◄─►40	mistral-medium-2508	1479	±25	732	Mistral	Proprietary
6	1◄─►43	grok-4.1-thinking	1479	±32	391	xAI	Proprietary
7	1◄─►49	qwen3-vl-235b-a22b-instruct	1478	±51	139	Alibaba	Apache 2.0
8	1◄─►44	claude-opus-4-5-20251101	1477	±41	254	Anthropic	Proprietary
9	1◄─►44	qwen3-max-preview	1469	±31	396	Alibaba	Proprietary
10	1◄─►44	grok-3-preview-02-24	1469	±32	366	xAI	Proprietary
11	1◄─►50	claude-opus-4-5-20251101-thinking-32k	1468	±42	233	Anthropic	Proprietary
12	1◄─►47	gpt-5.1-high	1467	±35	336	OpenAI	Proprietary
13	1◄─►44	qwen3-235b-a22b-instruct-2507	1464	±23	824	Alibaba	Apache 2.0
14	1◄─►59	longcat-flash-chat	1464	±49	157	Meituan	MIT
15	1◄─►56	deepseek-v3.1	1461	±39	241	DeepSeek	MIT
16	1◄─►52	grok-4.1	1457	±32	412	xAI	Proprietary
17	1◄─►63	mistral-large-3	1455	±47	177	Mistral	Apache 2.0
18	1◄─►59	gpt-5.1	1452	±37	309	OpenAI	Proprietary
19	1◄─►54	gemini-2.5-flash-preview-09-2025	1452	±29	499	Google	Proprietary
20	1◄─►59	claude-sonnet-4-5-20250929	1447	±32	418	Anthropic	Proprietary
21	2◄─►56	o3-2025-04-16	1445	±24	767	OpenAI	Proprietary
22	2◄─►54	chatgpt-4o-latest-20250326	1445	±22	907	OpenAI	Proprietary
23	2◄─►58	claude-opus-4-1-20250805-thinking-16k	1444	±25	684	Anthropic	Proprietary
24	1◄─►64	glm-4.5	1442	±35	310	Z.ai	MIT
25	2◄─►58	claude-opus-4-1-20250805	1441	±23	914	Anthropic	Proprietary
26	1◄─►67	mai-1-preview	1438	±37	298	Microsoft AI	Proprietary
27	2◄─►64	claude-sonnet-4-5-20250929-thinking-32k	1435	±30	506	Anthropic	Proprietary
28	2◄─►68	kimi-k2-thinking-turbo	1434	±34	343	Moonshot	Modified MIT
29	2◄─►67	qwen3-next-80b-a3b-instruct	1434	±33	349	Alibaba	Apache 2.0
30	5◄─►62	gemini-2.5-flash	1431	±21	1,111	Google	Proprietary
31	1◄─►81	deepseek-v3.2	1430	±46	186	DeepSeek AI	MIT
32	2◄─►73	grok-4-fast-reasoning	1429	±38	261	xAI	Proprietary
33	2◄─►73	deepseek-r1-0528	1429	±40	220	DeepSeek	MIT
34	1◄─►81	grok-4-1-fast-reasoning	1429	±44	205	xAI	Proprietary
35	1◄─►81	deepseek-v3.2-exp	1428	±44	192	DeepSeek AI	MIT
36	4◄─►67	grok-4-0709	1428	±27	564	xAI	Proprietary
37	1◄─►82	amazon-nova-experimental-chat-10-20	1427	±45	191	Amazon	Proprietary
38	1◄─►86	gpt-4.5-preview-2025-02-27	1425	±56	121	OpenAI	Proprietary
39	4◄─►73	gpt-5-chat	1424	±31	400	OpenAI	Proprietary
40	2◄─►86	deepseek-v3.2-exp-thinking	1417	±50	135	DeepSeek AI	MIT
41	5◄─►81	qwen3-30b-a3b-instruct-2507	1417	±34	304	Alibaba	Apache 2.0
42	7◄─►76	glm-4.5-air	1417	±29	468	Z.ai	MIT
43	5◄─►82	qwen3-coder-480b-a35b-instruct	1416	±34	318	Alibaba	Apache 2.0
44	3◄─►86	deepseek-v3.2-thinking	1411	±48	168	DeepSeek AI	MIT
45	11◄─►84	gpt-5-high	1404	±31	447	OpenAI	Proprietary
46	11◄─►86	qwen2.5-max	1402	±33	329	Alibaba	Proprietary
47	12◄─►85	claude-opus-4-20250514-thinking-16k	1400	±29	472	Anthropic	Proprietary
48	15◄─►85	gemini-2.0-flash-001	1398	±26	514	Google	Proprietary
49	15◄─►86	deepseek-v3-0324	1397	±27	559	DeepSeek	MIT
50	13◄─►86	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1396	±30	469	Google	Proprietary
51	19◄─►86	gpt-4.1-2025-04-14	1395	±25	677	OpenAI	Proprietary
52	14◄─►86	gemini-2.5-flash-lite-preview-06-17-thinking	1393	±31	403	Google	Proprietary
53	11◄─►90	kimi-k2-0905-preview	1392	±44	171	Moonshot	Modified MIT
54	17◄─►86	claude-haiku-4-5-20251001	1391	±31	447	Anthropic	Proprietary
55	17◄─►87	gpt-5-mini-high	1389	±33	370	OpenAI	Proprietary
56	24◄─►87	minimax-m1	1385	±30	438	MiniMax	Apache 2.0
57	24◄─►87	qwen3-235b-a22b-no-thinking	1384	±28	479	Alibaba	Apache 2.0
58	14◄─►90	qwen3-next-80b-a3b-thinking	1383	±42	205	Alibaba	Apache 2.0
59	12◄─►94	hunyuan-turbos-20250416	1381	±49	147	Tencent	Proprietary
60	24◄─►87	mistral-medium-2505	1381	±29	459	Mistral	Proprietary
61	28◄─►87	gemma-3-27b-it	1380	±25	630	Google	Gemma
62	25◄─►90	kimi-k2-0711-preview	1376	±32	376	Moonshot	Modified MIT
63	28◄─►90	claude-sonnet-4-20250514	1375	±28	533	Anthropic	Proprietary
64	21◄─►96	deepseek-r1	1373	±42	188	DeepSeek	MIT
65	26◄─►94	grok-3-mini-beta	1370	±38	282	xAI	Proprietary
66	31◄─►90	gpt-oss-120b	1370	±31	408	OpenAI	Apache 2.0
67	28◄─►92	qwen3-235b-a22b	1370	±33	334	Alibaba	Apache 2.0
68	32◄─►90	claude-sonnet-4-20250514-thinking-32k	1369	±29	431	Anthropic	Proprietary
69	19◄─►103	nova-2-lite	1368	±51	158	Amazon	Proprietary
70	32◄─►90	o4-mini-2025-04-16	1367	±26	580	OpenAI	Proprietary
71	32◄─►94	qwen3-30b-a3b	1366	±33	328	Alibaba	Apache 2.0
72	36◄─►92	command-a-03-2025	1362	±24	706	Cohere	CC-BY-NC-4.0
73	35◄─►94	gpt-4.1-mini-2025-04-14	1362	±28	542	OpenAI	Proprietary
74	36◄─►94	claude-opus-4-20250514	1360	±27	577	Anthropic	Proprietary
75	32◄─►103	gemini-2.0-flash-lite-preview-02-05	1355	±38	256	Google	Proprietary
76	36◄─►103	o1-preview	1353	±34	291	OpenAI	Proprietary
77	35◄─►106	o1-2024-12-17	1352	±37	253	OpenAI	Proprietary
78	32◄─►112	grok-3-mini-high	1350	±44	167	xAI	Proprietary
79	36◄─►107	deepseek-v3	1350	±37	243	DeepSeek	DeepSeek
80	40◄─►107	qwq-32b	1348	±34	294	Alibaba	Apache 2.0
81	35◄─►111	mistral-small-2506	1348	±41	227	Mistral	Apache 2.0
82	36◄─►117	o3-mini-high	1342	±44	204	OpenAI	Proprietary
83	42◄─►112	athene-v2-chat	1341	±36	228	NexusFlow	NexusFlow
84	42◄─►117	qwen-max-0919	1337	±40	183	Alibaba	Qwen
85	45◄─►113	gemma-3n-e4b-it	1336	±35	307	Google	Gemma
86	43◄─►119	mistral-large-2411	1333	±40	204	Mistral	MRL
87	54◄─►111	o3-mini	1332	±24	654	OpenAI	Proprietary
88	59◄─►114	grok-2-2024-08-13	1325	±25	605	xAI	Proprietary
89	59◄─►124	glm-4-plus	1316	±36	286	Zhipu AI	Proprietary
90	66◄─►122	gemini-advanced-0514	1314	±24	757	Google	Proprietary
91	73◄─►119	gpt-4o-2024-05-13	1313	±19	1,356	OpenAI	Proprietary
92	59◄─►124	yi-lightning	1312	±36	272	01 AI	Proprietary
93	66◄─►124	claude-3-7-sonnet-20250219	1310	±28	508	Anthropic	Proprietary
94	68◄─►124	gemini-1.5-pro-002	1309	±27	460	Google	Proprietary
95	74◄─►123	claude-3-5-sonnet-20241022	1308	±21	826	Anthropic	Proprietary
96	74◄─►124	gpt-4o-mini-2024-07-18	1304	±23	654	OpenAI	Proprietary
97	74◄─►124	claude-3-5-sonnet-20240620	1301	±22	938	Anthropic	Proprietary
98	74◄─►126	o1-mini	1300	±29	424	OpenAI	Proprietary
99	74◄─►128	llama-4-scout-17b-16e-instruct	1298	±31	395	Meta	Llama
100	73◄─►130	deepseek-v2.5	1295	±37	223	DeepSeek	DeepSeek
101	68◄─►131	athene-70b-0725	1294	±41	206	NexusFlow	CC-BY-NC-4.0
102	74◄─►128	grok-2-mini-2024-08-13	1294	±27	472	xAI	Proprietary
103	77◄─►128	llama-3.3-70b-instruct	1291	±26	541	Meta	Llama-3.3
104	80◄─►127	gpt-4-1106-preview	1290	±19	1,737	OpenAI	Proprietary
105	80◄─►128	gpt-4-0125-preview	1289	±20	1,522	OpenAI	Proprietary
106	77◄─►129	claude-3-7-sonnet-20250219-thinking-32k	1287	±30	487	Anthropic	Proprietary
107	77◄─►131	qwen2.5-72b-instruct	1286	±31	343	Alibaba	Qwen
108	78◄─►130	llama-3.1-405b-instruct-bf16	1285	±30	365	Meta	Llama 3.1 Community
109	84◄─►128	gpt-4-turbo-2024-04-09	1283	±20	1,402	OpenAI	Proprietary
110	86◄─►128	claude-3-opus-20240229	1282	±16	2,850	Anthropic	Proprietary
111	74◄─►132	amazon-nova-pro-v1.0	1282	±38	224	Amazon	Proprietary
112	80◄─►131	mistral-large-2407	1280	±28	443	Mistral	Mistral Research
113	82◄─►131	llama-3.1-405b-instruct-fp8	1280	±26	549	Meta	Llama 3.1 Community
114	85◄─►129	gemini-1.5-pro-001	1280	±21	1,081	Google	Proprietary
115	88◄─►132	gpt-4o-2024-08-06	1270	±27	459	OpenAI	Proprietary
116	88◄─►132	llama-3.1-70b-instruct	1269	±27	501	Meta	Llama 3.1 Community
117	86◄─►135	mistral-small-3.1-24b-instruct-2503	1268	±32	418	Mistral	Apache 2.0
118	90◄─►132	claude-3-5-haiku-20241022	1267	±23	789	Anthropic	Proprietary
119	86◄─►135	gemini-1.5-flash-002	1266	±33	297	Google	Proprietary
120	90◄─►135	llama-4-maverick-17b-128e-instruct	1264	±27	566	Meta	Llama 4
121	80◄─►141	magistral-medium-2506	1261	±50	165	Mistral	Proprietary
122	91◄─►137	c4ai-aya-expanse-32b	1255	±34	274	Cohere	CC-BY-NC-4.0
123	98◄─►135	gemma-2-27b-it	1255	±21	795	Google	Gemma license
124	100◄─►136	gemini-1.5-flash-001	1248	±22	922	Google	Proprietary
125	90◄─►143	amazon-nova-micro-v1.0	1246	±44	164	Amazon	Proprietary
126	92◄─►143	amazon-nova-lite-v1.0	1242	±44	171	Amazon	Proprietary
127	98◄─►141	gemini-1.5-flash-8b-001	1242	±32	334	Google	Proprietary
128	108◄─►136	llama-3-70b-instruct	1240	±17	2,514	Meta	Llama 3 Community
129	110◄─►138	claude-3-sonnet-20240229	1237	±19	1,826	Anthropic	Proprietary
130	99◄─►149	phi-4	1232	±39	206	Microsoft	MIT
131	114◄─►143	gpt-4-0314	1227	±24	843	OpenAI	Proprietary
132	118◄─►145	mistral-large-2402	1217	±22	1,055	Mistral	Proprietary
133	118◄─►145	command-r-plus	1216	±21	1,234	Cohere	CC-BY-NC-4.0
134	106◄─►157	mistral-small-24b-instruct-2501	1211	±50	142	Mistral	Apache 2.0
135	118◄─►154	nemotron-4-340b-instruct	1207	±33	356	Nvidia	NVIDIA Open Model
136	125◄─►153	claude-3-haiku-20240307	1202	±18	1,777	Anthropic	Proprietary
137	124◄─►154	gemma-2-9b-it	1198	±25	592	Google	Gemma license
138	122◄─►158	deepseek-coder-v2	1191	±41	207	DeepSeek AI	DeepSeek License
139	126◄─►157	mistral-medium	1187	±26	723	Mistral	Proprietary
140	126◄─►157	llama-3.1-8b-instruct	1187	±28	482	Meta	Llama 3.1 Community
141	126◄─►158	reka-flash-21b-20240226	1183	±30	432	Reka AI	Proprietary
142	128◄─►158	qwen2-72b-instruct	1178	±25	597	Alibaba	Qianwen LICENSE
143	131◄─►157	gpt-4-0613	1178	±20	1,551	OpenAI	Proprietary
144	133◄─►158	mixtral-8x7b-instruct-v0.1	1174	±21	1,258	Mistral	Apache 2.0
145	131◄─►158	mixtral-8x22b-instruct-v0.1	1173	±24	775	Mistral	Apache 2.0
146	133◄─►159	command-r	1170	±24	841	Cohere	CC-BY-NC-4.0
147	128◄─►165	reka-flash-21b-20240226-online	1169	±40	231	Reka AI	Proprietary
148	134◄─►158	llama-3-8b-instruct	1168	±19	1,640	Meta	Llama 3 Community
149	134◄─►159	qwen1.5-72b-chat	1167	±23	862	Alibaba	Qianwen LICENSE
150	133◄─►161	gemma-2-2b-it	1165	±29	469	Google	Gemma license
151	133◄─►163	yi-1.5-34b-chat	1163	±31	403	01 AI	Apache-2.0
152	134◄─►165	qwen1.5-110b-chat	1160	±32	378	Alibaba	Qianwen LICENSE
153	134◄─►166	gemini-pro-dev-api	1153	±31	462	Google	Proprietary
154	135◄─►168	phi-3-small-8k-instruct	1143	±35	271	Microsoft	MIT
155	137◄─►167	snowflake-arctic-instruct	1141	±29	529	Snowflake	Apache 2.0
156	147◄─►169	gpt-3.5-turbo-0125	1126	±21	1,293	OpenAI	Proprietary
157	137◄─►172	qwen1.5-14b-chat	1125	±38	278	Alibaba	Qianwen LICENSE
158	137◄─►172	starling-lm-7b-beta	1124	±38	248	Nexusflow	Apache-2.0
159	141◄─►170	phi-3-medium-4k-instruct	1122	±33	352	Microsoft	MIT
160	149◄─►176	qwen1.5-32b-chat	1107	±34	310	Alibaba	Qianwen LICENSE
161	150◄─►174	dbrx-instruct-preview	1104	±29	544	Databricks	DBRX LICENSE
162	149◄─►176	openchat-3.5-0106	1100	±42	212	OpenChat	Apache-2.0
163	153◄─►176	llama-2-70b-chat	1098	±26	683	Meta	Llama 2 Community
164	151◄─►176	vicuna-33b	1094	±37	295	LMSYS	Non-commercial
165	150◄─►176	starling-lm-7b-alpha	1093	±42	211	UC Berkeley	CC-BY-NC-4.0
166	151◄─►176	yi-34b-chat	1089	±40	236	01 AI	Yi License
167	154◄─►176	phi-3-mini-4k-instruct	1086	±35	310	Microsoft	MIT
168	156◄─►176	gemma-1.1-7b-it	1074	±31	407	Google	Gemma license
169	155◄─►176	gpt-3.5-turbo-1106	1074	±38	310	OpenAI	Proprietary
170	157◄─►177	llama-2-13b-chat	1053	±39	265	Meta	Llama 2 Community
171	160◄─►177	phi-3-mini-128k-instruct	1047	±34	372	Microsoft	MIT
172	161◄─►177	mistral-7b-instruct-v0.2	1043	±31	479	Mistral	Apache-2.0
173	158◄─►178	zephyr-7b-beta	1040	±48	154	HuggingFace	MIT
174	158◄─►178	stripedhyena-nous-7b	1039	±49	170	Together AI	Apache 2.0
175	160◄─►178	gemma-7b-it	1031	±47	201	Google	Gemma license
176	161◄─►178	vicuna-13b	1029	±44	200	LMSYS	Llama 2 Community
177	170◄─►178	llama-2-7b-chat	981	±42	257	Meta	Llama 2 Community
178	173◄─►178	mistral-7b-instruct	954	±48	175	Mistral	Apache 2.0

Text Arena

Remove Style Control Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

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

Confidence Intervals on Model Strength (via Bootstrapping)

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