Text Arena

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

Last Updated

Jan 16, 2026

Total Votes

761,748

Total Models

277

/

Style Control

	Rank Spread
1	1◄─►6	claude-opus-4-5-20251101	1495	±9	4,843	Anthropic	Proprietary
2	1◄─►6	claude-opus-4-5-20251101-thinking-32k	1492	±10	4,520	Anthropic	Proprietary
3	1◄─►6	gemini-3-pro	1490	±8	6,690	Google	Proprietary
4	1◄─►7	claude-opus-4-1-20250805-thinking-16k	1483	±6	10,974	Anthropic	Proprietary
5	1◄─►8	claude-sonnet-4-5-20250929-thinking-32k	1483	±7	8,743	Anthropic	Proprietary
6	1◄─►9	claude-sonnet-4-5-20250929	1479	±8	8,282	Anthropic	Proprietary
7	6◄─►14	claude-opus-4-1-20250805	1469	±6	14,883	Anthropic	Proprietary
8	4◄─►17	gemini-3-flash	1468	±11	3,221	Google	Proprietary
9	5◄─►21	gemini-3-flash (thinking-minimal)	1464	±12	2,336	Google	Proprietary
10	7◄─►20	claude-opus-4-20250514-thinking-16k	1462	±8	7,161	Anthropic	Proprietary
11	7◄─►21	gpt-5.1-high	1461	±9	5,637	OpenAI	Proprietary
12	7◄─►20	gemini-2.5-pro	1459	±5	18,953	Google	Proprietary
13	7◄─►34	glm-4.7	1454	±12	2,382	Z.ai	MIT
14	8◄─►34	grok-4.1	1450	±8	7,076	xAI	Proprietary
15	7◄─►43	gpt-5.2	1449	±17	1,308	OpenAI	Proprietary
16	9◄─►34	grok-4.1-thinking	1449	±8	6,541	xAI	Proprietary
17	8◄─►40	deepseek-v3.1-thinking	1447	±12	2,404	DeepSeek	MIT
18	13◄─►38	claude-opus-4-20250514	1444	±7	8,588	Anthropic	Proprietary
19	13◄─►40	gpt-5.1	1443	±8	6,484	OpenAI	Proprietary
20	13◄─►41	qwen3-max-preview	1442	±8	5,991	Alibaba	Proprietary
21	9◄─►46	gpt-4.5-preview-2025-02-27	1441	±14	1,796	OpenAI	Proprietary
22	11◄─►46	gpt-5.2-high	1440	±13	2,065	OpenAI	Proprietary
23	13◄─►46	deepseek-v3.2	1439	±10	4,429	DeepSeek	MIT
24	9◄─►53	ernie-5.0-0110	1439	±17	1,079	Baidu	Proprietary
25	13◄─►43	claude-sonnet-4-20250514-thinking-32k	1438	±8	6,961	Anthropic	Proprietary
26	13◄─►46	deepseek-v3.2-exp	1438	±11	2,813	DeepSeek	MIT
27	13◄─►43	chatgpt-4o-latest-20250326	1438	±6	14,982	OpenAI	Proprietary
28	8◄─►64	deepseek-v3.1-terminus-thinking	1437	±22	709	DeepSeek	MIT
29	13◄─►46	deepseek-v3.2-thinking	1436	±10	3,516	DeepSeek	MIT
30	13◄─►46	gpt-5-chat	1436	±8	6,714	OpenAI	Proprietary
31	13◄─►45	qwen3-235b-a22b-instruct-2507	1436	±6	13,811	Alibaba	Apache 2.0
32	13◄─►53	ernie-5.0-preview-1203	1433	±12	2,424	Baidu	Proprietary
33	13◄─►54	qwen3-max-2025-09-23	1432	±13	2,096	Alibaba	Proprietary
34	16◄─►48	claude-haiku-4-5-20251001	1432	±7	8,723	Anthropic	Proprietary
35	16◄─►50	kimi-k2-thinking-turbo	1431	±8	6,160	Moonshot	Modified MIT
36	16◄─►50	glm-4.6	1431	±7	8,017	Z.ai	MIT
37	13◄─►58	deepseek-v3.2-exp-thinking	1430	±13	2,045	DeepSeek	MIT
38	17◄─►56	grok-3-preview-02-24	1427	±9	5,094	xAI	Proprietary
39	20◄─►58	claude-3-7-sonnet-20250219-thinking-32k	1425	±8	6,388	Anthropic	Proprietary
40	16◄─►67	qwen3-vl-235b-a22b-instruct	1424	±13	2,218	Alibaba	Apache 2.0
41	23◄─►61	claude-sonnet-4-20250514	1423	±7	7,930	Anthropic	Proprietary
42	24◄─►61	gpt-4.1-2025-04-14	1423	±6	10,037	OpenAI	Proprietary
43	23◄─►67	deepseek-v3.1	1420	±10	3,288	DeepSeek	MIT
44	19◄─►70	grok-4-fast-chat	1419	±15	1,531	xAI	Proprietary
45	31◄─►65	gemini-2.5-flash	1418	±5	17,988	Google	Proprietary
46	30◄─►70	glm-4.5	1417	±9	5,080	Z.ai	MIT
47	20◄─►74	ernie-5.0-preview-1022	1417	±17	1,135	Baidu	Proprietary
48	17◄─►77	deepseek-v3.1-terminus	1416	±20	854	DeepSeek	MIT
49	30◄─►70	grok-4-1-fast-reasoning	1416	±9	4,927	xAI	Proprietary
50	33◄─►70	grok-4-0709	1415	±7	8,964	xAI	Proprietary
51	33◄─►70	gemini-2.5-flash-preview-09-2025	1415	±7	7,772	Google	Proprietary
52	31◄─►70	mistral-large-3	1414	±10	4,025	Mistral	Apache 2.0
53	37◄─►72	gpt-5-high	1411	±8	6,901	OpenAI	Proprietary
54	35◄─►73	o1-2024-12-17	1410	±10	3,574	OpenAI	Proprietary
55	41◄─►70	mistral-medium-2508	1410	±6	12,760	Mistral	Proprietary
56	39◄─►72	qwen3-235b-a22b-no-thinking	1410	±8	7,415	Alibaba	Apache 2.0
57	36◄─►73	grok-4-fast-reasoning	1410	±9	4,381	xAI	Proprietary
58	33◄─►77	mimo-v2-flash (non-thinking)	1409	±12	2,259	Xiaomi	MIT
59	41◄─►73	claude-3-7-sonnet-20250219	1408	±7	6,976	Anthropic	Proprietary
60	39◄─►77	deepseek-r1-0528	1406	±10	3,325	DeepSeek	MIT
61	43◄─►75	o3-2025-04-16	1406	±6	11,843	OpenAI	Proprietary
62	36◄─►80	minimax-m2.1-preview	1405	±13	2,047	MiniMax	MIT
63	42◄─►77	qwen3-coder-480b-a35b-instruct	1405	±9	5,053	Alibaba	Apache 2.0
64	37◄─►81	qwen3-vl-235b-a22b-thinking	1404	±14	1,726	Alibaba	Apache 2.0
65	41◄─►85	qwen3-235b-a22b-thinking-2507	1402	±14	1,676	Alibaba	Apache 2.0
66	43◄─►85	kimi-k2-0905-preview	1400	±12	2,536	Moonshot	Modified MIT
67	45◄─►89	deepseek-r1	1397	±12	2,326	DeepSeek	MIT
68	39◄─►108	hunyuan-vision-1.5-thinking	1392	±25	499	Tencent	Proprietary
69	57◄─►91	kimi-k2-0711-preview	1392	±8	5,708	Moonshot	Modified MIT
70	59◄─►87	claude-3-5-sonnet-20241022	1392	±6	14,047	Anthropic	Proprietary
71	54◄─►93	mai-1-preview	1391	±10	3,640	Microsoft AI	Proprietary
72	58◄─►92	qwen3-next-80b-a3b-instruct	1391	±9	5,158	Alibaba	Apache 2.0
73	59◄─►90	deepseek-v3-0324	1391	±7	8,676	DeepSeek	MIT
74	45◄─►105	hunyuan-t1-20250711	1389	±20	892	Tencent	Proprietary
75	63◄─►95	mistral-medium-2505	1388	±8	6,208	Mistral	Proprietary
76	45◄─►109	amazon-nova-experimental-chat-12-10	1387	±21	682	Amazon	Proprietary
77	63◄─►96	gpt-4.1-mini-2025-04-14	1385	±7	7,330	OpenAI	Proprietary
78	63◄─►102	longcat-flash-chat	1384	±12	2,374	Meituan	MIT
79	65◄─►98	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1383	±7	9,410	Google	Proprietary
80	64◄─►98	qwen2.5-max	1383	±8	4,675	Alibaba	Proprietary
81	65◄─►102	qwen3-30b-a3b-instruct-2507	1380	±9	4,943	Alibaba	Apache 2.0
82	65◄─►104	o1-preview	1380	±10	4,579	OpenAI	Proprietary
83	52◄─►124	glm-4.6v	1379	±23	652	Z.ai	MIT
84	67◄─►103	gemini-2.5-flash-lite-preview-06-17-thinking	1378	±8	6,526	Google	Proprietary
85	68◄─►103	glm-4.5-air	1378	±8	6,636	Z.ai	MIT
86	67◄─►106	qwen3-235b-a22b	1378	±9	4,802	Alibaba	Apache 2.0
87	68◄─►109	grok-3-mini-high	1376	±10	3,422	xAI	Proprietary
88	65◄─►115	hunyuan-turbos-20250416	1375	±14	1,613	Tencent	Proprietary
89	52◄─►130	hunyuan-large-2025-02-10	1375	±29	371	Tencent	Proprietary
90	70◄─►112	deepseek-v3	1373	±10	3,127	DeepSeek	DeepSeek
91	71◄─►118	o3-mini-high	1371	±12	2,159	OpenAI	Proprietary
92	75◄─►115	gpt-5-mini-high	1369	±8	5,729	OpenAI	Proprietary
93	75◄─►112	minimax-m1	1369	±7	7,311	MiniMax	Apache 2.0
94	73◄─►121	qwen3-next-80b-a3b-thinking	1369	±11	2,812	Alibaba	Apache 2.0
95	73◄─►124	amazon-nova-experimental-chat-11-10	1367	±13	2,079	Amazon	Proprietary
96	77◄─►115	command-a-03-2025	1367	±6	10,726	Cohere	CC-BY-NC-4.0
97	77◄─►115	o4-mini-2025-04-16	1367	±7	8,801	OpenAI	Proprietary
98	77◄─►124	grok-3-mini-beta	1365	±9	4,377	xAI	Proprietary
99	79◄─►123	gemini-2.0-flash-001	1364	±7	6,694	Google	Proprietary
100	82◄─►124	gemma-3-27b-it	1362	±7	6,848	Google	Gemma
101	72◄─►138	qwen-plus-0125	1361	±21	690	Alibaba	Proprietary
102	87◄─►126	o3-mini	1357	±6	9,535	OpenAI	Proprietary
103	85◄─►130	mistral-small-2506	1357	±10	3,561	Mistral	Apache 2.0
104	89◄─►129	gemini-1.5-pro-002	1355	±7	8,370	Google	Proprietary
105	74◄─►154	qwen3-32b	1354	±25	511	Alibaba	Apache 2.0
106	69◄─►161	hunyuan-turbos-20250226	1353	±32	289	Tencent	Proprietary
107	87◄─►139	amazon-nova-experimental-chat-10-20	1351	±12	2,535	Amazon	Proprietary
108	84◄─►147	intellect-3	1350	±17	1,231	Prime Intellect	MIT
109	95◄─►136	claude-3-5-sonnet-20240620	1350	±8	10,574	Anthropic	Proprietary
110	96◄─►139	gemini-1.5-pro-001	1348	±8	9,751	Google	Proprietary
111	95◄─►142	gemini-2.0-flash-lite-preview-02-05	1346	±10	2,958	Google	Proprietary
112	84◄─►156	nvidia-llama-3.3-nemotron-super-49b-v1.5	1346	±21	672	Nvidia	Nvidia Open
113	89◄─►154	step-3	1345	±16	1,262	StepFun	Apache 2.0
114	77◄─►165	gemma-3-12b-it	1344	±29	376	Google	Gemma
115	93◄─►156	minimax-m2	1344	±15	1,535	MiniMax	Apache 2.0
116	93◄─►156	step-1o-turbo-202506	1343	±16	1,409	StepFun	Proprietary
117	101◄─►144	o1-mini	1343	±7	7,915	OpenAI	Proprietary
118	102◄─►144	claude-3-5-haiku-20241022	1341	±6	11,233	Anthropic	Proprietary
119	94◄─►159	glm-4.5v	1340	±18	1,065	Z.ai	MIT
120	89◄─►163	step-2-16k-exp-202412	1340	±21	693	StepFun	Proprietary
121	81◄─►169	llama-3.1-nemotron-ultra-253b-v1	1340	±30	322	Nvidia	Nvidia Open Model
122	82◄─►169	hunyuan-turbo-0110	1340	±30	314	Tencent	Proprietary
123	101◄─►152	qwen3-30b-a3b	1340	±9	4,681	Alibaba	Apache 2.0
124	94◄─►163	glm-4-plus-0111	1338	±20	765	Zhipu	Proprietary
125	101◄─►156	nova-2-lite	1337	±11	2,840	Amazon	Proprietary
126	104◄─►156	qwq-32b	1336	±9	4,171	Alibaba	Apache 2.0
127	104◄─►156	gpt-4o-2024-08-06	1336	±8	6,159	OpenAI	Proprietary
128	100◄─►163	deepseek-v2.5-1210	1336	±17	1,037	DeepSeek	DeepSeek
129	93◄─►168	amazon-nova-experimental-chat-10-09	1335	±24	588	Amazon	Proprietary
130	87◄─►173	llama-3.3-nemotron-49b-super-v1	1335	±30	323	Nvidia	Nvidia
131	105◄─►156	llama-4-maverick-17b-128e-instruct	1333	±7	7,306	Meta	Llama 4
132	104◄─►162	magistral-medium-2506	1333	±12	2,490	Mistral	Proprietary
133	106◄─►156	grok-2-2024-08-13	1333	±7	8,904	xAI	Proprietary
134	100◄─►167	olmo-3.1-32b-instruct	1332	±20	897	Allen AI	Apache 2.0
135	94◄─►172	hunyuan-standard-2025-02-10	1332	±27	435	Tencent	Proprietary
136	104◄─►165	ring-flash-2.0	1329	±16	1,349	Ant Group	MIT
137	108◄─►159	gpt-4o-2024-05-13	1329	±7	14,919	OpenAI	Proprietary
138	104◄─►166	gpt-5-nano-high	1327	±15	1,635	OpenAI	Proprietary
139	111◄─►163	llama-4-scout-17b-16e-instruct	1325	±8	5,954	Meta	Llama
140	105◄─►169	ling-flash-2.0	1325	±16	1,248	Ant Group	MIT
141	112◄─►163	claude-3-opus-20240229	1325	±6	23,373	Anthropic	Proprietary
142	112◄─►164	gpt-oss-120b	1325	±8	6,462	OpenAI	Apache 2.0
143	112◄─►165	llama-3.1-405b-instruct-bf16	1324	±8	5,479	Meta	Llama 3.1 Community
144	104◄─►174	gpt-4.1-nano-2025-04-14	1324	±20	742	OpenAI	Proprietary
145	109◄─►168	qwen-max-0919	1324	±12	2,440	Alibaba	Qwen
146	111◄─►165	glm-4-plus	1324	±10	3,992	Zhipu AI	Proprietary
147	113◄─►165	gpt-4o-mini-2024-07-18	1324	±7	8,997	OpenAI	Proprietary
148	111◄─►165	yi-lightning	1323	±11	3,633	01 AI	Proprietary
149	113◄─►165	mistral-small-3.1-24b-instruct-2503	1323	±8	6,486	Mistral	Apache 2.0
150	112◄─►168	gemini-advanced-0514	1321	±10	5,486	Google	Proprietary
151	115◄─►168	gemini-1.5-flash-002	1320	±8	5,466	Google	Proprietary
152	115◄─►169	athene-v2-chat	1319	±10	3,663	NexusFlow	NexusFlow
153	108◄─►177	hunyuan-large-vision	1319	±19	944	Tencent	Proprietary
154	109◄─►177	olmo-3-32b-think	1319	±17	1,309	Allen AI	Apache 2.0
155	123◄─►169	llama-3.1-405b-instruct-fp8	1316	±8	8,050	Meta	Llama 3.1 Community
156	123◄─►170	qwen2.5-72b-instruct	1315	±8	6,007	Alibaba	Qwen
157	123◄─►170	grok-2-mini-2024-08-13	1315	±8	7,052	xAI	Proprietary
158	126◄─►172	gpt-4-turbo-2024-04-09	1314	±8	11,561	OpenAI	Proprietary
159	125◄─►177	deepseek-v2.5	1312	±10	3,500	DeepSeek	DeepSeek
160	125◄─►177	gemma-3n-e4b-it	1311	±11	2,961	Google	Gemma
161	133◄─►175	llama-3.3-70b-instruct	1310	±7	8,474	Meta	Llama-3.3
162	108◄─►193	gemma-3-4b-it	1310	±27	449	Google	Gemma
163	127◄─►187	qwen2.5-plus-1127	1306	±14	1,584	Alibaba	Proprietary
164	141◄─►183	gpt-4-0125-preview	1304	±9	9,653	OpenAI	Proprietary
165	112◄─►196	mercury	1304	±28	478	Inception AI	Proprietary
166	132◄─►190	olmo-3.1-32b-think	1303	±14	1,867	Allen AI	Apache 2.0
167	142◄─►187	mistral-large-2411	1303	±10	3,607	Mistral	MRL
168	146◄─►187	mistral-large-2407	1302	±9	5,885	Mistral	Mistral Research
169	140◄─►190	gpt-oss-20b	1299	±13	2,125	OpenAI	Apache 2.0
170	153◄─►190	gemini-1.5-flash-001	1298	±9	7,837	Google	Proprietary
171	151◄─►190	amazon-nova-pro-v1.0	1298	±10	3,412	Amazon	Proprietary
172	153◄─►190	gpt-4-1106-preview	1298	±8	9,141	OpenAI	Proprietary
173	157◄─►189	gemma-2-27b-it	1297	±7	9,921	Google	Gemma license
174	162◄─►191	llama-3.1-70b-instruct	1291	±8	7,623	Meta	Llama 3.1 Community
175	158◄─►195	athene-70b-0725	1290	±12	2,123	NexusFlow	CC-BY-NC-4.0
176	156◄─►203	ibm-granite-h-small	1287	±18	1,262	IBM	Apache 2.0
177	162◄─►195	c4ai-aya-expanse-32b	1287	±9	4,166	Cohere	CC-BY-NC-4.0
178	155◄─►205	gemma-2-9b-it-simpo	1286	±19	841	Princeton	MIT
179	162◄─►200	nvidia-nemotron-3-nano-30b-a3b-bf16	1285	±12	2,832	Nvidia	NVIDIA Open Model
180	162◄─►201	nemotron-4-340b-instruct	1285	±13	2,130	Nvidia	NVIDIA Open Model
181	157◄─►205	qwen2.5-coder-32b-instruct	1285	±19	804	Alibaba	Apache 2.0
182	162◄─►203	deepseek-coder-v2	1284	±14	1,842	DeepSeek	DeepSeek License
183	166◄─►200	claude-3-sonnet-20240229	1282	±9	11,870	Anthropic	Proprietary
184	162◄─►205	llama-3.1-nemotron-70b-instruct	1279	±18	1,048	Nvidia	Llama 3.1
185	163◄─►205	command-r-plus-08-2024	1278	±15	1,369	Cohere	CC-BY-NC-4.0
186	166◄─►205	mistral-small-24b-instruct-2501	1277	±14	1,764	Mistral	Apache 2.0
187	163◄─►206	reka-core-20240904	1277	±18	950	Reka AI	Proprietary
188	173◄─►205	gpt-4-0613	1274	±9	7,524	OpenAI	Proprietary
189	172◄─►205	gpt-4-0314	1273	±12	4,250	OpenAI	Proprietary
190	173◄─►205	amazon-nova-lite-v1.0	1272	±11	2,785	Amazon	Proprietary
191	163◄─►212	llama-3.1-tulu-3-70b	1270	±25	463	Ai2	Llama 3.1
192	163◄─►213	hunyuan-standard-256k	1268	±27	414	Tencent	Proprietary
193	167◄─►212	llama-3.1-nemotron-51b-instruct	1267	±23	587	Nvidia	Llama 3.1
194	174◄─►211	glm-4-0520	1265	±17	1,174	Zhipu AI	Proprietary
195	177◄─►209	phi-4	1264	±11	2,898	Microsoft	MIT
196	179◄─►208	gemini-1.5-flash-8b-001	1264	±8	5,568	Google	Proprietary
197	180◄─►209	claude-3-haiku-20240307	1262	±8	13,976	Anthropic	Proprietary
198	180◄─►209	gemma-2-9b-it	1262	±8	6,879	Google	Gemma license
199	174◄─►213	reka-flash-20240904	1261	±18	992	Reka AI	Proprietary
200	177◄─►212	command-r-08-2024	1259	±15	1,421	Cohere	CC-BY-NC-4.0
201	177◄─►213	jamba-1.5-large	1258	±17	1,024	AI21 Labs	Jamba Open
202	182◄─►211	command-r-plus	1258	±9	9,149	Cohere	CC-BY-NC-4.0
203	182◄─►211	qwen2-72b-instruct	1257	±10	4,614	Alibaba	Qianwen LICENSE
204	176◄─►216	ministral-8b-2410	1256	±20	720	Mistral	MRL
205	191◄─►213	llama-3-70b-instruct	1249	±8	17,502	Meta	Llama 3 Community
206	190◄─►218	c4ai-aya-expanse-8b	1246	±15	1,485	Cohere	CC-BY-NC-4.0
207	191◄─►216	amazon-nova-micro-v1.0	1246	±11	2,623	Amazon	Proprietary
208	195◄─►216	mistral-large-2402	1242	±10	6,217	Mistral	Proprietary
209	177◄─►233	olmo-2-0325-32b-instruct	1241	±34	262	Allen AI	Apache-2.0
210	201◄─►225	qwen1.5-72b-chat	1232	±12	3,483	Alibaba	Qianwen LICENSE
211	205◄─►225	command-r	1228	±10	6,161	Cohere	CC-BY-NC-4.0
212	192◄─►236	granite-3.1-8b-instruct	1228	±27	462	IBM	Apache 2.0
213	205◄─►228	qwen1.5-110b-chat	1224	±12	3,345	Alibaba	Qianwen LICENSE
214	195◄─►237	llama-3.1-tulu-3-8b	1223	±26	453	Ai2	Llama 3.1
215	205◄─►234	gemini-pro-dev-api	1221	±18	1,351	Google	Proprietary
216	209◄─►228	llama-3.1-8b-instruct	1221	±8	6,735	Meta	Llama 3.1 Community
217	198◄─►238	granite-3.1-2b-instruct	1220	±26	491	IBM	Apache 2.0
218	208◄─►232	qwen1.5-32b-chat	1219	±13	2,574	Alibaba	Qianwen LICENSE
219	209◄─►232	gpt-3.5-turbo-0125	1216	±9	6,708	OpenAI	Proprietary
220	209◄─►235	mistral-medium	1215	±13	2,718	Mistral	Proprietary
221	208◄─►237	jamba-1.5-mini	1215	±18	1,023	AI21 Labs	Jamba Open
222	209◄─►233	mixtral-8x22b-instruct-v0.1	1214	±10	5,865	Mistral	Apache 2.0
223	209◄─►236	reka-flash-21b-20240226	1213	±13	2,720	Reka AI	Proprietary
224	209◄─►237	reka-flash-21b-20240226-online	1213	±16	1,651	Reka AI	Proprietary
225	213◄─►238	llama-3-8b-instruct	1204	±9	11,162	Meta	Llama 3 Community
226	211◄─►241	yi-1.5-34b-chat	1200	±13	2,098	01 AI	Apache-2.0
227	209◄─►247	granite-3.0-8b-instruct	1198	±24	605	IBM	Apache 2.0
228	211◄─►245	internlm2_5-20b-chat	1197	±16	1,266	InternLM	Other
229	218◄─►248	qwen1.5-14b-chat	1188	±15	2,102	Alibaba	Qianwen LICENSE
230	221◄─►248	phi-3-medium-4k-instruct	1186	±13	2,150	Microsoft	MIT
231	226◄─►246	gemma-2-2b-it	1184	±9	5,866	Google	Gemma license
232	224◄─►249	dbrx-instruct-preview	1184	±13	3,489	Databricks	DBRX LICENSE
233	219◄─►254	gpt-3.5-turbo-1106	1182	±21	933	OpenAI	Proprietary
234	211◄─►261	deepseek-llm-67b-chat	1179	±37	243	DeepSeek	DeepSeek License
235	213◄─►257	zephyr-orpo-141b-A35b-v0.1	1179	±28	448	HuggingFace	Apache 2.0
236	215◄─►257	openchat-3.5	1178	±29	414	OpenChat	Apache-2.0
237	226◄─►251	mixtral-8x7b-instruct-v0.1	1178	±10	6,574	Mistral	Apache 2.0
238	213◄─►261	wizardlm-70b	1177	±32	355	Microsoft	Llama 2 Community
239	217◄─►257	qwq-32b-preview	1177	±26	474	Alibaba	Apache 2.0
240	213◄─►261	tulu-2-dpo-70b	1173	±34	280	AllenAI/UW	AI2 ImpACT Low-risk
241	227◄─►258	yi-34b-chat	1167	±18	1,106	01 AI	Yi License
242	227◄─►259	openchat-3.5-0106	1165	±19	1,097	OpenChat	Apache-2.0
243	228◄─►257	gemma-1.1-7b-it	1162	±13	2,649	Google	Gemma license
244	228◄─►260	starling-lm-7b-beta	1162	±16	1,676	Nexusflow	Apache-2.0
245	226◄─►265	qwen1.5-7b-chat	1160	±30	372	Alibaba	Qianwen LICENSE
246	233◄─►261	phi-3-small-8k-instruct	1158	±13	2,238	Microsoft	MIT
247	230◄─►262	llama-3.2-3b-instruct	1155	±18	1,046	Meta	Llama 3.2
248	233◄─►266	starling-lm-7b-alpha	1146	±23	666	UC Berkeley	CC-BY-NC-4.0
249	227◄─►271	wizardlm-13b	1145	±41	203	Microsoft	Llama 2 Community
250	234◄─►269	granite-3.0-2b-instruct	1143	±25	646	IBM	Apache 2.0
251	234◄─►269	vicuna-13b	1140	±22	756	LMSYS	Llama 2 Community
252	227◄─►274	vicuna-7b	1138	±45	162	LMSYS	Llama 2 Community
253	235◄─►269	llama-2-13b-chat	1136	±18	1,193	Meta	Llama 2 Community
254	232◄─►273	palm-2	1135	±38	251	Google	Proprietary
255	234◄─►271	openhermes-2.5-mistral-7b	1135	±34	270	NousResearch	Apache-2.0
256	241◄─►267	llama-2-70b-chat	1134	±13	2,813	Meta	Llama 2 Community
257	242◄─►270	mistral-7b-instruct-v0.2	1130	±15	1,591	Mistral	Apache-2.0
258	239◄─►271	vicuna-33b	1130	±19	1,047	LMSYS	Non-commercial
259	235◄─►274	smollm2-1.7b-instruct	1127	±33	329	HuggingFace	Apache 2.0
260	246◄─►271	snowflake-arctic-instruct	1124	±14	2,794	Snowflake	Apache 2.0
261	235◄─►276	qwen-14b-chat	1122	±39	214	Alibaba	Qianwen LICENSE
262	247◄─►274	gemma-1.1-2b-it	1113	±18	1,179	Google	Gemma license
263	240◄─►277	nous-hermes-2-mixtral-8x7b-dpo	1111	±36	230	NousResearch	Apache-2.0
264	247◄─►275	gemma-7b-it	1108	±23	676	Google	Gemma license
265	250◄─►275	phi-3-mini-4k-instruct	1104	±15	1,706	Microsoft	MIT
266	249◄─►276	phi-3-mini-4k-instruct-june-2024	1102	±19	1,035	Microsoft	MIT
267	247◄─►277	zephyr-7b-beta	1102	±28	461	HuggingFace	MIT
268	253◄─►276	llama-3.2-1b-instruct	1098	±19	1,057	Meta	Llama 3.2
269	248◄─►277	codellama-34b-instruct	1094	±33	320	Meta	Llama 2 Community
270	250◄─►277	mistral-7b-instruct	1093	±27	448	Mistral	Apache 2.0
271	254◄─►277	gemma-2b-it	1080	±31	377	Google	Gemma license
272	258◄─►277	qwen1.5-4b-chat	1073	±24	692	Alibaba	Qianwen LICENSE
273	262◄─►277	llama-2-7b-chat	1072	±20	835	Meta	Llama 2 Community
274	258◄─►277	stripedhyena-nous-7b	1068	±33	334	Together AI	Apache 2.0
275	264◄─►277	phi-3-mini-128k-instruct	1068	±16	2,074	Microsoft	MIT
276	259◄─►277	llama2-70b-steerlm-chat	1053	±44	208	Nvidia	Llama 2 Community
277	267◄─►277	chatglm3-6b	1038	±41	205	Tsinghua	Apache-2.0

Text Arena

Default 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)