Text Arena

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

Last Updated

Feb 6, 2026

Total Votes

5,227,467

Total Models

302

/

Style Control

	Rank Spread
1	1◄─►2	claude-opus-4-6	1496	±11	2,829	Anthropic	Proprietary
2	1◄─►2	gemini-3-pro	1486	±4	34,419	Google	Proprietary
3	3◄─►6	grok-4.1-thinking	1475	±4	34,455	xAI	Proprietary
4	3◄─►8	gemini-3-flash	1470	±5	25,085	Google	Proprietary
5	3◄─►8	claude-opus-4-5-20251101-thinking-32k	1468	±5	26,178	Anthropic	Proprietary
6	3◄─►8	claude-opus-4-5-20251101	1467	±5	31,069	Anthropic	Proprietary
7	4◄─►9	grok-4.1	1465	±4	38,605	xAI	Proprietary
8	4◄─►10	gemini-3-flash (thinking-minimal)	1463	±6	16,255	Google	Proprietary
9	7◄─►14	gpt-5.1-high	1458	±5	30,500	OpenAI	Proprietary
10	8◄─►19	ernie-5.0-0110	1452	±7	10,184	Baidu	Proprietary
11	9◄─►19	claude-sonnet-4-5-20250929	1450	±4	42,437	Anthropic	Proprietary
12	9◄─►19	claude-sonnet-4-5-20250929-thinking-32k	1450	±4	44,799	Anthropic	Proprietary
13	10◄─►19	gemini-2.5-pro	1450	±3	93,835	Google	Proprietary
14	9◄─►23	ernie-5.0-preview-1203	1449	±7	9,775	Baidu	Proprietary
15	9◄─►24	kimi-k2.5-thinking	1449	±7	7,085	Moonshot	Modified MIT
16	10◄─►19	claude-opus-4-1-20250805-thinking-16k	1449	±4	49,956	Anthropic	Proprietary
17	10◄─►23	claude-opus-4-1-20250805	1445	±3	73,888	Anthropic	Proprietary
18	10◄─►26	gpt-4.5-preview-2025-02-27	1444	±6	14,549	OpenAI	Proprietary
19	15◄─►24	chatgpt-4o-latest-20250326	1442	±3	81,283	OpenAI	Proprietary
20	10◄─►28	glm-4.7	1441	±6	12,021	Z.ai	MIT
21	15◄─►29	gpt-5.2-high	1438	±6	15,062	OpenAI	Proprietary
22	17◄─►28	gpt-5.1	1437	±4	32,684	OpenAI	Proprietary
23	15◄─►30	gpt-5.2	1437	±6	11,695	OpenAI	Proprietary
24	19◄─►31	gpt-5-high	1434	±5	32,626	OpenAI	Proprietary
25	19◄─►34	qwen3-max-preview	1434	±5	27,843	Alibaba	Proprietary
26	15◄─►46	kimi-k2.5-instant	1433	±11	2,752	Moonshot	Modified MIT
27	20◄─►34	o3-2025-04-16	1433	±4	61,361	OpenAI	Proprietary
28	20◄─►37	grok-4-1-fast-reasoning	1430	±5	27,088	xAI	Proprietary
29	22◄─►44	kimi-k2-thinking-turbo	1428	±4	32,101	Moonshot	Modified MIT
30	24◄─►46	gpt-5-chat	1426	±4	31,831	OpenAI	Proprietary
31	27◄─►48	glm-4.6	1425	±4	35,339	Z.ai	MIT
32	23◄─►49	qwen3-max-2025-09-23	1425	±6	9,221	Alibaba	Proprietary
33	27◄─►48	claude-opus-4-20250514-thinking-16k	1424	±4	37,974	Anthropic	Proprietary
34	25◄─►51	deepseek-v3.2-exp	1423	±6	11,767	DeepSeek	MIT
35	25◄─►51	deepseek-v3.2-exp-thinking	1423	±7	9,002	DeepSeek	MIT
36	28◄─►48	qwen3-235b-a22b-instruct-2507	1422	±3	68,201	Alibaba	Apache 2.0
37	25◄─►54	grok-4-fast-chat	1422	±8	6,989	xAI	Proprietary
38	28◄─►51	deepseek-v3.2-thinking	1420	±5	21,792	DeepSeek	MIT
39	28◄─►53	deepseek-v3.2	1419	±5	26,704	DeepSeek	MIT
40	28◄─►56	deepseek-r1-0528	1418	±6	19,290	DeepSeek	MIT
41	27◄─►56	ernie-5.0-preview-1022	1418	±9	4,619	Baidu	Proprietary
42	29◄─►56	deepseek-v3.1	1418	±6	15,299	DeepSeek	MIT
43	28◄─►56	kimi-k2-0905-preview	1418	±6	11,974	Moonshot	Modified MIT
44	29◄─►56	deepseek-v3.1-thinking	1417	±7	11,983	DeepSeek	MIT
45	31◄─►56	kimi-k2-0711-preview	1417	±5	28,662	Moonshot	Modified MIT
46	28◄─►59	deepseek-v3.1-terminus	1416	±10	3,761	DeepSeek	MIT
47	28◄─►62	deepseek-v3.1-terminus-thinking	1416	±10	3,549	DeepSeek	MIT
48	31◄─►58	qwen3-vl-235b-a22b-instruct	1415	±6	11,683	Alibaba	Apache 2.0
49	34◄─►56	mistral-large-3	1414	±5	23,001	Mistral	Apache 2.0
50	35◄─►56	claude-opus-4-20250514	1414	±4	45,579	Anthropic	Proprietary
51	35◄─►56	gpt-4.1-2025-04-14	1413	±4	52,220	OpenAI	Proprietary
52	38◄─►58	mistral-medium-2508	1411	±3	62,020	Mistral	Proprietary
53	38◄─►59	grok-3-preview-02-24	1411	±4	33,974	xAI	Proprietary
54	40◄─►59	gemini-2.5-flash	1410	±3	93,104	Google	Proprietary
55	39◄─►64	glm-4.5	1410	±5	24,794	Z.ai	MIT
56	40◄─►62	grok-4-0709	1410	±4	42,162	xAI	Proprietary
57	49◄─►69	gemini-2.5-flash-preview-09-2025	1405	±4	32,880	Google	Proprietary
58	51◄─►69	claude-haiku-4-5-20251001	1404	±4	43,455	Anthropic	Proprietary
59	49◄─►70	grok-4-fast-reasoning	1404	±5	18,640	xAI	Proprietary
60	54◄─►71	o1-2024-12-17	1402	±4	27,822	OpenAI	Proprietary
61	54◄─►71	qwen3-235b-a22b-no-thinking	1401	±4	39,549	Alibaba	Apache 2.0
62	54◄─►72	qwen3-next-80b-a3b-instruct	1401	±5	22,856	Alibaba	Apache 2.0
63	57◄─►72	claude-sonnet-4-20250514-thinking-32k	1400	±4	36,209	Anthropic	Proprietary
64	56◄─►78	longcat-flash-chat	1399	±6	11,546	Meituan	MIT
65	57◄─►78	qwen3-235b-a22b-thinking-2507	1398	±6	9,252	Alibaba	Apache 2.0
66	57◄─►78	deepseek-r1	1398	±5	18,537	DeepSeek	MIT
67	57◄─►84	qwen3-vl-235b-a22b-thinking	1395	±7	7,970	Alibaba	Apache 2.0
68	59◄─►80	mimo-v2-flash (non-thinking)	1395	±5	15,575	Xiaomi	MIT
69	57◄─►85	amazon-nova-experimental-chat-12-10	1394	±10	3,717	Amazon	Proprietary
70	60◄─►80	deepseek-v3-0324	1394	±4	46,691	DeepSeek	MIT
71	56◄─►86	hunyuan-vision-1.5-thinking	1393	±12	2,225	Tencent	Proprietary
72	62◄─►85	mai-1-preview	1391	±5	18,137	Microsoft AI	Proprietary
73	64◄─►84	o4-mini-2025-04-16	1391	±4	46,676	OpenAI	Proprietary
74	64◄─►85	gpt-5-mini-high	1390	±5	27,148	OpenAI	Proprietary
75	64◄─►85	claude-sonnet-4-20250514	1390	±4	41,644	Anthropic	Proprietary
76	64◄─►85	claude-3-7-sonnet-20250219-thinking-32k	1389	±4	39,891	Anthropic	Proprietary
77	64◄─►85	o1-preview	1388	±5	31,120	OpenAI	Proprietary
78	64◄─►88	hunyuan-t1-20250711	1387	±9	4,802	Tencent	Proprietary
79	67◄─►86	qwen3-coder-480b-a35b-instruct	1387	±5	26,653	Alibaba	Apache 2.0
80	67◄─►87	minimax-m2.1-preview	1385	±6	15,063	MiniMax	MIT
81	69◄─►86	mistral-medium-2505	1385	±5	34,551	Mistral	Proprietary
82	69◄─►88	qwen3-30b-a3b-instruct-2507	1383	±5	24,095	Alibaba	Apache 2.0
83	69◄─►89	hunyuan-turbos-20250416	1383	±6	11,053	Tencent	Proprietary
84	71◄─►89	gpt-4.1-mini-2025-04-14	1382	±4	40,530	OpenAI	Proprietary
85	77◄─►89	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1380	±4	46,388	Google	Proprietary
86	69◄─►99	glm-4.6v	1378	±11	2,819	Z.ai	MIT
87	81◄─►95	gemini-2.5-flash-lite-preview-06-17-thinking	1375	±4	33,936	Google	Proprietary
88	80◄─►95	qwen3-235b-a22b	1375	±5	27,166	Alibaba	Apache 2.0
89	83◄─►95	qwen2.5-max	1374	±4	33,294	Alibaba	Proprietary
90	86◄─►95	claude-3-5-sonnet-20241022	1373	±3	89,471	Anthropic	Proprietary
91	86◄─►97	claude-3-7-sonnet-20250219	1372	±4	44,437	Anthropic	Proprietary
92	86◄─►99	glm-4.5-air	1371	±4	31,386	Z.ai	MIT
93	86◄─►102	qwen3-next-80b-a3b-thinking	1369	±6	13,857	Alibaba	Apache 2.0
94	86◄─►102	minimax-m1	1367	±4	36,841	MiniMax	Apache 2.0
95	86◄─►104	amazon-nova-experimental-chat-11-10	1367	±6	15,442	Amazon	Proprietary
96	90◄─►103	gemma-3-27b-it	1365	±4	48,696	Google	Gemma
97	90◄─►107	o3-mini-high	1364	±5	18,584	OpenAI	Proprietary
98	91◄─►110	grok-3-mini-high	1363	±5	17,525	xAI	Proprietary
99	93◄─►110	gemini-2.0-flash-001	1361	±4	44,827	Google	Proprietary
100	91◄─►118	glm-4.7-flash	1360	±8	6,255	Z.ai	MIT
101	93◄─►116	deepseek-v3	1359	±5	21,788	DeepSeek	DeepSeek
102	95◄─►120	grok-3-mini-beta	1357	±5	23,767	xAI	Proprietary
103	97◄─►122	mistral-small-2506	1356	±5	18,341	Mistral	Apache 2.0
104	93◄─►124	intellect-3	1356	±8	5,326	Prime Intellect	MIT
105	98◄─►123	gpt-oss-120b	1354	±4	30,971	OpenAI	Apache 2.0
106	98◄─►124	gemini-2.0-flash-lite-preview-02-05	1353	±4	24,951	Google	Proprietary
107	96◄─►125	glm-4.5v	1353	±8	4,974	Z.ai	MIT
108	100◄─►124	command-a-03-2025	1353	±3	57,445	Cohere	CC-BY-NC-4.0
109	100◄─►124	gemini-1.5-pro-002	1352	±3	55,607	Google	Proprietary
110	97◄─►136	hunyuan-turbos-20250226	1349	±12	2,226	Tencent	Proprietary
111	100◄─►128	amazon-nova-experimental-chat-10-20	1349	±6	11,442	Amazon	Proprietary
112	102◄─►125	o3-mini	1348	±3	58,642	OpenAI	Proprietary
113	98◄─►136	amazon-nova-experimental-chat-10-09	1347	±11	2,889	Amazon	Proprietary
114	97◄─►137	llama-3.1-nemotron-ultra-253b-v1	1347	±12	2,546	Nvidia	Nvidia Open Model
115	100◄─►136	qwen3-32b	1347	±9	3,932	Alibaba	Apache 2.0
116	100◄─►134	minimax-m2	1347	±8	6,746	MiniMax	Apache 2.0
117	101◄─►132	ling-flash-2.0	1347	±7	7,040	Ant Group	MIT
118	101◄─►134	step-3	1346	±7	6,592	StepFun	Apache 2.0
119	100◄─►135	qwen-plus-0125	1346	±8	5,823	Alibaba	Proprietary
120	105◄─►127	gpt-4o-2024-05-13	1346	±3	112,863	OpenAI	Proprietary
121	103◄─►137	glm-4-plus-0111	1343	±8	5,760	Zhipu	Proprietary
122	109◄─►131	claude-3-5-sonnet-20240620	1343	±3	82,417	Anthropic	Proprietary
123	103◄─►141	gemma-3-12b-it	1342	±10	3,829	Google	Gemma
124	103◄─►142	nvidia-llama-3.3-nemotron-super-49b-v1.5	1341	±10	3,432	Nvidia	Nvidia Open
125	102◄─►143	hunyuan-turbo-0110	1341	±12	2,295	Tencent	Proprietary
126	111◄─►142	gpt-5-nano-high	1338	±7	8,399	OpenAI	Proprietary
127	113◄─►138	o1-mini	1337	±4	51,986	OpenAI	Proprietary
128	111◄─►142	nova-2-lite	1337	±6	12,264	Amazon	Proprietary
129	113◄─►142	qwq-32b	1336	±4	26,118	Alibaba	Apache 2.0
130	114◄─►140	llama-3.1-405b-instruct-bf16	1336	±4	41,392	Meta	Llama 3.1 Community
131	114◄─►142	gpt-4o-2024-08-06	1335	±4	45,498	OpenAI	Proprietary
132	117◄─►142	grok-2-2024-08-13	1335	±4	63,495	xAI	Proprietary
133	113◄─►142	gemini-advanced-0514	1335	±5	50,142	Google	Proprietary
134	112◄─►150	step-2-16k-exp-202412	1334	±9	4,829	StepFun	Proprietary
135	118◄─►142	llama-3.1-405b-instruct-fp8	1334	±4	59,655	Meta	Llama 3.1 Community
136	123◄─►155	yi-lightning	1329	±5	27,340	01 AI	Proprietary
137	124◄─►155	qwen3-30b-a3b	1328	±5	27,435	Alibaba	Apache 2.0
138	124◄─►155	llama-4-maverick-17b-128e-instruct	1328	±4	41,137	Meta	Llama 4
139	115◄─►164	llama-3.3-nemotron-49b-super-v1	1327	±12	2,230	Nvidia	Nvidia
140	121◄─►164	hunyuan-large-2025-02-10	1327	±10	3,738	Tencent	Proprietary
141	124◄─►160	olmo-3.1-32b-instruct	1327	±7	10,567	Allen AI	Apache 2.0
142	135◄─►160	gpt-4-turbo-2024-04-09	1325	±4	98,130	OpenAI	Proprietary
143	135◄─►160	claude-3-5-haiku-20241022	1324	±3	71,181	Anthropic	Proprietary
144	126◄─►164	deepseek-v2.5-1210	1323	±8	6,793	DeepSeek	DeepSeek
145	135◄─►160	gemini-1.5-pro-001	1323	±4	79,132	Google	Proprietary
146	135◄─►162	llama-4-scout-17b-16e-instruct	1323	±5	31,236	Meta	Llama
147	135◄─►160	claude-3-opus-20240229	1323	±3	194,904	Anthropic	Proprietary
148	134◄─►165	gpt-4.1-nano-2025-04-14	1322	±8	6,107	OpenAI	Proprietary
149	135◄─►164	step-1o-turbo-202506	1321	±7	9,689	StepFun	Proprietary
150	135◄─►166	ring-flash-2.0	1320	±7	7,205	Ant Group	MIT
151	139◄─►164	llama-3.3-70b-instruct	1320	±3	55,575	Meta	Llama-3.3
152	136◄─►164	glm-4-plus	1319	±5	26,134	Zhipu AI	Proprietary
153	136◄─►165	gemma-3n-e4b-it	1319	±5	23,342	Google	Gemma
154	136◄─►166	qwen-max-0919	1318	±6	16,479	Alibaba	Qwen
155	139◄─►164	gpt-4o-mini-2024-07-18	1318	±3	68,801	OpenAI	Proprietary
156	136◄─►171	gpt-oss-20b	1318	±6	10,810	OpenAI	Apache 2.0
157	139◄─►171	nvidia-nemotron-3-nano-30b-a3b-bf16	1317	±6	15,505	Nvidia	NVIDIA Open Model
158	139◄─►173	qwen2.5-plus-1127	1315	±6	10,179	Alibaba	Proprietary
159	144◄─►171	athene-v2-chat	1315	±4	24,746	NexusFlow	NexusFlow
160	144◄─►171	mistral-large-2407	1314	±4	45,460	Mistral	Mistral Research
161	145◄─►172	gpt-4-0125-preview	1314	±4	93,439	OpenAI	Proprietary
162	145◄─►171	gpt-4-1106-preview	1314	±4	100,107	OpenAI	Proprietary
163	139◄─►176	hunyuan-standard-2025-02-10	1312	±10	3,905	Tencent	Proprietary
164	136◄─►180	mercury	1310	±14	1,920	Inception AI	Proprietary
165	152◄─►175	gemini-1.5-flash-002	1310	±4	34,909	Google	Proprietary
166	156◄─►176	grok-2-mini-2024-08-13	1308	±4	52,574	xAI	Proprietary
167	156◄─►176	deepseek-v2.5	1307	±5	24,574	DeepSeek	DeepSeek
168	156◄─►176	athene-70b-0725	1306	±6	19,622	NexusFlow	CC-BY-NC-4.0
169	154◄─►178	olmo-3-32b-think	1305	±8	5,891	Allen AI	Apache 2.0
170	161◄─►176	mistral-large-2411	1305	±4	28,081	Mistral	MRL
171	156◄─►176	magistral-medium-2506	1305	±6	12,064	Mistral	Proprietary
172	162◄─►176	mistral-small-3.1-24b-instruct-2503	1305	±4	34,131	Mistral	Apache 2.0
173	156◄─►183	gemma-3-4b-it	1303	±9	4,177	Google	Gemma
174	163◄─►176	qwen2.5-72b-instruct	1303	±4	39,409	Alibaba	Qwen
175	163◄─►186	llama-3.1-nemotron-70b-instruct	1299	±8	7,136	Nvidia	Llama 3.1
176	164◄─►187	hunyuan-large-vision	1296	±9	5,600	Tencent	Proprietary
177	172◄─►187	llama-3.1-70b-instruct	1294	±4	55,234	Meta	Llama 3.1 Community
178	174◄─►188	amazon-nova-pro-v1.0	1290	±5	24,753	Amazon	Proprietary
179	174◄─►191	jamba-1.5-large	1289	±7	8,659	AI21 Labs	Jamba Open
180	173◄─►193	ibm-granite-h-small	1288	±8	5,682	IBM	Apache 2.0
181	175◄─►189	gemma-2-27b-it	1288	±3	75,764	Google	Gemma license
182	174◄─►191	reka-core-20240904	1288	±7	7,309	Reka AI	Proprietary
183	175◄─►191	gpt-4-0314	1288	±5	54,167	OpenAI	Proprietary
184	172◄─►197	llama-3.1-tulu-3-70b	1287	±10	2,846	Ai2	Llama 3.1
185	173◄─►197	llama-3.1-nemotron-51b-instruct	1287	±10	3,749	Nvidia	Llama 3.1
186	176◄─►191	gemini-1.5-flash-001	1286	±4	62,823	Google	Proprietary
187	175◄─►197	olmo-3.1-32b-think	1286	±7	8,486	Allen AI	Apache 2.0
188	179◄─►197	claude-3-sonnet-20240229	1282	±4	109,289	Anthropic	Proprietary
189	178◄─►197	gemma-2-9b-it-simpo	1280	±7	10,069	Princeton	MIT
190	180◄─►197	nemotron-4-340b-instruct	1278	±5	19,661	Nvidia	NVIDIA Open Model
191	180◄─►199	command-r-plus-08-2024	1277	±7	9,869	Cohere	CC-BY-NC-4.0
192	184◄─►197	llama-3-70b-instruct	1276	±4	156,880	Meta	Llama 3 Community
193	185◄─►198	gpt-4-0613	1276	±4	88,721	OpenAI	Proprietary
194	185◄─►200	mistral-small-24b-instruct-2501	1274	±6	14,677	Mistral	Apache 2.0
195	184◄─►202	glm-4-0520	1274	±7	9,788	Zhipu AI	Proprietary
196	185◄─►203	reka-flash-20240904	1273	±7	7,537	Reka AI	Proprietary
197	185◄─►206	qwen2.5-coder-32b-instruct	1271	±8	5,430	Alibaba	Apache 2.0
198	192◄─►206	c4ai-aya-expanse-32b	1267	±5	27,123	Cohere	CC-BY-NC-4.0
199	194◄─►206	gemma-2-9b-it	1266	±4	54,615	Google	Gemma license
200	193◄─►207	deepseek-coder-v2	1265	±6	15,147	DeepSeek	DeepSeek License
201	195◄─►207	command-r-plus	1263	±4	77,556	Cohere	CC-BY-NC-4.0
202	195◄─►207	qwen2-72b-instruct	1262	±5	37,325	Alibaba	Qianwen LICENSE
203	197◄─►207	claude-3-haiku-20240307	1262	±4	117,705	Anthropic	Proprietary
204	196◄─►208	amazon-nova-lite-v1.0	1261	±5	19,376	Amazon	Proprietary
205	197◄─►208	gemini-1.5-flash-8b-001	1259	±4	35,556	Google	Proprietary
206	200◄─►208	phi-4	1256	±5	24,126	Microsoft	MIT
207	197◄─►214	olmo-2-0325-32b-instruct	1252	±11	3,335	Allen AI	Apache-2.0
208	204◄─►213	command-r-08-2024	1251	±7	10,141	Cohere	CC-BY-NC-4.0
209	207◄─►217	mistral-large-2402	1243	±5	62,437	Mistral	Proprietary
210	207◄─►217	amazon-nova-micro-v1.0	1241	±5	19,355	Amazon	Proprietary
211	207◄─►221	jamba-1.5-mini	1239	±7	8,854	AI21 Labs	Jamba Open
212	207◄─►225	ministral-8b-2410	1237	±9	4,780	Mistral	MRL
213	208◄─►225	gemini-pro-dev-api	1236	±7	18,352	Google	Proprietary
214	209◄─►225	qwen1.5-110b-chat	1235	±6	26,191	Alibaba	Qianwen LICENSE
215	209◄─►226	reka-flash-21b-20240226-online	1234	±7	15,451	Reka AI	Proprietary
216	209◄─►225	qwen1.5-72b-chat	1234	±5	39,296	Alibaba	Qianwen LICENSE
217	207◄─►227	hunyuan-standard-256k	1234	±12	2,729	Tencent	Proprietary
218	211◄─►226	mixtral-8x22b-instruct-v0.1	1230	±5	51,417	Mistral	Apache 2.0
219	211◄─►227	command-r	1228	±5	54,038	Cohere	CC-BY-NC-4.0
220	211◄─►227	reka-flash-21b-20240226	1227	±6	24,806	Reka AI	Proprietary
221	212◄─►228	gpt-3.5-turbo-0125	1225	±5	66,191	OpenAI	Proprietary
222	212◄─►229	mistral-medium	1224	±5	34,552	Mistral	Proprietary
223	216◄─►228	llama-3-8b-instruct	1224	±4	104,636	Meta	Llama 3 Community
224	212◄─►229	c4ai-aya-expanse-8b	1223	±7	9,827	Cohere	CC-BY-NC-4.0
225	211◄─►232	gemini-pro	1222	±12	6,390	Google	Proprietary
226	212◄─►232	llama-3.1-tulu-3-8b	1221	±11	2,895	Ai2	Llama 3.1
227	223◄─►232	yi-1.5-34b-chat	1214	±5	24,142	01 AI	Apache-2.0
228	218◄─►234	zephyr-orpo-141b-A35b-v0.1	1213	±11	4,653	HuggingFace	Apache 2.0
229	225◄─►232	llama-3.1-8b-instruct	1212	±4	49,605	Meta	Llama 3.1 Community
230	221◄─►238	granite-3.1-8b-instruct	1209	±11	3,092	IBM	Apache 2.0
231	225◄─►238	qwen1.5-32b-chat	1205	±6	21,744	Alibaba	Qianwen LICENSE
232	225◄─►240	gpt-3.5-turbo-1106	1203	±9	16,616	OpenAI	Proprietary
233	229◄─►239	gemma-2-2b-it	1199	±4	46,618	Google	Gemma license
234	229◄─►240	phi-3-medium-4k-instruct	1199	±5	25,055	Microsoft	MIT
235	230◄─►240	mixtral-8x7b-instruct-v0.1	1198	±4	73,505	Mistral	Apache 2.0
236	230◄─►245	dbrx-instruct-preview	1196	±6	32,196	Databricks	DBRX LICENSE
237	230◄─►249	internlm2_5-20b-chat	1192	±7	9,902	InternLM	Other
238	230◄─►249	qwen1.5-14b-chat	1191	±7	17,841	Alibaba	Qianwen LICENSE
239	233◄─►255	wizardlm-70b	1185	±9	8,214	Microsoft	Llama 2 Community
240	232◄─►256	deepseek-llm-67b-chat	1185	±12	4,933	DeepSeek	DeepSeek License
241	236◄─►252	yi-34b-chat	1184	±7	15,483	01 AI	Yi License
242	236◄─►255	openchat-3.5-0106	1183	±8	12,636	OpenChat	Apache-2.0
243	236◄─►256	openchat-3.5	1183	±10	7,967	OpenChat	Apache-2.0
244	236◄─►256	granite-3.0-8b-instruct	1183	±9	6,643	IBM	Apache 2.0
245	237◄─►256	gemma-1.1-7b-it	1181	±6	23,893	Google	Gemma license
246	237◄─►256	snowflake-arctic-instruct	1180	±6	32,836	Snowflake	Apache 2.0
247	236◄─►258	granite-3.1-2b-instruct	1180	±11	3,191	IBM	Apache 2.0
248	237◄─►256	tulu-2-dpo-70b	1179	±10	6,534	AllenAI/UW	AI2 ImpACT Low-risk
249	237◄─►260	openhermes-2.5-mistral-7b	1176	±10	5,006	NousResearch	Apache-2.0
250	239◄─►259	vicuna-33b	1173	±6	22,479	LMSYS	Non-commercial
251	239◄─►262	starling-lm-7b-beta	1172	±7	16,057	Nexusflow	Apache-2.0
252	239◄─►260	phi-3-small-8k-instruct	1172	±6	17,763	Microsoft	MIT
253	240◄─►260	llama-2-70b-chat	1171	±5	38,491	Meta	Llama 2 Community
254	240◄─►263	starling-lm-7b-alpha	1168	±8	10,224	UC Berkeley	CC-BY-NC-4.0
255	242◄─►263	llama-3.2-3b-instruct	1167	±8	7,936	Meta	Llama 3.2
256	240◄─►266	nous-hermes-2-mixtral-8x7b-dpo	1165	±12	3,776	NousResearch	Apache-2.0
257	248◄─►273	qwq-32b-preview	1157	±12	3,233	Alibaba	Apache 2.0
258	253◄─►270	granite-3.0-2b-instruct	1157	±8	6,837	IBM	Apache 2.0
259	248◄─►273	llama2-70b-steerlm-chat	1156	±13	3,584	Nvidia	Llama 2 Community
260	250◄─►276	solar-10.7b-instruct-v1.0	1153	±13	4,155	Upstage AI	CC-BY-NC-4.0
261	249◄─►278	dolphin-2.2.1-mistral-7b	1153	±15	1,679	Cognitive Computations	Apache-2.0
262	254◄─►276	mpt-30b-chat	1151	±12	2,571	MosaicML	CC-BY-NC-SA-4.0
263	256◄─►273	mistral-7b-instruct-v0.2	1150	±7	19,402	Mistral	Apache-2.0
264	256◄─►275	wizardlm-13b	1150	±9	7,046	Microsoft	Llama 2 Community
265	253◄─►280	falcon-180b-chat	1148	±17	1,295	TII	Falcon-180B TII License
266	256◄─►279	qwen1.5-7b-chat	1144	±10	4,735	Alibaba	Qianwen LICENSE
267	257◄─►278	phi-3-mini-4k-instruct-june-2024	1144	±6	12,296	Microsoft	MIT
268	257◄─►279	llama-2-13b-chat	1142	±7	19,171	Meta	Llama 2 Community
269	257◄─►279	vicuna-13b	1142	±7	19,366	LMSYS	Llama 2 Community
270	257◄─►281	qwen-14b-chat	1139	±11	4,964	Alibaba	Qianwen LICENSE
271	258◄─►281	palm-2	1138	±9	8,554	Google	Proprietary
272	258◄─►281	codellama-34b-instruct	1137	±9	7,363	Meta	Llama 2 Community
273	258◄─►281	gemma-7b-it	1136	±10	8,925	Google	Gemma license
274	261◄─►282	zephyr-7b-beta	1132	±9	11,116	HuggingFace	MIT
275	264◄─►282	phi-3-mini-128k-instruct	1130	±7	20,691	Microsoft	MIT
276	266◄─►282	phi-3-mini-4k-instruct	1129	±6	20,115	Microsoft	MIT
277	262◄─►285	guanaco-33b	1128	±12	2,921	UW	Non-commercial
278	261◄─►286	zephyr-7b-alpha	1128	±16	1,785	HuggingFace	MIT
279	269◄─►286	stripedhyena-nous-7b	1122	±11	5,184	Together AI	Apache 2.0
280	264◄─►287	codellama-70b-instruct	1120	±18	1,143	Meta	Llama 2 Community
281	274◄─►286	vicuna-7b	1115	±9	6,923	LMSYS	Llama 2 Community
282	270◄─►287	smollm2-1.7b-instruct	1115	±14	2,201	HuggingFace	Apache 2.0
283	277◄─►286	gemma-1.1-2b-it	1115	±8	10,853	Google	Gemma license
284	277◄─►286	llama-3.2-1b-instruct	1112	±8	8,045	Meta	Llama 3.2
285	277◄─►287	mistral-7b-instruct	1110	±9	8,977	Mistral	Apache 2.0
286	278◄─►287	llama-2-7b-chat	1109	±7	14,148	Meta	Llama 2 Community
287	283◄─►291	gemma-2b-it	1092	±12	4,779	Google	Gemma license
288	287◄─►290	qwen1.5-4b-chat	1091	±9	7,598	Alibaba	Qianwen LICENSE
289	287◄─►294	olmo-7b-instruct	1075	±11	6,329	Allen AI	Apache-2.0
290	288◄─►294	koala-13b	1071	±10	6,964	UC Berkeley	Non-commercial
291	289◄─►294	alpaca-13b	1068	±12	5,745	Stanford	Non-commercial
292	287◄─►295	gpt4all-13b-snoozy	1067	±15	1,743	Nomic AI	Non-commercial
293	289◄─►295	mpt-7b-chat	1063	±12	3,925	MosaicML	CC-BY-NC-SA-4.0
294	289◄─►295	chatglm3-6b	1057	±12	4,658	Tsinghua	Apache-2.0
295	292◄─►297	RWKV-4-Raven-14B	1042	±11	4,845	RWKV	Apache 2.0
296	295◄─►297	chatglm2-6b	1025	±14	2,657	Tsinghua	Apache-2.0
297	295◄─►297	oasst-pythia-12b	1023	±11	6,311	OpenAssistant	Apache 2.0
298	298◄─►301	chatglm-6b	996	±13	4,914	Tsinghua	Non-commercial
299	298◄─►301	fastchat-t5-3b	992	±12	4,203	LMSYS	Apache 2.0
300	298◄─►301	dolly-v2-12b	981	±14	3,412	Databricks	MIT
301	298◄─►302	llama-13b	973	±16	2,391	Meta	Non-commercial
302	301◄─►302	stablelm-tuned-alpha-7b	953	±13	3,287	Stability AI	CC-BY-NC-SA-4.0

Text Arena

Default Leaderboard Plots

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

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)