Text Arena

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

Last Updated

Jan 29, 2026

Total Votes

5,154,557

Total Models

300

/

Style Control

	Rank Spread
1	1◄─►1	gemini-3-pro	1481	±5	32,205	Google	Proprietary
2	2◄─►4	gemini-3-flash	1464	±5	22,683	Google	Proprietary
3	2◄─►4	gemini-2.5-pro	1463	±3	91,734	Google	Proprietary
4	2◄─►11	ernie-5.0-0110	1453	±7	8,274	Baidu	Proprietary
5	4◄─►13	gemini-3-flash (thinking-minimal)	1449	±6	13,989	Google	Proprietary
6	4◄─►13	grok-4.1-thinking	1447	±5	32,194	xAI	Proprietary
7	4◄─►15	kimi-k2.5-thinking	1446	±9	4,901	Moonshot	Modified MIT
8	4◄─►14	gpt-5.1-high	1445	±5	28,296	OpenAI	Proprietary
9	4◄─►15	claude-opus-4-5-20251101	1444	±5	28,752	Anthropic	Proprietary
10	4◄─►15	grok-4.1	1443	±4	36,363	xAI	Proprietary
11	4◄─►17	ernie-5.0-preview-1203	1443	±7	9,786	Baidu	Proprietary
12	5◄─►17	claude-opus-4-5-20251101-thinking-32k	1440	±5	23,990	Anthropic	Proprietary
13	5◄─►17	glm-4.6	1440	±4	35,373	Z.ai	MIT
14	7◄─►18	qwen3-max-preview	1438	±5	27,857	Alibaba	Proprietary
15	8◄─►28	glm-4.7	1434	±6	12,027	Z.ai	MIT
16	11◄─►31	mistral-large-3	1431	±5	20,796	Mistral	Apache 2.0
17	14◄─►31	claude-sonnet-4-5-20250929	1430	±4	40,121	Anthropic	Proprietary
18	15◄─►31	mistral-medium-2508	1430	±3	59,880	Mistral	Proprietary
19	15◄─►31	chatgpt-4o-latest-20250326	1429	±3	78,991	OpenAI	Proprietary
20	15◄─►39	glm-4.5	1428	±5	24,803	Z.ai	MIT
21	11◄─►46	ernie-5.0-preview-1022	1428	±9	4,630	Baidu	Proprietary
22	15◄─►41	claude-sonnet-4-5-20250929-thinking-32k	1426	±4	42,538	Anthropic	Proprietary
23	15◄─►46	deepseek-r1-0528	1425	±6	19,289	DeepSeek	MIT
24	15◄─►44	grok-3-preview-02-24	1424	±4	33,980	xAI	Proprietary
25	15◄─►49	deepseek-v3.2-exp	1423	±6	11,774	DeepSeek	MIT
26	15◄─►49	deepseek-v3.2-exp-thinking	1423	±7	9,000	DeepSeek	MIT
27	15◄─►54	amazon-nova-experimental-chat-12-10	1421	±10	3,722	Amazon	Proprietary
28	16◄─►51	longcat-flash-chat	1421	±6	11,554	Meituan	MIT
29	16◄─►51	qwen3-vl-235b-a22b-instruct	1421	±6	11,684	Alibaba	Apache 2.0
30	20◄─►51	deepseek-v3.2	1420	±5	24,571	DeepSeek	MIT
31	20◄─►52	deepseek-v3.1	1419	±6	15,304	DeepSeek	MIT
32	20◄─►51	gpt-5.1	1419	±5	30,355	OpenAI	Proprietary
33	22◄─►50	qwen3-235b-a22b-instruct-2507	1418	±3	66,045	Alibaba	Apache 2.0
34	22◄─►51	claude-opus-4-1-20250805-thinking-16k	1418	±4	49,975	Anthropic	Proprietary
35	20◄─►54	amazon-nova-experimental-chat-11-10	1418	±6	13,391	Amazon	Proprietary
36	21◄─►51	qwen3-next-80b-a3b-instruct	1418	±5	22,874	Alibaba	Apache 2.0
37	20◄─►54	deepseek-v3.2-thinking	1418	±5	19,713	DeepSeek	MIT
38	16◄─►56	deepseek-v3.1-terminus	1418	±10	3,762	DeepSeek	MIT
39	15◄─►56	deepseek-v3.1-terminus-thinking	1418	±10	3,547	DeepSeek	MIT
40	21◄─►54	gpt-4.5-preview-2025-02-27	1418	±6	14,549	OpenAI	Proprietary
41	20◄─►54	gpt-5.2-high	1417	±7	12,869	OpenAI	Proprietary
42	20◄─►55	gpt-5.2	1417	±7	9,387	OpenAI	Proprietary
43	20◄─►55	deepseek-v3.1-thinking	1417	±7	11,986	DeepSeek	MIT
44	23◄─►51	gemini-2.5-flash	1416	±3	90,980	Google	Proprietary
45	25◄─►54	claude-opus-4-1-20250805	1415	±3	71,681	Anthropic	Proprietary
46	22◄─►57	qwen3-max-2025-09-23	1414	±6	9,223	Alibaba	Proprietary
47	25◄─►56	kimi-k2-thinking-turbo	1413	±4	30,011	Moonshot	Modified MIT
48	23◄─►59	qwen3-235b-a22b-thinking-2507	1413	±6	9,248	Alibaba	Apache 2.0
49	25◄─►60	grok-4-fast-chat	1409	±8	6,992	xAI	Proprietary
50	36◄─►59	o3-2025-04-16	1409	±4	61,365	OpenAI	Proprietary
51	28◄─►59	mimo-v2-flash (non-thinking)	1409	±6	13,410	Xiaomi	MIT
52	36◄─►59	grok-4-0709	1409	±4	42,174	xAI	Proprietary
53	35◄─►59	grok-4-1-fast-reasoning	1409	±5	25,264	xAI	Proprietary
54	42◄─►59	gemini-2.5-flash-preview-09-2025	1407	±4	32,903	Google	Proprietary
55	44◄─►60	gpt-5-high	1405	±4	32,651	OpenAI	Proprietary
56	27◄─►64	hunyuan-vision-1.5-thinking	1404	±12	2,222	Tencent	Proprietary
57	48◄─►61	gpt-5-chat	1403	±4	31,849	OpenAI	Proprietary
58	48◄─►63	qwen3-vl-235b-a22b-thinking	1401	±7	7,974	Alibaba	Apache 2.0
59	47◄─►64	hunyuan-t1-20250711	1399	±9	4,801	Tencent	Proprietary
60	54◄─►64	grok-4-fast-reasoning	1397	±5	18,646	xAI	Proprietary
61	56◄─►65	amazon-nova-experimental-chat-10-20	1394	±6	11,439	Amazon	Proprietary
62	57◄─►65	mai-1-preview	1393	±5	18,137	Microsoft AI	Proprietary
63	57◄─►65	qwen3-235b-a22b-no-thinking	1392	±4	39,554	Alibaba	Apache 2.0
64	58◄─►72	minimax-m2.1-preview	1388	±6	12,907	MiniMax	MIT
65	61◄─►73	qwen3-30b-a3b-instruct-2507	1384	±5	24,093	Alibaba	Apache 2.0
66	64◄─►73	claude-haiku-4-5-20251001	1383	±4	41,166	Anthropic	Proprietary
67	64◄─►73	gpt-4.1-2025-04-14	1382	±4	52,220	OpenAI	Proprietary
68	64◄─►76	glm-4.5-air	1382	±4	31,396	Z.ai	MIT
69	64◄─►81	kimi-k2-0905-preview	1379	±6	11,977	Moonshot	Modified MIT
70	64◄─►78	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1378	±4	44,231	Google	Proprietary
71	64◄─►87	hunyuan-turbos-20250416	1376	±6	11,050	Tencent	Proprietary
72	64◄─►91	glm-4.6v	1375	±11	2,822	Z.ai	MIT
73	65◄─►85	claude-opus-4-20250514-thinking-16k	1375	±4	37,990	Anthropic	Proprietary
74	68◄─►86	deepseek-v3-0324	1374	±4	46,699	DeepSeek	MIT
75	68◄─►89	gpt-5-mini-high	1373	±5	27,174	OpenAI	Proprietary
76	68◄─►89	deepseek-r1	1373	±5	18,537	DeepSeek	MIT
77	69◄─►90	kimi-k2-0711-preview	1371	±5	28,666	Moonshot	Modified MIT
78	70◄─►91	gemini-2.5-flash-lite-preview-06-17-thinking	1368	±4	33,931	Google	Proprietary
79	70◄─►91	mistral-medium-2505	1368	±5	34,547	Mistral	Proprietary
80	70◄─►92	qwen3-next-80b-a3b-thinking	1367	±6	13,871	Alibaba	Apache 2.0
81	71◄─►91	grok-3-mini-high	1367	±5	17,525	xAI	Proprietary
82	71◄─►91	qwen2.5-max	1367	±4	33,288	Alibaba	Proprietary
83	72◄─►91	o1-2024-12-17	1366	±4	27,822	OpenAI	Proprietary
84	71◄─►92	qwen3-235b-a22b	1366	±5	27,156	Alibaba	Apache 2.0
85	72◄─►91	gpt-oss-120b	1366	±4	30,977	OpenAI	Apache 2.0
86	69◄─►99	amazon-nova-experimental-chat-10-09	1365	±11	2,892	Amazon	Proprietary
87	74◄─►92	claude-opus-4-20250514	1365	±4	45,572	Anthropic	Proprietary
88	71◄─►97	ling-flash-2.0	1364	±7	7,044	Ant Group	MIT
89	74◄─►97	nova-2-lite	1363	±6	12,274	Amazon	Proprietary
90	76◄─►97	grok-3-mini-beta	1362	±5	23,763	xAI	Proprietary
91	84◄─►99	gemma-3-27b-it	1358	±4	48,686	Google	Gemma
92	77◄─►103	intellect-3	1356	±8	5,325	Prime Intellect	MIT
93	87◄─►100	qwen3-coder-480b-a35b-instruct	1356	±5	26,648	Alibaba	Apache 2.0
94	87◄─►100	gemini-2.0-flash-001	1354	±4	44,815	Google	Proprietary
95	87◄─►103	o1-preview	1353	±5	31,120	OpenAI	Proprietary
96	87◄─►103	o4-mini-2025-04-16	1353	±4	46,681	OpenAI	Proprietary
97	90◄─►105	nvidia-nemotron-3-nano-30b-a3b-bf16	1350	±6	15,510	Nvidia	NVIDIA Open Model
98	92◄─►104	claude-sonnet-4-20250514-thinking-32k	1349	±4	36,212	Anthropic	Proprietary
99	90◄─►111	step-3	1349	±7	6,595	StepFun	Apache 2.0
100	87◄─►113	glm-4.7-flash	1348	±9	4,090	Z.ai	MIT
101	94◄─►110	minimax-m1	1346	±4	36,843	MiniMax	Apache 2.0
102	94◄─►115	minimax-m2	1342	±8	6,749	MiniMax	Apache 2.0
103	94◄─►120	qwen3-32b	1340	±9	3,932	Alibaba	Apache 2.0
104	98◄─►114	gpt-4.1-mini-2025-04-14	1340	±4	40,533	OpenAI	Proprietary
105	99◄─►115	claude-sonnet-4-20250514	1339	±4	41,643	Anthropic	Proprietary
106	99◄─►118	mistral-small-2506	1339	±5	18,340	Mistral	Apache 2.0
107	99◄─►119	o3-mini-high	1337	±5	18,584	OpenAI	Proprietary
108	99◄─►121	step-1o-turbo-202506	1337	±7	9,687	StepFun	Proprietary
109	97◄─►122	nvidia-llama-3.3-nemotron-super-49b-v1.5	1336	±10	3,430	Nvidia	Nvidia Open
110	99◄─►122	gemma-3-12b-it	1334	±9	3,829	Google	Gemma
111	100◄─►122	glm-4.5v	1334	±8	4,977	Z.ai	MIT
112	102◄─►121	deepseek-v3	1333	±5	21,788	DeepSeek	DeepSeek
113	101◄─►122	ring-flash-2.0	1332	±7	7,199	Ant Group	MIT
114	101◄─►123	glm-4-plus-0111	1332	±8	5,760	Zhipu	Proprietary
115	105◄─►121	command-a-03-2025	1331	±3	57,447	Cohere	CC-BY-NC-4.0
116	105◄─►122	gemini-2.0-flash-lite-preview-02-05	1330	±4	24,951	Google	Proprietary
117	105◄─►122	qwq-32b	1330	±4	26,123	Alibaba	Apache 2.0
118	103◄─►129	qwen-plus-0125	1327	±8	5,823	Alibaba	Proprietary
119	108◄─►129	step-2-16k-exp-202412	1321	±9	4,829	StepFun	Proprietary
120	106◄─►132	hunyuan-turbos-20250226	1320	±12	2,226	Tencent	Proprietary
121	111◄─►129	gpt-5-nano-high	1320	±7	8,402	OpenAI	Proprietary
122	107◄─►132	llama-3.1-nemotron-ultra-253b-v1	1320	±12	2,546	Nvidia	Nvidia Open Model
123	118◄─►129	gemini-1.5-pro-002	1320	±3	55,607	Google	Proprietary
124	118◄─►129	o3-mini	1320	±3	58,645	OpenAI	Proprietary
125	118◄─►129	qwen3-30b-a3b	1318	±5	27,428	Alibaba	Apache 2.0
126	118◄─►129	o1-mini	1318	±4	51,986	OpenAI	Proprietary
127	118◄─►130	claude-3-7-sonnet-20250219-thinking-32k	1316	±4	39,890	Anthropic	Proprietary
128	117◄─►140	hunyuan-turbo-0110	1312	±12	2,295	Tencent	Proprietary
129	118◄─►143	llama-3.3-nemotron-49b-super-v1	1309	±12	2,230	Nvidia	Nvidia
130	125◄─►138	gemma-3n-e4b-it	1307	±5	23,347	Google	Gemma
131	126◄─►138	grok-2-2024-08-13	1305	±4	63,495	xAI	Proprietary
132	126◄─►142	olmo-3.1-32b-instruct	1304	±7	8,310	Allen AI	Apache 2.0
133	128◄─►142	yi-lightning	1302	±5	27,340	01 AI	Proprietary
134	128◄─►142	gpt-4o-2024-05-13	1301	±3	112,863	OpenAI	Proprietary
135	128◄─►143	claude-3-7-sonnet-20250219	1300	±4	44,434	Anthropic	Proprietary
136	128◄─►144	qwen2.5-plus-1127	1300	±6	10,179	Alibaba	Proprietary
137	128◄─►149	olmo-3-32b-think	1299	±8	5,891	Allen AI	Apache 2.0
138	130◄─►143	claude-3-5-sonnet-20241022	1298	±3	89,457	Anthropic	Proprietary
139	128◄─►153	deepseek-v2.5-1210	1294	±8	6,793	DeepSeek	DeepSeek
140	134◄─►152	athene-v2-chat	1292	±4	24,746	NexusFlow	NexusFlow
141	130◄─►160	gemma-3-4b-it	1291	±9	4,177	Google	Gemma
142	137◄─►155	glm-4-plus	1290	±5	26,134	Zhipu AI	Proprietary
143	131◄─►161	hunyuan-large-2025-02-10	1289	±10	3,738	Tencent	Proprietary
144	138◄─►159	llama-4-maverick-17b-128e-instruct	1288	±4	41,136	Meta	Llama 4
145	138◄─►160	gemini-1.5-flash-002	1287	±4	34,909	Google	Proprietary
146	138◄─►160	gpt-oss-20b	1287	±6	10,807	OpenAI	Apache 2.0
147	138◄─►160	gpt-4o-mini-2024-07-18	1287	±3	68,801	OpenAI	Proprietary
148	131◄─►167	mercury	1286	±14	1,921	Inception AI	Proprietary
149	138◄─►163	gpt-4.1-nano-2025-04-14	1285	±8	6,107	OpenAI	Proprietary
150	139◄─►160	llama-3.1-405b-instruct-bf16	1284	±4	41,392	Meta	Llama 3.1 Community
151	138◄─►165	llama-3.1-nemotron-70b-instruct	1283	±8	7,136	Nvidia	Llama 3.1
152	140◄─►161	gpt-4o-2024-08-06	1283	±4	45,498	OpenAI	Proprietary
153	139◄─►163	qwen-max-0919	1282	±6	16,479	Alibaba	Qwen
154	141◄─►161	llama-3.1-405b-instruct-fp8	1282	±4	59,655	Meta	Llama 3.1 Community
155	142◄─►162	claude-3-5-sonnet-20240620	1281	±3	82,417	Anthropic	Proprietary
156	142◄─►163	grok-2-mini-2024-08-13	1281	±4	52,574	xAI	Proprietary
157	141◄─►164	llama-4-scout-17b-16e-instruct	1281	±5	31,231	Meta	Llama
158	143◄─►166	mistral-small-3.1-24b-instruct-2503	1279	±4	34,132	Mistral	Apache 2.0
159	142◄─►166	gemini-advanced-0514	1279	±5	50,142	Google	Proprietary
160	148◄─►167	llama-3.3-70b-instruct	1276	±3	55,561	Meta	Llama-3.3
161	142◄─►174	hunyuan-standard-2025-02-10	1275	±10	3,905	Tencent	Proprietary
162	151◄─►169	gemini-1.5-pro-001	1274	±4	79,132	Google	Proprietary
163	156◄─►170	gpt-4-turbo-2024-04-09	1272	±4	98,130	OpenAI	Proprietary
164	155◄─►171	deepseek-v2.5	1272	±5	24,574	DeepSeek	DeepSeek
165	151◄─►175	olmo-3.1-32b-think	1271	±7	8,498	Allen AI	Apache 2.0
166	159◄─►174	qwen2.5-72b-instruct	1269	±4	39,409	Alibaba	Qwen
167	161◄─►176	mistral-large-2407	1267	±4	45,460	Mistral	Mistral Research
168	157◄─►178	hunyuan-large-vision	1266	±9	5,601	Tencent	Proprietary
169	161◄─►177	athene-70b-0725	1266	±6	19,622	NexusFlow	CC-BY-NC-4.0
170	162◄─►177	mistral-large-2411	1266	±4	28,081	Mistral	MRL
171	163◄─►177	gpt-4-1106-preview	1264	±4	100,107	OpenAI	Proprietary
172	164◄─►178	gpt-4-0125-preview	1263	±4	93,439	OpenAI	Proprietary
173	164◄─►177	claude-3-opus-20240229	1263	±3	194,904	Anthropic	Proprietary
174	166◄─►178	llama-3.1-70b-instruct	1261	±4	55,234	Meta	Llama 3.1 Community
175	167◄─►179	amazon-nova-pro-v1.0	1259	±4	24,753	Amazon	Proprietary
176	172◄─►179	claude-3-5-haiku-20241022	1256	±3	71,179	Anthropic	Proprietary
177	164◄─►180	llama-3.1-tulu-3-70b	1256	±11	2,846	Ai2	Llama 3.1
178	168◄─►180	magistral-medium-2506	1256	±6	12,061	Mistral	Proprietary
179	175◄─►182	reka-core-20240904	1249	±7	7,309	Reka AI	Proprietary
180	177◄─►189	ibm-granite-h-small	1242	±8	5,675	IBM	Apache 2.0
181	179◄─►186	gemini-1.5-flash-001	1240	±4	62,823	Google	Proprietary
182	179◄─►192	jamba-1.5-large	1237	±7	8,659	AI21 Labs	Jamba Open
183	180◄─►194	mistral-small-24b-instruct-2501	1234	±6	14,677	Mistral	Apache 2.0
184	181◄─►194	gemma-2-27b-it	1232	±3	75,764	Google	Gemma license
185	180◄─►197	qwen2.5-coder-32b-instruct	1231	±8	5,430	Alibaba	Apache 2.0
186	180◄─►196	command-r-plus-08-2024	1229	±7	9,869	Cohere	CC-BY-NC-4.0
187	181◄─►196	amazon-nova-lite-v1.0	1229	±5	19,376	Amazon	Proprietary
188	180◄─►198	llama-3.1-nemotron-51b-instruct	1229	±10	3,749	Nvidia	Llama 3.1
189	181◄─►198	gemma-2-9b-it-simpo	1228	±7	10,069	Princeton	MIT
190	182◄─►198	glm-4-0520	1226	±7	9,788	Zhipu AI	Proprietary
191	182◄─►197	gemini-1.5-flash-8b-001	1226	±4	35,556	Google	Proprietary
192	182◄─►198	nemotron-4-340b-instruct	1225	±5	19,661	Nvidia	NVIDIA Open Model
193	183◄─►198	c4ai-aya-expanse-32b	1225	±5	27,123	Cohere	CC-BY-NC-4.0
194	185◄─►198	llama-3-70b-instruct	1221	±4	156,880	Meta	Llama 3 Community
195	187◄─►198	claude-3-sonnet-20240229	1219	±4	109,289	Anthropic	Proprietary
196	185◄─►201	reka-flash-20240904	1219	±7	7,537	Reka AI	Proprietary
197	183◄─►204	olmo-2-0325-32b-instruct	1218	±11	3,335	Allen AI	Apache-2.0
198	189◄─►200	phi-4	1217	±5	24,126	Microsoft	MIT
199	196◄─►205	amazon-nova-micro-v1.0	1209	±5	19,355	Amazon	Proprietary
200	197◄─►204	gemma-2-9b-it	1208	±4	54,615	Google	Gemma license
201	198◄─►205	gpt-4-0314	1207	±5	54,167	OpenAI	Proprietary
202	198◄─►206	command-r-plus	1204	±4	77,556	Cohere	CC-BY-NC-4.0
203	198◄─►207	qwen2-72b-instruct	1204	±5	37,325	Alibaba	Qianwen LICENSE
204	196◄─►212	hunyuan-standard-256k	1202	±12	2,729	Tencent	Proprietary
205	203◄─►211	claude-3-haiku-20240307	1195	±4	117,705	Anthropic	Proprietary
206	200◄─►213	llama-3.1-tulu-3-8b	1193	±11	2,895	Ai2	Llama 3.1
207	204◄─►213	deepseek-coder-v2	1192	±6	15,147	DeepSeek	DeepSeek License
208	202◄─►213	ministral-8b-2410	1191	±9	4,780	Mistral	MRL
209	204◄─►214	command-r-08-2024	1188	±7	10,141	Cohere	CC-BY-NC-4.0
210	204◄─►215	jamba-1.5-mini	1187	±7	8,854	AI21 Labs	Jamba Open
211	205◄─►213	llama-3.1-8b-instruct	1187	±4	49,605	Meta	Llama 3.1 Community
212	206◄─►213	gpt-4-0613	1187	±4	88,721	OpenAI	Proprietary
213	204◄─►215	c4ai-aya-expanse-8b	1186	±7	9,827	Cohere	CC-BY-NC-4.0
214	211◄─►218	mistral-large-2402	1177	±5	62,437	Mistral	Proprietary
215	212◄─►222	qwen1.5-110b-chat	1175	±6	26,191	Alibaba	Qianwen LICENSE
216	214◄─►223	yi-1.5-34b-chat	1173	±5	24,142	01 AI	Apache-2.0
217	214◄─►225	reka-flash-21b-20240226-online	1171	±7	15,451	Reka AI	Proprietary
218	215◄─►225	qwen1.5-72b-chat	1167	±5	39,296	Alibaba	Qianwen LICENSE
219	215◄─►225	llama-3-8b-instruct	1166	±4	104,636	Meta	Llama 3 Community
220	215◄─►227	mistral-medium	1166	±6	34,552	Mistral	Proprietary
221	215◄─►227	reka-flash-21b-20240226	1166	±6	24,806	Reka AI	Proprietary
222	216◄─►227	command-r	1164	±5	54,038	Cohere	CC-BY-NC-4.0
223	217◄─►227	mixtral-8x22b-instruct-v0.1	1163	±5	51,417	Mistral	Apache 2.0
224	214◄─►229	qwq-32b-preview	1162	±11	3,233	Alibaba	Apache 2.0
225	217◄─►229	internlm2_5-20b-chat	1159	±7	9,902	InternLM	Other
226	220◄─►229	gemma-2-2b-it	1156	±4	46,618	Google	Gemma license
227	220◄─►234	granite-3.1-8b-instruct	1150	±11	3,092	IBM	Apache 2.0
228	224◄─►232	gemini-pro-dev-api	1149	±7	18,352	Google	Proprietary
229	224◄─►237	zephyr-orpo-141b-A35b-v0.1	1144	±11	4,653	HuggingFace	Apache 2.0
230	227◄─►237	phi-3-medium-4k-instruct	1138	±5	25,055	Microsoft	MIT
231	227◄─►237	qwen1.5-32b-chat	1138	±6	21,744	Alibaba	Qianwen LICENSE
232	228◄─►241	starling-lm-7b-beta	1132	±7	16,057	Nexusflow	Apache-2.0
233	229◄─►240	mixtral-8x7b-instruct-v0.1	1132	±4	73,505	Mistral	Apache 2.0
234	227◄─►243	gemini-pro	1131	±12	6,390	Google	Proprietary
235	229◄─►242	yi-34b-chat	1129	±7	15,483	01 AI	Yi License
236	228◄─►245	granite-3.1-2b-instruct	1128	±11	3,191	IBM	Apache 2.0
237	229◄─►243	qwen1.5-14b-chat	1128	±7	17,841	Alibaba	Qianwen LICENSE
238	232◄─►243	gpt-3.5-turbo-0125	1125	±5	66,191	OpenAI	Proprietary
239	232◄─►249	tulu-2-dpo-70b	1122	±10	6,534	AllenAI/UW	AI2 ImpACT Low-risk
240	232◄─►250	wizardlm-70b	1120	±10	8,214	Microsoft	Llama 2 Community
241	233◄─►248	dbrx-instruct-preview	1119	±6	32,196	Databricks	DBRX LICENSE
242	235◄─►250	llama-2-70b-chat	1116	±6	38,491	Meta	Llama 2 Community
243	234◄─►256	nous-hermes-2-mixtral-8x7b-dpo	1113	±12	3,776	NousResearch	Apache-2.0
244	239◄─►253	phi-3-small-8k-instruct	1110	±6	17,763	Microsoft	MIT
245	238◄─►255	llama-3.2-3b-instruct	1110	±8	7,936	Meta	Llama 3.2
246	239◄─►256	starling-lm-7b-alpha	1108	±8	10,224	UC Berkeley	CC-BY-NC-4.0
247	239◄─►256	openchat-3.5-0106	1107	±8	12,636	OpenChat	Apache-2.0
248	240◄─►256	vicuna-33b	1106	±6	22,479	LMSYS	Non-commercial
249	238◄─►260	deepseek-llm-67b-chat	1106	±12	4,933	DeepSeek	DeepSeek License
250	243◄─►259	snowflake-arctic-instruct	1102	±6	32,836	Snowflake	Apache 2.0
251	241◄─►264	llama2-70b-steerlm-chat	1099	±13	3,584	Nvidia	Llama 2 Community
252	243◄─►262	openchat-3.5	1098	±10	7,967	OpenChat	Apache-2.0
253	243◄─►262	granite-3.0-8b-instruct	1097	±9	6,643	IBM	Apache 2.0
254	244◄─►264	gpt-3.5-turbo-1106	1095	±9	16,616	OpenAI	Proprietary
255	245◄─►262	gemma-1.1-7b-it	1094	±6	23,893	Google	Gemma license
256	244◄─►264	openhermes-2.5-mistral-7b	1093	±11	5,006	NousResearch	Apache-2.0
257	249◄─►264	mistral-7b-instruct-v0.2	1090	±7	19,402	Mistral	Apache-2.0
258	251◄─►267	llama-2-13b-chat	1085	±7	19,171	Meta	Llama 2 Community
259	250◄─►270	qwen1.5-7b-chat	1084	±10	4,735	Alibaba	Qianwen LICENSE
260	249◄─►271	solar-10.7b-instruct-v1.0	1084	±13	4,155	Upstage AI	CC-BY-NC-4.0
261	249◄─►273	dolphin-2.2.1-mistral-7b	1082	±16	1,679	Cognitive Computations	Apache-2.0
262	254◄─►270	phi-3-mini-4k-instruct-june-2024	1080	±6	12,296	Microsoft	MIT
263	251◄─►271	granite-3.0-2b-instruct	1080	±8	6,837	IBM	Apache 2.0
264	254◄─►271	wizardlm-13b	1077	±9	7,046	Microsoft	Llama 2 Community
265	258◄─►271	phi-3-mini-4k-instruct	1074	±6	20,115	Microsoft	MIT
266	258◄─►276	zephyr-7b-beta	1070	±9	11,116	HuggingFace	MIT
267	258◄─►279	mpt-30b-chat	1069	±12	2,571	MosaicML	CC-BY-NC-SA-4.0
268	259◄─►278	codellama-34b-instruct	1066	±9	7,363	Meta	Llama 2 Community
269	259◄─►281	zephyr-7b-alpha	1059	±16	1,785	HuggingFace	MIT
270	266◄─►279	vicuna-13b	1058	±7	19,366	LMSYS	Llama 2 Community
271	259◄─►282	codellama-70b-instruct	1058	±18	1,143	Meta	Llama 2 Community
272	265◄─►280	gemma-7b-it	1057	±10	8,925	Google	Gemma license
273	266◄─►280	llama-3.2-1b-instruct	1055	±8	8,045	Meta	Llama 3.2
274	261◄─►282	falcon-180b-chat	1055	±17	1,295	TII	Falcon-180B TII License
275	267◄─►280	llama-2-7b-chat	1054	±7	14,148	Meta	Llama 2 Community
276	265◄─►281	guanaco-33b	1054	±12	2,921	UW	Non-commercial
277	266◄─►282	qwen-14b-chat	1052	±11	4,964	Alibaba	Qianwen LICENSE
278	267◄─►281	phi-3-mini-128k-instruct	1051	±7	20,691	Microsoft	MIT
279	268◄─►285	smollm2-1.7b-instruct	1043	±14	2,201	HuggingFace	Apache 2.0
280	270◄─►285	stripedhyena-nous-7b	1039	±11	5,184	Together AI	Apache 2.0
281	273◄─►285	olmo-7b-instruct	1032	±11	6,329	Allen AI	Apache-2.0
282	276◄─►285	vicuna-7b	1031	±9	6,923	LMSYS	Llama 2 Community
283	279◄─►285	palm-2	1028	±9	8,554	Google	Proprietary
284	279◄─►285	mistral-7b-instruct	1024	±9	8,977	Mistral	Apache 2.0
285	279◄─►285	gemma-1.1-2b-it	1023	±8	10,853	Google	Gemma license
286	286◄─►288	gemma-2b-it	1003	±12	4,779	Google	Gemma license
287	286◄─►288	qwen1.5-4b-chat	998	±9	7,598	Alibaba	Qianwen LICENSE
288	286◄─►289	koala-13b	990	±10	6,964	UC Berkeley	Non-commercial
289	288◄─►291	chatglm3-6b	973	±12	4,658	Tsinghua	Apache-2.0
290	289◄─►294	gpt4all-13b-snoozy	957	±16	1,743	Nomic AI	Non-commercial
291	289◄─►294	mpt-7b-chat	956	±12	3,925	MosaicML	CC-BY-NC-SA-4.0
292	290◄─►294	RWKV-4-Raven-14B	949	±12	4,845	RWKV	Apache 2.0
293	290◄─►296	chatglm2-6b	939	±14	2,657	Tsinghua	Apache-2.0
294	290◄─►296	alpaca-13b	933	±12	5,745	Stanford	Non-commercial
295	293◄─►297	chatglm-6b	919	±13	4,914	Tsinghua	Non-commercial
296	293◄─►297	oasst-pythia-12b	917	±11	6,311	OpenAssistant	Apache 2.0
297	295◄─►297	fastchat-t5-3b	895	±13	4,203	LMSYS	Apache 2.0
298	298◄─►299	stablelm-tuned-alpha-7b	867	±13	3,287	Stability AI	CC-BY-NC-SA-4.0
299	298◄─►300	dolly-v2-12b	852	±14	3,412	Databricks	MIT
300	299◄─►300	llama-13b	834	±16	2,391	Meta	Non-commercial

Text Arena

Remove Style Control Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

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)