Text Arena

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

Last Updated

Dec 23, 2025

Total Votes

4,873,395

Total Models

291

/

Style Control

	Rank Spread
1	1◄─►2	gemini-3-pro	1484	±6	20,141	Google	Proprietary
2	1◄─►3	gemini-3-flash	1471	±9	5,333	Google	Proprietary
3	2◄─►3	gemini-2.5-pro	1464	±3	80,690	Google	Proprietary
4	4◄─►13	gemini-3-flash (thinking-minimal)	1451	±9	5,629	Google	Proprietary
5	4◄─►11	grok-4.1-thinking	1450	±5	20,967	xAI	Proprietary
6	4◄─►14	claude-opus-4-5-20251101	1446	±6	14,395	Anthropic	Proprietary
7	4◄─►14	ernie-5.0-preview-1103	1446	±8	7,430	Baidu	Proprietary
8	4◄─►14	claude-opus-4-5-20251101-thinking-32k	1444	±6	13,596	Anthropic	Proprietary
9	4◄─►14	grok-4.1	1443	±5	21,934	xAI	Proprietary
10	4◄─►14	gpt-5.1-high	1443	±6	17,868	OpenAI	Proprietary
11	4◄─►21	ernie-5.0-preview-1203	1441	±11	3,185	Baidu	Proprietary
12	5◄─►15	glm-4.6	1440	±4	27,979	Z.ai	MIT
13	5◄─►16	qwen3-max-preview	1438	±5	28,023	Alibaba	Proprietary
14	6◄─►27	mistral-large-3	1434	±7	10,299	Mistral	Apache 2.0
15	12◄─►32	mistral-medium-2508	1430	±4	49,247	Mistral	Proprietary
16	13◄─►34	chatgpt-4o-latest-20250326	1428	±3	67,658	OpenAI	Proprietary
17	13◄─►35	glm-4.5	1428	±5	24,723	Z.ai	MIT
18	13◄─►35	claude-sonnet-4-5-20250929	1427	±5	27,356	Anthropic	Proprietary
19	13◄─►35	claude-sonnet-4-5-20250929-thinking-32k	1427	±4	31,992	Anthropic	Proprietary
20	13◄─►40	deepseek-r1-0528	1426	±6	19,162	DeepSeek	MIT
21	14◄─►40	grok-3-preview-02-24	1424	±4	34,041	xAI	Proprietary
22	14◄─►43	deepseek-v3.2-exp	1424	±7	11,926	DeepSeek AI	MIT
23	11◄─►50	gpt-5.2	1424	±12	2,435	OpenAI	Proprietary
24	14◄─►43	longcat-flash-chat	1422	±6	11,465	Meituan	MIT
25	14◄─►46	deepseek-v3.2-exp-thinking	1422	±7	9,188	DeepSeek AI	MIT
26	15◄─►44	gpt-5.1	1421	±6	19,276	OpenAI	Proprietary
27	14◄─►47	qwen3-vl-235b-a22b-instruct	1421	±7	9,449	Alibaba	Apache 2.0
28	15◄─►48	deepseek-v3.2-thinking	1420	±7	9,657	DeepSeek AI	MIT
29	16◄─►48	deepseek-v3.2	1419	±7	11,544	DeepSeek AI	MIT
30	16◄─►48	deepseek-v3.1	1419	±6	15,210	DeepSeek	MIT
31	20◄─►47	claude-opus-4-1-20250805-thinking-16k	1419	±4	47,738	Anthropic	Proprietary
32	14◄─►52	deepseek-v3.1-terminus	1419	±10	3,733	DeepSeek AI	MIT
33	20◄─►47	qwen3-235b-a22b-instruct-2507	1418	±4	55,241	Alibaba	Apache 2.0
34	15◄─►52	gpt-5.2-high	1418	±9	6,193	OpenAI	Proprietary
35	20◄─►48	qwen3-next-80b-a3b-instruct	1418	±5	23,005	Alibaba	Apache 2.0
36	20◄─►50	gpt-4.5-preview-2025-02-27	1417	±6	14,646	OpenAI	Proprietary
37	15◄─►52	deepseek-v3.1-terminus-thinking	1417	±10	3,508	DeepSeek AI	MIT
38	15◄─►55	amazon-nova-experimental-chat-11-10	1417	±11	3,479	Amazon	Proprietary
39	17◄─►52	deepseek-v3.1-thinking	1416	±7	11,944	DeepSeek	MIT
40	22◄─►50	gemini-2.5-flash	1415	±3	80,226	Google	Proprietary
41	20◄─►52	qwen3-max-2025-09-23	1414	±6	9,222	Alibaba	Proprietary
42	22◄─►55	qwen3-235b-a22b-thinking-2507	1413	±6	9,310	Alibaba	Apache 2.0
43	22◄─►52	kimi-k2-thinking-turbo	1413	±5	19,526	Moonshot	Modified MIT
44	24◄─►52	claude-opus-4-1-20250805	1412	±4	60,843	Anthropic	Proprietary
45	29◄─►52	o3-2025-04-16	1411	±4	61,371	OpenAI	Proprietary
46	25◄─►55	grok-4-1-fast-reasoning	1410	±6	13,526	xAI	Proprietary
47	33◄─►55	grok-4-0709	1409	±4	42,387	xAI	Proprietary
48	25◄─►55	grok-4-fast-chat	1408	±8	7,036	xAI	Proprietary
49	36◄─►55	gemini-2.5-flash-preview-09-2025	1407	±4	33,373	Google	Proprietary
50	36◄─►55	gpt-5-high	1407	±4	32,759	OpenAI	Proprietary
51	26◄─►59	hunyuan-vision-1.5-thinking	1403	±12	2,204	Tencent	Proprietary
52	44◄─►58	gpt-5-chat	1403	±4	32,021	OpenAI	Proprietary
53	33◄─►59	mimo-v2-flash	1400	±12	2,604	Xiaomi	MIT
54	44◄─►59	qwen3-vl-235b-a22b-thinking	1400	±7	7,959	Alibaba	Apache 2.0
55	44◄─►59	hunyuan-t1-20250711	1398	±9	4,802	Tencent	Proprietary
56	51◄─►59	grok-4-fast-reasoning	1395	±5	18,804	xAI	Proprietary
57	51◄─►61	amazon-nova-experimental-chat-10-20	1394	±6	11,625	Amazon	Proprietary
58	51◄─►61	mai-1-preview	1393	±5	18,102	Microsoft AI	Proprietary
59	52◄─►61	qwen3-235b-a22b-no-thinking	1392	±4	39,231	Alibaba	Apache 2.0
60	57◄─►67	claude-haiku-4-5-20251001	1384	±4	30,384	Anthropic	Proprietary
61	57◄─►68	qwen3-30b-a3b-instruct-2507	1383	±5	24,105	Alibaba	Apache 2.0
62	60◄─►68	gpt-4.1-2025-04-14	1382	±4	52,374	OpenAI	Proprietary
63	60◄─►69	glm-4.5-air	1382	±4	31,522	Z.ai	MIT
64	60◄─►72	kimi-k2-0905-preview	1380	±7	11,873	Moonshot	Modified MIT
65	60◄─►72	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1378	±4	33,428	Google	Proprietary
66	60◄─►81	hunyuan-turbos-20250416	1375	±6	11,094	Tencent	Proprietary
67	60◄─►79	gpt-5-mini-high	1375	±5	27,328	OpenAI	Proprietary
68	61◄─►79	claude-opus-4-20250514-thinking-16k	1374	±4	37,703	Anthropic	Proprietary
69	63◄─►79	deepseek-v3-0324	1374	±4	46,613	DeepSeek	MIT
70	64◄─►84	deepseek-r1	1372	±5	18,722	DeepSeek	MIT
71	64◄─►84	kimi-k2-0711-preview	1371	±5	28,520	Moonshot	Modified MIT
72	66◄─►84	gemini-2.5-flash-lite-preview-06-17-thinking	1369	±4	33,803	Google	Proprietary
73	66◄─►86	mistral-medium-2505	1368	±5	34,390	Mistral	Proprietary
74	66◄─►86	grok-3-mini-high	1367	±5	17,496	xAI	Proprietary
75	66◄─►86	qwen3-235b-a22b	1367	±5	27,066	Alibaba	Apache 2.0
76	66◄─►88	qwen3-next-80b-a3b-thinking	1367	±6	13,762	Alibaba	Apache 2.0
77	66◄─►86	qwen2.5-max	1367	±4	33,497	Alibaba	Proprietary
78	69◄─►88	o1-2024-12-17	1365	±4	28,039	OpenAI	Proprietary
79	64◄─►92	amazon-nova-experimental-chat-10-09	1365	±11	2,878	Amazon	Proprietary
80	69◄─►88	gpt-oss-120b	1365	±4	31,118	OpenAI	Apache 2.0
81	70◄─►88	claude-opus-4-20250514	1364	±4	45,461	Anthropic	Proprietary
82	66◄─►92	ling-flash-2.0	1364	±7	7,120	Ant Group	MIT
83	70◄─►88	grok-3-mini-beta	1363	±5	23,693	xAI	Proprietary
84	70◄─►92	nova-2-lite	1362	±7	9,785	Amazon	Proprietary
85	77◄─►92	gemma-3-27b-it	1357	±4	49,174	Google	Gemma
86	77◄─►93	qwen3-coder-480b-a35b-instruct	1357	±5	24,124	Alibaba	Apache 2.0
87	73◄─►96	intellect-3	1356	±8	5,426	Prime Intellect	MIT
88	73◄─►97	nvidia-nemotron-3-nano-30b-a3b-bf16	1355	±9	5,033	Nvidia	NVIDIA Open Model
89	82◄─►94	gemini-2.0-flash-001	1354	±4	45,008	Google	Proprietary
90	82◄─►95	o4-mini-2025-04-16	1354	±4	46,697	OpenAI	Proprietary
91	82◄─►96	o1-preview	1353	±5	31,505	OpenAI	Proprietary
92	82◄─►103	step-3	1350	±7	6,611	StepFun	Apache 2.0
93	86◄─►98	claude-sonnet-4-20250514-thinking-32k	1349	±4	36,055	Anthropic	Proprietary
94	87◄─►103	minimax-m1	1346	±4	36,709	MiniMax	Apache 2.0
95	88◄─►107	minimax-m2	1343	±8	7,084	MiniMax	Apache 2.0
96	92◄─►107	gpt-4.1-mini-2025-04-14	1340	±4	40,365	OpenAI	Proprietary
97	89◄─►113	qwen3-32b	1339	±9	3,944	Alibaba	Apache 2.0
98	93◄─►110	mistral-small-2506	1339	±5	18,247	Mistral	Apache 2.0
99	93◄─►110	claude-sonnet-4-20250514	1338	±4	41,477	Anthropic	Proprietary
100	91◄─►115	nvidia-llama-3.3-nemotron-super-49b-v1.5	1336	±10	3,468	Nvidia	Nvidia Open
101	95◄─►112	o3-mini-high	1336	±5	18,725	OpenAI	Proprietary
102	93◄─►114	step-1o-turbo-202506	1336	±7	9,635	StepFun	Proprietary
103	93◄─►115	glm-4.5v	1334	±8	4,967	Z.ai	MIT
104	93◄─►115	gemma-3-12b-it	1334	±9	3,866	Google	Gemma
105	95◄─►114	deepseek-v3	1333	±5	21,995	DeepSeek	DeepSeek
106	95◄─►115	ring-flash-2.0	1332	±7	7,246	Ant Group	MIT
107	95◄─►115	glm-4-plus-0111	1332	±8	5,808	Zhipu	Proprietary
108	97◄─►114	command-a-03-2025	1331	±3	57,626	Cohere	CC-BY-NC-4.0
109	97◄─►115	gemini-2.0-flash-lite-preview-02-05	1330	±4	25,222	Google	Proprietary
110	99◄─►115	qwq-32b	1329	±4	26,194	Alibaba	Apache 2.0
111	97◄─►122	qwen-plus-0125	1326	±8	5,862	Alibaba	Proprietary
112	101◄─►122	step-2-16k-exp-202412	1321	±9	4,896	StepFun	Proprietary
113	104◄─►122	gpt-5-nano-high	1320	±7	8,363	OpenAI	Proprietary
114	111◄─►122	o3-mini	1320	±3	58,682	OpenAI	Proprietary
115	111◄─►122	gemini-1.5-pro-002	1319	±3	56,014	Google	Proprietary
116	99◄─►124	llama-3.1-nemotron-ultra-253b-v1	1319	±12	2,573	Nvidia	Nvidia Open Model
117	100◄─►124	hunyuan-turbos-20250226	1319	±12	2,254	Tencent	Proprietary
118	111◄─►122	o1-mini	1317	±4	52,303	OpenAI	Proprietary
119	111◄─►122	qwen3-30b-a3b	1317	±5	27,398	Alibaba	Apache 2.0
120	111◄─►123	claude-3-7-sonnet-20250219-thinking-32k	1315	±4	39,815	Anthropic	Proprietary
121	111◄─►133	hunyuan-turbo-0110	1311	±11	2,324	Tencent	Proprietary
122	111◄─►134	llama-3.3-nemotron-49b-super-v1	1308	±12	2,246	Nvidia	Nvidia
123	118◄─►130	gemma-3n-e4b-it	1307	±5	23,417	Google	Gemma
124	119◄─►130	grok-2-2024-08-13	1305	±4	63,725	xAI	Proprietary
125	121◄─►134	yi-lightning	1302	±5	27,624	01 AI	Proprietary
126	121◄─►134	gpt-4o-2024-05-13	1301	±3	113,568	OpenAI	Proprietary
127	121◄─►135	claude-3-7-sonnet-20250219	1300	±4	44,474	Anthropic	Proprietary
128	121◄─►137	qwen2.5-plus-1127	1299	±6	10,254	Alibaba	Proprietary
129	120◄─►141	olmo-3-32b-think	1299	±8	5,976	Allen AI	Apache 2.0
130	123◄─►135	claude-3-5-sonnet-20241022	1298	±3	89,725	Anthropic	Proprietary
131	121◄─►146	deepseek-v2.5-1210	1294	±8	6,877	DeepSeek	DeepSeek
132	127◄─►145	athene-v2-chat	1292	±4	24,880	NexusFlow	NexusFlow
133	123◄─►152	gemma-3-4b-it	1291	±9	4,196	Google	Gemma
134	129◄─►147	glm-4-plus	1290	±5	26,343	Zhipu AI	Proprietary
135	129◄─►152	gpt-oss-20b	1289	±6	10,825	OpenAI	Apache 2.0
136	130◄─►150	llama-4-maverick-17b-128e-instruct	1288	±4	41,081	Meta	Llama 4
137	124◄─►153	hunyuan-large-2025-02-10	1288	±10	3,760	Tencent	Proprietary
138	130◄─►151	gemini-1.5-flash-002	1287	±4	35,180	Google	Proprietary
139	123◄─►158	mercury	1287	±14	1,960	Inception AI	Proprietary
140	131◄─►151	gpt-4o-mini-2024-07-18	1287	±3	69,292	OpenAI	Proprietary
141	130◄─►154	gpt-4.1-nano-2025-04-14	1285	±8	6,146	OpenAI	Proprietary
142	131◄─►152	llama-3.1-405b-instruct-bf16	1284	±4	41,948	Meta	Llama 3.1 Community
143	131◄─►153	gpt-4o-2024-08-06	1283	±4	45,787	OpenAI	Proprietary
144	130◄─►156	llama-3.1-nemotron-70b-instruct	1283	±8	7,216	Nvidia	Llama 3.1
145	131◄─►154	qwen-max-0919	1282	±6	16,599	Alibaba	Qwen
146	133◄─►153	llama-3.1-405b-instruct-fp8	1282	±3	60,273	Meta	Llama 3.1 Community
147	132◄─►154	llama-4-scout-17b-16e-instruct	1281	±5	31,060	Meta	Llama
148	134◄─►154	grok-2-mini-2024-08-13	1281	±4	52,792	xAI	Proprietary
149	134◄─►153	claude-3-5-sonnet-20240620	1281	±3	82,864	Anthropic	Proprietary
150	135◄─►157	gemini-advanced-0514	1279	±5	50,652	Google	Proprietary
151	137◄─►157	mistral-small-3.1-24b-instruct-2503	1279	±4	34,024	Mistral	Apache 2.0
152	140◄─►158	llama-3.3-70b-instruct	1276	±3	55,954	Meta	Llama-3.3
153	134◄─►166	hunyuan-standard-2025-02-10	1275	±10	3,923	Tencent	Proprietary
154	144◄─►160	gemini-1.5-pro-001	1274	±4	79,769	Google	Proprietary
155	148◄─►161	gpt-4-turbo-2024-04-09	1272	±4	98,965	OpenAI	Proprietary
156	148◄─►162	deepseek-v2.5	1272	±5	24,839	DeepSeek	DeepSeek
157	151◄─►164	qwen2.5-72b-instruct	1270	±4	39,634	Alibaba	Qwen
158	153◄─►167	mistral-large-2407	1266	±4	45,968	Mistral	Mistral Research
159	153◄─►168	mistral-large-2411	1266	±4	28,454	Mistral	MRL
160	149◄─►169	hunyuan-large-vision	1265	±9	5,575	Tencent	Proprietary
161	153◄─►168	athene-70b-0725	1265	±6	19,795	NexusFlow	CC-BY-NC-4.0
162	155◄─►168	gpt-4-1106-preview	1264	±4	101,116	OpenAI	Proprietary
163	156◄─►169	gpt-4-0125-preview	1263	±4	94,534	OpenAI	Proprietary
164	157◄─►168	claude-3-opus-20240229	1262	±3	196,365	Anthropic	Proprietary
165	157◄─►169	llama-3.1-70b-instruct	1262	±4	56,002	Meta	Llama 3.1 Community
166	158◄─►170	amazon-nova-pro-v1.0	1259	±4	25,218	Amazon	Proprietary
167	163◄─►170	claude-3-5-haiku-20241022	1256	±3	71,235	Anthropic	Proprietary
168	156◄─►172	llama-3.1-tulu-3-70b	1256	±10	2,882	Ai2	Llama 3.1
169	159◄─►171	magistral-medium-2506	1255	±6	11,952	Mistral	Proprietary
170	166◄─►173	reka-core-20240904	1249	±7	7,380	Reka AI	Proprietary
171	168◄─►181	ibm-granite-h-small	1242	±8	5,686	IBM	Apache 2.0
172	170◄─►178	gemini-1.5-flash-001	1240	±4	63,418	Google	Proprietary
173	169◄─►183	jamba-1.5-large	1238	±7	8,730	AI21 Labs	Jamba Open
174	171◄─►185	mistral-small-24b-instruct-2501	1234	±6	14,831	Mistral	Apache 2.0
175	171◄─►185	gemma-2-27b-it	1232	±3	76,196	Google	Gemma license
176	171◄─►188	qwen2.5-coder-32b-instruct	1230	±8	5,452	Alibaba	Apache 2.0
177	171◄─►187	command-r-plus-08-2024	1230	±7	9,932	Cohere	CC-BY-NC-4.0
178	172◄─►187	amazon-nova-lite-v1.0	1229	±5	19,765	Amazon	Proprietary
179	171◄─►189	llama-3.1-nemotron-51b-instruct	1228	±10	3,777	Nvidia	Llama 3.1
180	172◄─►189	gemma-2-9b-it-simpo	1228	±7	10,108	Princeton	MIT
181	173◄─►187	gemini-1.5-flash-8b-001	1227	±4	35,914	Google	Proprietary
182	172◄─►189	glm-4-0520	1226	±7	9,857	Zhipu AI	Proprietary
183	173◄─►189	nemotron-4-340b-instruct	1225	±5	19,913	Nvidia	NVIDIA Open Model
184	174◄─►189	c4ai-aya-expanse-32b	1225	±5	27,362	Cohere	CC-BY-NC-4.0
185	176◄─►189	llama-3-70b-instruct	1221	±4	158,907	Meta	Llama 3 Community
186	176◄─►191	reka-flash-20240904	1219	±7	7,585	Reka AI	Proprietary
187	179◄─►191	claude-3-sonnet-20240229	1219	±4	110,173	Anthropic	Proprietary
188	174◄─►195	olmo-2-0325-32b-instruct	1219	±11	3,379	Allen AI	Apache-2.0
189	180◄─►191	phi-4	1217	±4	24,355	Microsoft	MIT
190	186◄─►196	amazon-nova-micro-v1.0	1210	±5	19,776	Amazon	Proprietary
191	189◄─►196	gemma-2-9b-it	1208	±4	54,957	Google	Gemma license
192	189◄─►196	gpt-4-0314	1206	±5	54,754	OpenAI	Proprietary
193	189◄─►197	command-r-plus	1205	±4	78,400	Cohere	CC-BY-NC-4.0
194	189◄─►198	qwen2-72b-instruct	1203	±5	37,688	Alibaba	Qianwen LICENSE
195	186◄─►203	hunyuan-standard-256k	1203	±12	2,761	Tencent	Proprietary
196	194◄─►202	claude-3-haiku-20240307	1196	±4	118,626	Anthropic	Proprietary
197	190◄─►204	llama-3.1-tulu-3-8b	1195	±11	2,943	Ai2	Llama 3.1
198	193◄─►204	ministral-8b-2410	1192	±9	4,833	Mistral	MRL
199	195◄─►204	deepseek-coder-v2	1192	±6	15,242	DeepSeek AI	DeepSeek License
200	195◄─►204	command-r-08-2024	1189	±6	10,229	Cohere	CC-BY-NC-4.0
201	195◄─►206	jamba-1.5-mini	1188	±7	8,918	AI21 Labs	Jamba Open
202	196◄─►204	llama-3.1-8b-instruct	1188	±4	50,235	Meta	Llama 3.1 Community
203	195◄─►206	c4ai-aya-expanse-8b	1187	±7	9,922	Cohere	CC-BY-NC-4.0
204	197◄─►204	gpt-4-0613	1187	±4	89,612	OpenAI	Proprietary
205	203◄─►210	mistral-large-2402	1177	±5	63,404	Mistral	Proprietary
206	203◄─►213	qwen1.5-110b-chat	1175	±6	26,679	Alibaba	Qianwen LICENSE
207	205◄─►214	yi-1.5-34b-chat	1173	±5	24,417	01 AI	Apache-2.0
208	205◄─►216	reka-flash-21b-20240226-online	1171	±7	15,606	Reka AI	Proprietary
209	205◄─►217	qwen1.5-72b-chat	1167	±5	39,689	Alibaba	Qianwen LICENSE
210	206◄─►216	llama-3-8b-instruct	1166	±4	106,055	Meta	Llama 3 Community
211	206◄─►218	mistral-medium	1166	±5	34,893	Mistral	Proprietary
212	206◄─►218	reka-flash-21b-20240226	1166	±6	25,026	Reka AI	Proprietary
213	207◄─►218	command-r	1164	±5	54,710	Cohere	CC-BY-NC-4.0
214	205◄─►220	qwq-32b-preview	1163	±11	3,256	Alibaba	Apache 2.0
215	208◄─►218	mixtral-8x22b-instruct-v0.1	1163	±4	52,214	Mistral	Apache 2.0
216	208◄─►220	internlm2_5-20b-chat	1160	±7	10,038	InternLM	Other
217	211◄─►220	gemma-2-2b-it	1157	±4	46,900	Google	Gemma license
218	210◄─►225	granite-3.1-8b-instruct	1152	±11	3,142	IBM	Apache 2.0
219	215◄─►223	gemini-pro-dev-api	1150	±7	18,454	Google	Proprietary
220	215◄─►228	zephyr-orpo-141b-A35b-v0.1	1145	±11	4,712	HuggingFace	Apache 2.0
221	218◄─►228	qwen1.5-32b-chat	1139	±6	22,068	Alibaba	Qianwen LICENSE
222	218◄─►228	phi-3-medium-4k-instruct	1138	±5	25,301	Microsoft	MIT
223	219◄─►232	starling-lm-7b-beta	1133	±7	16,190	Nexusflow	Apache-2.0
224	220◄─►231	mixtral-8x7b-instruct-v0.1	1133	±4	74,303	Mistral	Apache 2.0
225	218◄─►234	gemini-pro	1132	±12	6,418	Google	Proprietary
226	219◄─►234	granite-3.1-2b-instruct	1130	±11	3,236	IBM	Apache 2.0
227	220◄─►233	qwen1.5-14b-chat	1130	±7	18,066	Alibaba	Qianwen LICENSE
228	220◄─►233	yi-34b-chat	1129	±7	15,624	01 AI	Yi License
229	223◄─►234	gpt-3.5-turbo-0125	1126	±5	67,214	OpenAI	Proprietary
230	223◄─►240	tulu-2-dpo-70b	1122	±10	6,579	AllenAI/UW	AI2 ImpACT Low-risk
231	223◄─►241	wizardlm-70b	1121	±9	8,270	Microsoft	Llama 2 Community
232	224◄─►239	dbrx-instruct-preview	1120	±6	32,760	Databricks	DBRX LICENSE
233	227◄─►241	llama-2-70b-chat	1116	±6	38,767	Meta	Llama 2 Community
234	225◄─►247	nous-hermes-2-mixtral-8x7b-dpo	1113	±12	3,792	NousResearch	Apache-2.0
235	230◄─►244	phi-3-small-8k-instruct	1111	±6	17,983	Microsoft	MIT
236	230◄─►246	llama-3.2-3b-instruct	1110	±8	8,043	Meta	Llama 3.2
237	230◄─►247	starling-lm-7b-alpha	1109	±8	10,267	UC Berkeley	CC-BY-NC-4.0
238	230◄─►247	openchat-3.5-0106	1108	±8	12,712	OpenChat	Apache-2.0
239	231◄─►247	vicuna-33b	1107	±6	22,613	LMSYS	Non-commercial
240	230◄─►251	deepseek-llm-67b-chat	1105	±12	4,950	DeepSeek AI	DeepSeek License
241	234◄─►250	snowflake-arctic-instruct	1102	±6	33,272	Snowflake	Apache 2.0
242	232◄─►254	llama2-70b-steerlm-chat	1100	±13	3,605	Nvidia	Llama 2 Community
243	234◄─►252	granite-3.0-8b-instruct	1099	±9	6,727	IBM	Apache 2.0
244	234◄─►253	openchat-3.5	1098	±10	8,009	OpenChat	Apache-2.0
245	236◄─►252	gemma-1.1-7b-it	1096	±6	24,327	Google	Gemma license
246	235◄─►255	gpt-3.5-turbo-1106	1095	±9	16,760	OpenAI	Proprietary
247	235◄─►255	openhermes-2.5-mistral-7b	1094	±10	5,026	NousResearch	Apache-2.0
248	240◄─►255	mistral-7b-instruct-v0.2	1091	±7	19,603	Mistral	Apache-2.0
249	242◄─►258	llama-2-13b-chat	1086	±7	19,357	Meta	Llama 2 Community
250	240◄─►262	solar-10.7b-instruct-v1.0	1085	±13	4,187	Upstage AI	CC-BY-NC-4.0
251	241◄─►261	qwen1.5-7b-chat	1084	±10	4,782	Alibaba	Qianwen LICENSE
252	240◄─►265	dolphin-2.2.1-mistral-7b	1081	±16	1,685	Cognitive Computations	Apache-2.0
253	244◄─►261	granite-3.0-2b-instruct	1081	±8	6,922	IBM	Apache 2.0
254	246◄─►261	phi-3-mini-4k-instruct-june-2024	1080	±6	12,414	Microsoft	MIT
255	245◄─►262	wizardlm-13b	1078	±9	7,122	Microsoft	Llama 2 Community
256	249◄─►262	phi-3-mini-4k-instruct	1075	±6	20,539	Microsoft	MIT
257	249◄─►268	zephyr-7b-beta	1071	±9	11,220	HuggingFace	MIT
258	249◄─►270	mpt-30b-chat	1070	±12	2,606	MosaicML	CC-BY-NC-SA-4.0
259	250◄─►270	codellama-34b-instruct	1066	±9	7,417	Meta	Llama 2 Community
260	250◄─►271	zephyr-7b-alpha	1060	±16	1,803	HuggingFace	MIT
261	256◄─►270	vicuna-13b	1059	±7	19,539	LMSYS	Llama 2 Community
262	250◄─►273	codellama-70b-instruct	1058	±18	1,151	Meta	Llama 2 Community
263	256◄─►271	gemma-7b-it	1057	±10	9,034	Google	Gemma license
264	257◄─►271	llama-3.2-1b-instruct	1056	±8	8,166	Meta	Llama 3.2
265	253◄─►273	falcon-180b-chat	1056	±17	1,312	TII	Falcon-180B TII License
266	256◄─►272	guanaco-33b	1055	±12	2,955	UW	Non-commercial
267	258◄─►271	llama-2-7b-chat	1054	±7	14,272	Meta	Llama 2 Community
268	258◄─►271	phi-3-mini-128k-instruct	1053	±7	21,024	Microsoft	MIT
269	257◄─►273	qwen-14b-chat	1052	±11	5,004	Alibaba	Qianwen LICENSE
270	257◄─►275	smollm2-1.7b-instruct	1048	±14	2,244	HuggingFace	Apache 2.0
271	261◄─►276	stripedhyena-nous-7b	1039	±11	5,214	Together AI	Apache 2.0
272	267◄─►276	vicuna-7b	1032	±9	6,972	LMSYS	Llama 2 Community
273	266◄─►276	olmo-7b-instruct	1032	±11	6,412	Allen AI	Apache-2.0
274	270◄─►276	palm-2	1029	±9	8,634	Google	Proprietary
275	270◄─►276	mistral-7b-instruct	1025	±9	9,042	Mistral	Apache 2.0
276	271◄─►276	gemma-1.1-2b-it	1024	±8	11,035	Google	Gemma license
277	277◄─►279	gemma-2b-it	1004	±12	4,817	Google	Gemma license
278	277◄─►279	qwen1.5-4b-chat	999	±9	7,662	Alibaba	Qianwen LICENSE
279	277◄─►280	koala-13b	991	±10	6,998	UC Berkeley	Non-commercial
280	279◄─►283	chatglm3-6b	973	±12	4,692	Tsinghua	Apache-2.0
281	280◄─►285	gpt4all-13b-snoozy	957	±15	1,773	Nomic AI	Non-commercial
282	280◄─►285	mpt-7b-chat	957	±12	3,977	MosaicML	CC-BY-NC-SA-4.0
283	280◄─►285	RWKV-4-Raven-14B	950	±12	4,898	RWKV	Apache 2.0
284	281◄─►287	chatglm2-6b	941	±14	2,683	Tsinghua	Apache-2.0
285	281◄─►287	alpaca-13b	934	±12	5,828	Stanford	Non-commercial
286	284◄─►288	chatglm-6b	920	±13	4,968	Tsinghua	Non-commercial
287	284◄─►288	oasst-pythia-12b	918	±11	6,343	OpenAssistant	Apache 2.0
288	286◄─►288	fastchat-t5-3b	896	±13	4,270	LMSYS	Apache 2.0
289	289◄─►290	stablelm-tuned-alpha-7b	868	±13	3,325	Stability AI	CC-BY-NC-SA-4.0
290	289◄─►291	dolly-v2-12b	853	±14	3,471	Databricks	MIT
291	290◄─►291	llama-13b	834	±16	2,441	Meta	Non-commercial

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)