Text Arena

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

Last Updated

Dec 16, 2025

Total Votes

4,821,345

Total Models

285

/

Style Control

	Rank Spread (Upper-Lower)
1	1◄─►1	gemini-3-pro	1492	±6	18,120	Google	Proprietary
2	2◄─►3	grok-4.1-thinking	1478	±6	19,094	xAI	Proprietary
3	2◄─►6	claude-opus-4-5-20251101-thinking-32k	1469	±7	11,942	Anthropic	Proprietary
4	3◄─►6	claude-opus-4-5-20251101	1465	±7	12,785	Anthropic	Proprietary
5	3◄─►6	grok-4.1	1465	±6	18,855	xAI	Proprietary
6	3◄─►8	gpt-5.1-high	1458	±6	16,188	OpenAI	Proprietary
7	6◄─►12	gemini-2.5-pro	1451	±3	79,015	Google	Proprietary
8	6◄─►12	claude-sonnet-4-5-20250929-thinking-32k	1450	±4	30,277	Anthropic	Proprietary
9	7◄─►13	claude-opus-4-1-20250805-thinking-16k	1448	±4	46,023	Anthropic	Proprietary
10	7◄─►15	claude-sonnet-4-5-20250929	1446	±5	25,512	Anthropic	Proprietary
11	7◄─►20	gpt-4.5-preview-2025-02-27	1443	±6	14,644	OpenAI	Proprietary
12	9◄─►18	claude-opus-4-1-20250805	1441	±4	59,113	Anthropic	Proprietary
13	7◄─►21	gpt-5.2-high	1441	±9	6,035	OpenAI	Proprietary
14	10◄─►20	chatgpt-4o-latest-20250326	1439	±3	65,567	OpenAI	Proprietary
15	10◄─►21	gpt-5.1	1437	±6	17,454	OpenAI	Proprietary
16	11◄─►21	gpt-5-high	1436	±5	32,784	OpenAI	Proprietary
17	12◄─►23	o3-2025-04-16	1434	±4	61,397	OpenAI	Proprietary
18	11◄─►26	qwen3-max-preview	1433	±5	28,044	Alibaba	Proprietary
19	12◄─►33	grok-4-1-fast-reasoning	1431	±6	11,335	xAI	Proprietary
20	11◄─►39	ernie-5.0-preview-1103	1430	±9	5,862	Baidu	Proprietary
21	14◄─►36	kimi-k2-thinking-turbo	1428	±6	17,812	Moonshot	Modified MIT
22	17◄─►39	glm-4.6	1426	±5	26,458	Z.ai	MIT
23	18◄─►40	gpt-5-chat	1425	±4	32,034	OpenAI	Proprietary
24	17◄─►40	qwen3-max-2025-09-23	1424	±6	9,231	Alibaba	Proprietary
25	18◄─►40	deepseek-v3.2-exp	1423	±7	11,934	DeepSeek AI	MIT
26	19◄─►40	claude-opus-4-20250514-thinking-16k	1423	±4	37,734	Anthropic	Proprietary
27	19◄─►40	qwen3-235b-a22b-instruct-2507	1422	±4	53,333	Alibaba	Apache 2.0
28	18◄─►44	deepseek-v3.2-thinking	1421	±8	8,029	DeepSeek AI	MIT
29	19◄─►42	deepseek-v3.2-exp-thinking	1421	±7	9,205	DeepSeek AI	MIT
30	19◄─►45	grok-4-fast-chat	1420	±8	7,042	xAI	Proprietary
31	19◄─►46	deepseek-v3.2	1419	±7	8,734	DeepSeek AI	MIT
32	20◄─►46	deepseek-r1-0528	1418	±6	19,169	DeepSeek	MIT
33	19◄─►47	kimi-k2-0905-preview	1418	±7	11,808	Moonshot	Modified MIT
34	21◄─►47	deepseek-v3.1	1417	±6	15,215	DeepSeek	MIT
35	23◄─►46	kimi-k2-0711-preview	1416	±5	28,538	Moonshot	Modified MIT
36	20◄─►48	mistral-large-3	1416	±7	8,618	Mistral	Apache 2.0
37	21◄─►47	deepseek-v3.1-thinking	1416	±7	11,953	DeepSeek	MIT
38	19◄─►51	deepseek-v3.1-terminus	1415	±10	3,739	DeepSeek AI	MIT
39	21◄─►48	qwen3-vl-235b-a22b-instruct	1415	±7	8,506	Alibaba	Apache 2.0
40	20◄─►54	deepseek-v3.1-terminus-thinking	1414	±10	3,512	DeepSeek AI	MIT
41	28◄─►48	gpt-4.1-2025-04-14	1412	±4	52,409	OpenAI	Proprietary
42	28◄─►48	claude-opus-4-20250514	1412	±4	45,486	Anthropic	Proprietary
43	29◄─►48	mistral-medium-2508	1411	±4	47,546	Mistral	Proprietary
44	29◄─►51	grok-3-preview-02-24	1410	±4	34,041	xAI	Proprietary
45	31◄─►53	grok-4-0709	1409	±4	42,429	xAI	Proprietary
46	30◄─►54	glm-4.5	1409	±5	24,743	Z.ai	MIT
47	34◄─►53	gemini-2.5-flash	1408	±3	78,510	Google	Proprietary
48	37◄─►58	gemini-2.5-flash-preview-09-2025	1405	±4	31,666	Google	Proprietary
49	42◄─►59	claude-haiku-4-5-20251001	1402	±4	28,635	Anthropic	Proprietary
50	42◄─►59	grok-4-fast-reasoning	1402	±5	18,827	xAI	Proprietary
51	44◄─►62	qwen3-next-80b-a3b-instruct	1401	±5	23,045	Alibaba	Apache 2.0
52	44◄─►60	o1-2024-12-17	1400	±4	28,039	OpenAI	Proprietary
53	42◄─►63	longcat-flash-chat	1400	±6	11,470	Meituan	MIT
54	46◄─►62	qwen3-235b-a22b-no-thinking	1400	±4	39,252	Alibaba	Apache 2.0
55	48◄─►63	claude-sonnet-4-20250514-thinking-32k	1399	±4	36,076	Anthropic	Proprietary
56	48◄─►67	qwen3-235b-a22b-thinking-2507	1397	±6	9,314	Alibaba	Apache 2.0
57	49◄─►67	deepseek-r1	1396	±5	18,718	DeepSeek	MIT
58	48◄─►69	qwen3-vl-235b-a22b-thinking	1394	±7	7,968	Alibaba	Apache 2.0
59	51◄─►69	gpt-5-mini-high	1392	±5	27,350	OpenAI	Proprietary
60	52◄─►68	deepseek-v3-0324	1392	±4	46,632	DeepSeek	MIT
61	48◄─►75	hunyuan-vision-1.5-thinking	1391	±12	2,212	Tencent	Proprietary
62	54◄─►69	o4-mini-2025-04-16	1391	±4	46,706	OpenAI	Proprietary
63	52◄─►71	mai-1-preview	1390	±5	18,128	Microsoft AI	Proprietary
64	56◄─►72	claude-sonnet-4-20250514	1389	±4	41,503	Anthropic	Proprietary
65	56◄─►73	o1-preview	1387	±5	31,505	OpenAI	Proprietary
66	56◄─►72	claude-3-7-sonnet-20250219-thinking-32k	1387	±4	39,819	Anthropic	Proprietary
67	58◄─►73	qwen3-coder-480b-a35b-instruct	1386	±5	23,031	Alibaba	Apache 2.0
68	56◄─►76	hunyuan-t1-20250711	1385	±9	4,803	Tencent	Proprietary
69	59◄─►75	mistral-medium-2505	1383	±5	34,409	Mistral	Proprietary
70	62◄─►75	qwen3-30b-a3b-instruct-2507	1382	±5	24,130	Alibaba	Apache 2.0
71	63◄─►76	gpt-4.1-mini-2025-04-14	1381	±4	40,378	OpenAI	Proprietary
72	62◄─►79	hunyuan-turbos-20250416	1380	±6	11,094	Tencent	Proprietary
73	65◄─►79	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1378	±4	31,734	Google	Proprietary
74	67◄─►80	gemini-2.5-flash-lite-preview-06-17-thinking	1375	±4	33,824	Google	Proprietary
75	67◄─►81	qwen3-235b-a22b	1374	±5	27,081	Alibaba	Apache 2.0
76	70◄─►81	qwen2.5-max	1373	±4	33,491	Alibaba	Proprietary
77	72◄─►81	claude-3-5-sonnet-20241022	1372	±3	89,736	Anthropic	Proprietary
78	72◄─►84	claude-3-7-sonnet-20250219	1371	±4	44,477	Anthropic	Proprietary
79	72◄─►84	glm-4.5-air	1370	±4	31,562	Z.ai	MIT
80	74◄─►87	qwen3-next-80b-a3b-thinking	1367	±6	13,785	Alibaba	Apache 2.0
81	75◄─►85	minimax-m1	1366	±4	36,745	MiniMax	Apache 2.0
82	78◄─►87	gemma-3-27b-it	1364	±4	49,186	Google	Gemma
83	78◄─►92	o3-mini-high	1362	±5	18,735	OpenAI	Proprietary
84	78◄─►92	grok-3-mini-high	1362	±5	17,509	xAI	Proprietary
85	80◄─►94	gemini-2.0-flash-001	1360	±4	45,025	Google	Proprietary
86	81◄─►103	deepseek-v3	1357	±5	21,994	DeepSeek	DeepSeek
87	81◄─►103	grok-3-mini-beta	1357	±5	23,702	xAI	Proprietary
88	83◄─►108	mistral-small-2506	1355	±5	18,258	Mistral	Apache 2.0
89	85◄─►108	gpt-oss-120b	1352	±4	31,158	OpenAI	Apache 2.0
90	85◄─►108	gemini-2.0-flash-lite-preview-02-05	1352	±4	25,215	Google	Proprietary
91	83◄─►112	glm-4.5v	1352	±8	4,971	Z.ai	MIT
92	86◄─►108	command-a-03-2025	1352	±3	57,663	Cohere	CC-BY-NC-4.0
93	82◄─►112	intellect-3	1351	±10	3,949	Prime Intellect	MIT
94	86◄─►109	gemini-1.5-pro-002	1351	±3	56,012	Google	Proprietary
95	86◄─►112	amazon-nova-experimental-chat-10-20	1349	±7	10,140	Amazon	Proprietary
96	88◄─►112	o3-mini	1348	±3	58,702	OpenAI	Proprietary
97	86◄─►114	ling-flash-2.0	1346	±7	7,129	Ant Group	MIT
98	83◄─►122	hunyuan-turbos-20250226	1346	±12	2,250	Tencent	Proprietary
99	86◄─►116	minimax-m2	1346	±8	7,096	MiniMax	Apache 2.0
100	86◄─►116	step-3	1346	±7	6,621	StepFun	Apache 2.0
101	83◄─►123	llama-3.1-nemotron-ultra-253b-v1	1346	±12	2,573	Nvidia	Nvidia Open Model
102	86◄─►122	amazon-nova-experimental-chat-10-09	1345	±11	2,880	Amazon	Proprietary
103	86◄─►122	qwen3-32b	1345	±9	3,943	Alibaba	Apache 2.0
104	92◄─►112	gpt-4o-2024-05-13	1344	±3	113,568	OpenAI	Proprietary
105	86◄─►122	qwen-plus-0125	1344	±8	5,861	Alibaba	Proprietary
106	88◄─►122	glm-4-plus-0111	1343	±8	5,806	Zhipu	Proprietary
107	93◄─►116	claude-3-5-sonnet-20240620	1342	±3	82,864	Anthropic	Proprietary
108	88◄─►125	gemma-3-12b-it	1340	±9	3,866	Google	Gemma
109	88◄─►127	nvidia-llama-3.3-nemotron-super-49b-v1.5	1340	±10	3,469	Nvidia	Nvidia Open
110	93◄─►125	nova-2-lite	1339	±8	8,061	Amazon	Proprietary
111	93◄─►124	gpt-5-nano-high	1339	±7	8,371	OpenAI	Proprietary
112	88◄─►129	hunyuan-turbo-0110	1339	±11	2,322	Tencent	Proprietary
113	99◄─►124	o1-mini	1335	±4	52,301	OpenAI	Proprietary
114	99◄─►124	llama-3.1-405b-instruct-bf16	1335	±4	41,932	Meta	Llama 3.1 Community
115	102◄─►127	gpt-4o-2024-08-06	1334	±4	45,787	OpenAI	Proprietary
116	102◄─►127	qwq-32b	1334	±4	26,201	Alibaba	Apache 2.0
117	102◄─►127	grok-2-2024-08-13	1334	±4	63,725	xAI	Proprietary
118	102◄─►128	gemini-advanced-0514	1333	±5	50,654	Google	Proprietary
119	102◄─►127	llama-3.1-405b-instruct-fp8	1333	±3	60,272	Meta	Llama 3.1 Community
120	98◄─►137	step-2-16k-exp-202412	1332	±9	4,895	StepFun	Proprietary
121	98◄─►145	nvidia-nemotron-3-nano-30b-a3b-bf16	1329	±11	3,365	Nvidia	NVIDIA Open Model
122	108◄─►138	yi-lightning	1328	±5	27,624	01 AI	Proprietary
123	111◄─►138	llama-4-maverick-17b-128e-instruct	1327	±4	41,102	Meta	Llama 4
124	113◄─►142	qwen3-30b-a3b	1326	±5	27,411	Alibaba	Apache 2.0
125	102◄─►150	llama-3.3-nemotron-49b-super-v1	1325	±12	2,243	Nvidia	Nvidia
126	107◄─►149	hunyuan-large-2025-02-10	1325	±10	3,760	Tencent	Proprietary
127	120◄─►145	gpt-4-turbo-2024-04-09	1323	±4	98,965	OpenAI	Proprietary
128	119◄─►145	llama-4-scout-17b-16e-instruct	1322	±5	31,085	Meta	Llama
129	120◄─►145	claude-3-5-haiku-20241022	1322	±3	71,248	Anthropic	Proprietary
130	113◄─►150	deepseek-v2.5-1210	1322	±8	6,877	DeepSeek	DeepSeek
131	120◄─►145	claude-3-opus-20240229	1321	±3	196,368	Anthropic	Proprietary
132	120◄─►145	gemini-1.5-pro-001	1321	±4	79,769	Google	Proprietary
133	118◄─►150	gpt-4.1-nano-2025-04-14	1321	±8	6,143	OpenAI	Proprietary
134	120◄─►150	ring-flash-2.0	1320	±7	7,260	Ant Group	MIT
135	120◄─►150	step-1o-turbo-202506	1319	±7	9,636	StepFun	Proprietary
136	123◄─►149	llama-3.3-70b-instruct	1319	±3	55,970	Meta	Llama-3.3
137	121◄─►150	gemma-3n-e4b-it	1318	±5	23,421	Google	Gemma
138	120◄─►151	gpt-oss-20b	1318	±6	10,831	OpenAI	Apache 2.0
139	123◄─►150	glm-4-plus	1318	±5	26,342	Zhipu AI	Proprietary
140	123◄─►151	qwen-max-0919	1317	±6	16,598	Alibaba	Qwen
141	124◄─►150	gpt-4o-mini-2024-07-18	1316	±3	69,290	OpenAI	Proprietary
142	124◄─►157	qwen2.5-plus-1127	1314	±6	10,252	Alibaba	Proprietary
143	130◄─►156	athene-v2-chat	1313	±4	24,880	NexusFlow	NexusFlow
144	130◄─►155	mistral-large-2407	1313	±4	45,968	Mistral	Mistral Research
145	123◄─►160	olmo-3-32b-think	1313	±9	4,534	Allen AI	Apache 2.0
146	130◄─►156	gpt-4-1106-preview	1312	±4	101,117	OpenAI	Proprietary
147	130◄─►156	gpt-4-0125-preview	1312	±4	94,534	OpenAI	Proprietary
148	120◄─►160	mercury	1311	±14	1,962	Inception AI	Proprietary
149	124◄─►160	hunyuan-standard-2025-02-10	1310	±10	3,920	Tencent	Proprietary
150	132◄─►157	gemini-1.5-flash-002	1310	±4	35,180	Google	Proprietary
151	142◄─►160	grok-2-mini-2024-08-13	1307	±4	52,789	xAI	Proprietary
152	142◄─►160	deepseek-v2.5	1306	±5	24,839	DeepSeek	DeepSeek
153	142◄─►160	magistral-medium-2506	1305	±6	11,961	Mistral	Proprietary
154	143◄─►160	mistral-large-2411	1304	±4	28,455	Mistral	MRL
155	142◄─►160	athene-70b-0725	1304	±6	19,796	NexusFlow	CC-BY-NC-4.0
156	146◄─►160	mistral-small-3.1-24b-instruct-2503	1303	±4	34,038	Mistral	Apache 2.0
157	140◄─►166	gemma-3-4b-it	1302	±9	4,195	Google	Gemma
158	148◄─►160	qwen2.5-72b-instruct	1301	±4	39,632	Alibaba	Qwen
159	148◄─►169	llama-3.1-nemotron-70b-instruct	1297	±8	7,216	Nvidia	Llama 3.1
160	148◄─►170	hunyuan-large-vision	1294	±9	5,578	Tencent	Proprietary
161	158◄─►169	llama-3.1-70b-instruct	1293	±4	56,003	Meta	Llama 3.1 Community
162	159◄─►172	amazon-nova-pro-v1.0	1288	±4	25,218	Amazon	Proprietary
163	158◄─►174	jamba-1.5-large	1288	±7	8,730	AI21 Labs	Jamba Open
164	158◄─►174	ibm-granite-h-small	1288	±8	5,690	IBM	Apache 2.0
165	159◄─►172	gemma-2-27b-it	1287	±3	76,195	Google	Gemma license
166	158◄─►174	reka-core-20240904	1287	±7	7,380	Reka AI	Proprietary
167	158◄─►180	llama-3.1-nemotron-51b-instruct	1286	±10	3,777	Nvidia	Llama 3.1
168	158◄─►180	llama-3.1-tulu-3-70b	1286	±10	2,881	Ai2	Llama 3.1
169	159◄─►174	gpt-4-0314	1285	±5	54,754	OpenAI	Proprietary
170	161◄─►174	gemini-1.5-flash-001	1284	±4	63,418	Google	Proprietary
171	162◄─►180	claude-3-sonnet-20240229	1280	±4	110,173	Anthropic	Proprietary
172	162◄─►180	gemma-2-9b-it-simpo	1278	±7	10,108	Princeton	MIT
173	164◄─►180	nemotron-4-340b-instruct	1277	±5	19,913	Nvidia	NVIDIA Open Model
174	164◄─►181	command-r-plus-08-2024	1277	±7	9,931	Cohere	CC-BY-NC-4.0
175	169◄─►180	llama-3-70b-instruct	1275	±3	158,908	Meta	Llama 3 Community
176	169◄─►181	gpt-4-0613	1274	±4	89,612	OpenAI	Proprietary
177	169◄─►183	mistral-small-24b-instruct-2501	1273	±6	14,830	Mistral	Apache 2.0
178	169◄─►185	glm-4-0520	1272	±7	9,857	Zhipu AI	Proprietary
179	169◄─►185	reka-flash-20240904	1272	±7	7,583	Reka AI	Proprietary
180	169◄─►189	qwen2.5-coder-32b-instruct	1269	±8	5,452	Alibaba	Apache 2.0
181	175◄─►189	c4ai-aya-expanse-32b	1266	±5	27,362	Cohere	CC-BY-NC-4.0
182	177◄─►189	gemma-2-9b-it	1264	±4	54,954	Google	Gemma license
183	177◄─►191	deepseek-coder-v2	1263	±6	15,242	DeepSeek AI	DeepSeek License
184	178◄─►190	command-r-plus	1262	±4	78,401	Cohere	CC-BY-NC-4.0
185	178◄─►191	qwen2-72b-instruct	1261	±5	37,688	Alibaba	Qianwen LICENSE
186	180◄─►191	claude-3-haiku-20240307	1261	±4	118,626	Anthropic	Proprietary
187	180◄─►191	amazon-nova-lite-v1.0	1259	±5	19,760	Amazon	Proprietary
188	180◄─►191	gemini-1.5-flash-8b-001	1259	±4	35,914	Google	Proprietary
189	183◄─►191	phi-4	1255	±4	24,354	Microsoft	MIT
190	180◄─►196	olmo-2-0325-32b-instruct	1252	±11	3,377	Allen AI	Apache-2.0
191	184◄─►196	command-r-08-2024	1251	±7	10,229	Cohere	CC-BY-NC-4.0
192	190◄─►200	mistral-large-2402	1241	±5	63,404	Mistral	Proprietary
193	190◄─►200	amazon-nova-micro-v1.0	1241	±5	19,774	Amazon	Proprietary
194	190◄─►205	jamba-1.5-mini	1238	±7	8,918	AI21 Labs	Jamba Open
195	190◄─►208	ministral-8b-2410	1237	±9	4,833	Mistral	MRL
196	192◄─►206	qwen1.5-110b-chat	1233	±5	26,679	Alibaba	Qianwen LICENSE
197	192◄─►209	gemini-pro-dev-api	1233	±7	18,454	Google	Proprietary
198	190◄─►210	hunyuan-standard-256k	1233	±12	2,761	Tencent	Proprietary
199	192◄─►208	qwen1.5-72b-chat	1233	±5	39,689	Alibaba	Qianwen LICENSE
200	192◄─►209	reka-flash-21b-20240226-online	1232	±7	15,606	Reka AI	Proprietary
201	194◄─►209	mixtral-8x22b-instruct-v0.1	1229	±4	52,214	Mistral	Apache 2.0
202	194◄─►210	command-r	1227	±5	54,710	Cohere	CC-BY-NC-4.0
203	194◄─►211	reka-flash-21b-20240226	1226	±6	25,026	Reka AI	Proprietary
204	196◄─►211	gpt-3.5-turbo-0125	1223	±5	67,214	OpenAI	Proprietary
205	195◄─►212	c4ai-aya-expanse-8b	1223	±7	9,922	Cohere	CC-BY-NC-4.0
206	198◄─►211	llama-3-8b-instruct	1222	±4	106,055	Meta	Llama 3 Community
207	196◄─►212	mistral-medium	1222	±5	34,893	Mistral	Proprietary
208	194◄─►213	llama-3.1-tulu-3-8b	1221	±11	2,943	Ai2	Llama 3.1
209	194◄─►215	gemini-pro	1220	±12	6,418	Google	Proprietary
210	201◄─►217	zephyr-orpo-141b-A35b-v0.1	1213	±11	4,712	HuggingFace	Apache 2.0
211	206◄─►215	yi-1.5-34b-chat	1213	±5	24,417	01 AI	Apache-2.0
212	208◄─►215	llama-3.1-8b-instruct	1211	±4	50,234	Meta	Llama 3.1 Community
213	203◄─►221	granite-3.1-8b-instruct	1210	±11	3,142	IBM	Apache 2.0
214	209◄─►221	qwen1.5-32b-chat	1204	±6	22,068	Alibaba	Qianwen LICENSE
215	209◄─►223	gpt-3.5-turbo-1106	1201	±9	16,760	OpenAI	Proprietary
216	212◄─►222	gemma-2-2b-it	1198	±4	46,901	Google	Gemma license
217	212◄─►223	phi-3-medium-4k-instruct	1198	±5	25,301	Microsoft	MIT
218	213◄─►223	mixtral-8x7b-instruct-v0.1	1197	±4	74,303	Mistral	Apache 2.0
219	213◄─►228	dbrx-instruct-preview	1195	±6	32,760	Databricks	DBRX LICENSE
220	213◄─►232	internlm2_5-20b-chat	1192	±7	10,038	InternLM	Other
221	213◄─►232	qwen1.5-14b-chat	1192	±7	18,066	Alibaba	Qianwen LICENSE
222	216◄─►238	wizardlm-70b	1184	±9	8,270	Microsoft	Llama 2 Community
223	219◄─►238	granite-3.0-8b-instruct	1183	±9	6,727	IBM	Apache 2.0
224	219◄─►236	yi-34b-chat	1183	±7	15,624	01 AI	Yi License
225	215◄─►239	deepseek-llm-67b-chat	1183	±12	4,950	DeepSeek AI	DeepSeek License
226	219◄─►239	openchat-3.5-0106	1182	±8	12,712	OpenChat	Apache-2.0
227	219◄─►239	openchat-3.5	1181	±10	8,009	OpenChat	Apache-2.0
228	219◄─►240	granite-3.1-2b-instruct	1180	±11	3,235	IBM	Apache 2.0
229	220◄─►239	snowflake-arctic-instruct	1179	±6	33,272	Snowflake	Apache 2.0
230	220◄─►239	gemma-1.1-7b-it	1179	±6	24,327	Google	Gemma license
231	220◄─►241	tulu-2-dpo-70b	1178	±10	6,579	AllenAI/UW	AI2 ImpACT Low-risk
232	220◄─►243	openhermes-2.5-mistral-7b	1175	±10	5,026	NousResearch	Apache-2.0
233	222◄─►241	vicuna-33b	1172	±6	22,613	LMSYS	Non-commercial
234	222◄─►244	starling-lm-7b-beta	1172	±7	16,190	Nexusflow	Apache-2.0
235	222◄─►243	phi-3-small-8k-instruct	1171	±6	17,983	Microsoft	MIT
236	223◄─►243	llama-2-70b-chat	1170	±5	38,767	Meta	Llama 2 Community
237	223◄─►246	starling-lm-7b-alpha	1167	±8	10,267	UC Berkeley	CC-BY-NC-4.0
238	225◄─►246	llama-3.2-3b-instruct	1166	±8	8,043	Meta	Llama 3.2
239	222◄─►249	nous-hermes-2-mixtral-8x7b-dpo	1165	±12	3,792	NousResearch	Apache-2.0
240	230◄─►253	qwq-32b-preview	1158	±11	3,256	Alibaba	Apache 2.0
241	236◄─►252	granite-3.0-2b-instruct	1156	±8	6,922	IBM	Apache 2.0
242	231◄─►256	llama2-70b-steerlm-chat	1155	±13	3,605	Nvidia	Llama 2 Community
243	233◄─►257	solar-10.7b-instruct-v1.0	1152	±13	4,187	Upstage AI	CC-BY-NC-4.0
244	233◄─►261	dolphin-2.2.1-mistral-7b	1151	±15	1,685	Cognitive Computations	Apache-2.0
245	237◄─►260	mpt-30b-chat	1150	±12	2,606	MosaicML	CC-BY-NC-SA-4.0
246	239◄─►256	mistral-7b-instruct-v0.2	1149	±7	19,603	Mistral	Apache-2.0
247	239◄─►257	wizardlm-13b	1149	±9	7,122	Microsoft	Llama 2 Community
248	237◄─►264	falcon-180b-chat	1146	±17	1,312	TII	Falcon-180B TII License
249	239◄─►262	qwen1.5-7b-chat	1143	±10	4,782	Alibaba	Qianwen LICENSE
250	240◄─►260	phi-3-mini-4k-instruct-june-2024	1142	±6	12,415	Microsoft	MIT
251	240◄─►261	llama-2-13b-chat	1141	±7	19,357	Meta	Llama 2 Community
252	241◄─►262	vicuna-13b	1141	±7	19,539	LMSYS	Llama 2 Community
253	240◄─►264	qwen-14b-chat	1138	±11	5,004	Alibaba	Qianwen LICENSE
254	242◄─►264	codellama-34b-instruct	1136	±9	7,417	Meta	Llama 2 Community
255	242◄─►264	palm-2	1136	±9	8,634	Google	Proprietary
256	242◄─►264	gemma-7b-it	1134	±9	9,034	Google	Gemma license
257	246◄─►265	zephyr-7b-beta	1130	±9	11,220	HuggingFace	MIT
258	246◄─►264	phi-3-mini-128k-instruct	1130	±7	21,024	Microsoft	MIT
259	250◄─►265	phi-3-mini-4k-instruct	1128	±6	20,539	Microsoft	MIT
260	244◄─►269	zephyr-7b-alpha	1127	±16	1,803	HuggingFace	MIT
261	246◄─►268	guanaco-33b	1127	±12	2,955	UW	Non-commercial
262	252◄─►269	stripedhyena-nous-7b	1120	±11	5,214	Together AI	Apache 2.0
263	252◄─►269	smollm2-1.7b-instruct	1119	±14	2,244	HuggingFace	Apache 2.0
264	248◄─►270	codellama-70b-instruct	1118	±18	1,151	Meta	Llama 2 Community
265	258◄─►269	vicuna-7b	1114	±9	6,972	LMSYS	Llama 2 Community
266	260◄─►269	gemma-1.1-2b-it	1113	±8	11,035	Google	Gemma license
267	260◄─►269	llama-3.2-1b-instruct	1113	±8	8,166	Meta	Llama 3.2
268	260◄─►270	mistral-7b-instruct	1109	±9	9,042	Mistral	Apache 2.0
269	261◄─►270	llama-2-7b-chat	1107	±7	14,272	Meta	Llama 2 Community
270	267◄─►274	gemma-2b-it	1090	±12	4,817	Google	Gemma license
271	270◄─►272	qwen1.5-4b-chat	1090	±9	7,662	Alibaba	Qianwen LICENSE
272	270◄─►277	olmo-7b-instruct	1073	±11	6,412	Allen AI	Apache-2.0
273	271◄─►277	koala-13b	1069	±10	6,998	UC Berkeley	Non-commercial
274	272◄─►277	alpaca-13b	1065	±12	5,828	Stanford	Non-commercial
275	271◄─►278	gpt4all-13b-snoozy	1064	±15	1,773	Nomic AI	Non-commercial
276	272◄─►278	mpt-7b-chat	1060	±12	3,977	MosaicML	CC-BY-NC-SA-4.0
277	272◄─►278	chatglm3-6b	1056	±12	4,692	Tsinghua	Apache-2.0
278	275◄─►280	RWKV-4-Raven-14B	1040	±11	4,898	RWKV	Apache 2.0
279	278◄─►280	chatglm2-6b	1024	±14	2,683	Tsinghua	Apache-2.0
280	278◄─►280	oasst-pythia-12b	1021	±11	6,343	OpenAssistant	Apache 2.0
281	281◄─►284	chatglm-6b	994	±13	4,968	Tsinghua	Non-commercial
282	281◄─►284	fastchat-t5-3b	990	±12	4,270	LMSYS	Apache 2.0
283	281◄─►284	dolly-v2-12b	977	±14	3,471	Databricks	MIT
284	281◄─►285	llama-13b	968	±16	2,441	Meta	Non-commercial
285	284◄─►285	stablelm-tuned-alpha-7b	950	±13	3,325	Stability AI	CC-BY-NC-SA-4.0

Text Arena

Default Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

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

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

Battle Count for Each Combination of Models (without Ties)