Text Arena

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

Last Updated

Dec 10, 2025

Total Votes

4,767,246

Total Models

282

/

Style Control

	Rank Spread (Upper-Lower)
1	1◄─►1	gemini-3-pro	1492	±6	15,871	Google	Proprietary
2	2◄─►4	grok-4.1-thinking	1478	±6	16,660	xAI	Proprietary
3	2◄─►6	claude-opus-4-5-20251101-thinking-32k	1470	±7	9,879	Anthropic	Proprietary
4	2◄─►6	claude-opus-4-5-20251101	1467	±7	10,659	Anthropic	Proprietary
5	3◄─►6	grok-4.1	1465	±6	16,501	xAI	Proprietary
6	3◄─►9	gpt-5.1-high	1457	±6	13,953	OpenAI	Proprietary
7	6◄─►11	gemini-2.5-pro	1451	±3	76,975	Google	Proprietary
8	6◄─►11	claude-sonnet-4-5-20250929-thinking-32k	1450	±5	28,019	Anthropic	Proprietary
9	6◄─►12	claude-opus-4-1-20250805-thinking-16k	1448	±4	43,836	Anthropic	Proprietary
10	7◄─►15	claude-sonnet-4-5-20250929	1445	±5	23,185	Anthropic	Proprietary
11	7◄─►17	gpt-4.5-preview-2025-02-27	1443	±6	14,644	OpenAI	Proprietary
12	9◄─►16	claude-opus-4-1-20250805	1441	±4	56,830	Anthropic	Proprietary
13	10◄─►18	chatgpt-4o-latest-20250326	1440	±3	63,299	OpenAI	Proprietary
14	10◄─►20	gpt-5.1	1437	±6	15,063	OpenAI	Proprietary
15	10◄─►19	gpt-5-high	1436	±5	32,884	OpenAI	Proprietary
16	12◄─►20	o3-2025-04-16	1433	±4	61,581	OpenAI	Proprietary
17	11◄─►24	qwen3-max-preview	1433	±5	28,133	Alibaba	Proprietary
18	14◄─►39	grok-4-1-fast-reasoning	1428	±7	9,096	xAI	Proprietary
19	13◄─►39	ernie-5.0-preview-1103	1428	±9	5,738	Baidu	Proprietary
20	15◄─►39	kimi-k2-thinking-turbo	1426	±6	15,621	Moonshot	Modified MIT
21	17◄─►39	gpt-5-chat	1425	±4	32,128	OpenAI	Proprietary
22	17◄─►39	glm-4.6	1425	±5	24,502	Z.ai	MIT
23	17◄─►39	qwen3-max-2025-09-23	1423	±6	9,251	Alibaba	Proprietary
24	17◄─►39	deepseek-v3.2-exp	1423	±7	11,973	DeepSeek AI	MIT
25	18◄─►39	claude-opus-4-20250514-thinking-16k	1423	±4	37,863	Anthropic	Proprietary
26	18◄─►39	qwen3-235b-a22b-instruct-2507	1421	±4	51,250	Alibaba	Apache 2.0
27	18◄─►42	deepseek-v3.2-exp-thinking	1421	±7	9,220	DeepSeek AI	MIT
28	18◄─►45	grok-4-fast-chat	1420	±8	7,056	xAI	Proprietary
29	18◄─►46	deepseek-v3.2-thinking	1418	±9	5,948	DeepSeek AI	MIT
30	18◄─►45	kimi-k2-0905-preview	1418	±7	11,836	Moonshot	Modified MIT
31	18◄─►45	deepseek-r1-0528	1418	±6	19,236	DeepSeek	MIT
32	18◄─►45	kimi-k2-0711-preview	1417	±5	28,658	Moonshot	Modified MIT
33	18◄─►46	deepseek-v3.1	1416	±6	15,256	DeepSeek	MIT
34	18◄─►46	deepseek-v3.1-thinking	1416	±7	11,987	DeepSeek	MIT
35	18◄─►48	mistral-large-3	1415	±8	6,377	Mistral	Apache 2.0
36	18◄─►47	qwen3-vl-235b-a22b-instruct	1415	±7	8,532	Alibaba	Apache 2.0
37	18◄─►50	deepseek-v3.1-terminus	1415	±10	3,745	DeepSeek AI	MIT
38	18◄─►51	deepseek-v3.2	1414	±8	6,494	DeepSeek AI	MIT
39	18◄─►52	deepseek-v3.1-terminus-thinking	1414	±10	3,520	DeepSeek AI	MIT
40	27◄─►47	claude-opus-4-20250514	1412	±4	45,672	Anthropic	Proprietary
41	27◄─►47	gpt-4.1-2025-04-14	1412	±4	52,571	OpenAI	Proprietary
42	27◄─►49	mistral-medium-2508	1411	±4	45,391	Mistral	Proprietary
43	28◄─►50	grok-3-preview-02-24	1410	±4	34,122	xAI	Proprietary
44	28◄─►52	grok-4-0709	1409	±4	42,568	xAI	Proprietary
45	28◄─►53	glm-4.5	1408	±5	24,820	Z.ai	MIT
46	32◄─►52	gemini-2.5-flash	1408	±3	76,434	Google	Proprietary
47	35◄─►57	gemini-2.5-flash-preview-09-2025	1405	±4	29,427	Google	Proprietary
48	38◄─►58	claude-haiku-4-5-20251001	1402	±5	26,365	Anthropic	Proprietary
49	38◄─►58	grok-4-fast-reasoning	1402	±5	18,876	xAI	Proprietary
50	42◄─►59	o1-2024-12-17	1401	±4	28,039	OpenAI	Proprietary
51	43◄─►61	qwen3-next-80b-a3b-instruct	1400	±5	23,111	Alibaba	Apache 2.0
52	40◄─►63	longcat-flash-chat	1400	±6	11,498	Meituan	MIT
53	46◄─►62	qwen3-235b-a22b-no-thinking	1399	±4	39,375	Alibaba	Apache 2.0
54	47◄─►62	claude-sonnet-4-20250514-thinking-32k	1399	±4	36,210	Anthropic	Proprietary
55	47◄─►66	qwen3-235b-a22b-thinking-2507	1397	±6	9,345	Alibaba	Apache 2.0
56	47◄─►66	deepseek-r1	1396	±5	18,718	DeepSeek	MIT
57	48◄─►68	qwen3-vl-235b-a22b-thinking	1394	±7	7,986	Alibaba	Apache 2.0
58	50◄─►68	gpt-5-mini-high	1392	±5	27,446	OpenAI	Proprietary
59	51◄─►67	deepseek-v3-0324	1392	±4	46,777	DeepSeek	MIT
60	47◄─►73	hunyuan-vision-1.5-thinking	1391	±12	2,210	Tencent	Proprietary
61	52◄─►68	o4-mini-2025-04-16	1391	±4	46,832	OpenAI	Proprietary
62	51◄─►71	mai-1-preview	1390	±5	18,178	Microsoft AI	Proprietary
63	55◄─►71	claude-sonnet-4-20250514	1389	±4	41,654	Anthropic	Proprietary
64	55◄─►71	o1-preview	1388	±5	31,505	OpenAI	Proprietary
65	55◄─►72	claude-3-7-sonnet-20250219-thinking-32k	1387	±4	39,905	Anthropic	Proprietary
66	57◄─►72	qwen3-coder-480b-a35b-instruct	1385	±5	23,148	Alibaba	Apache 2.0
67	54◄─►75	hunyuan-t1-20250711	1385	±9	4,818	Tencent	Proprietary
68	58◄─►74	mistral-medium-2505	1383	±5	34,522	Mistral	Proprietary
69	61◄─►74	qwen3-30b-a3b-instruct-2507	1382	±5	24,190	Alibaba	Apache 2.0
70	61◄─►75	gpt-4.1-mini-2025-04-14	1380	±4	40,485	OpenAI	Proprietary
71	61◄─►78	hunyuan-turbos-20250416	1380	±6	11,130	Tencent	Proprietary
72	64◄─►78	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1378	±4	29,396	Google	Proprietary
73	66◄─►79	gemini-2.5-flash-lite-preview-06-17-thinking	1375	±4	33,959	Google	Proprietary
74	67◄─►80	qwen3-235b-a22b	1374	±5	27,167	Alibaba	Apache 2.0
75	69◄─►80	qwen2.5-max	1373	±4	33,545	Alibaba	Proprietary
76	71◄─►80	claude-3-5-sonnet-20241022	1372	±3	89,836	Anthropic	Proprietary
77	71◄─►83	claude-3-7-sonnet-20250219	1371	±4	44,557	Anthropic	Proprietary
78	71◄─►83	glm-4.5-air	1370	±4	31,668	Z.ai	MIT
79	73◄─►86	qwen3-next-80b-a3b-thinking	1367	±6	13,822	Alibaba	Apache 2.0
80	74◄─►86	minimax-m1	1366	±4	36,877	MiniMax	Apache 2.0
81	77◄─►87	gemma-3-27b-it	1364	±4	49,312	Google	Gemma
82	77◄─►90	o3-mini-high	1363	±5	18,735	OpenAI	Proprietary
83	77◄─►91	grok-3-mini-high	1362	±5	17,587	xAI	Proprietary
84	79◄─►92	gemini-2.0-flash-001	1360	±4	45,105	Google	Proprietary
85	79◄─►100	deepseek-v3	1358	±5	21,994	DeepSeek	DeepSeek
86	79◄─►103	grok-3-mini-beta	1357	±5	23,791	xAI	Proprietary
87	82◄─►107	mistral-small-2506	1354	±5	18,325	Mistral	Apache 2.0
88	84◄─►108	gemini-2.0-flash-lite-preview-02-05	1353	±4	25,215	Google	Proprietary
89	85◄─►108	gpt-oss-120b	1352	±4	31,256	OpenAI	Apache 2.0
90	85◄─►108	command-a-03-2025	1352	±3	57,820	Cohere	CC-BY-NC-4.0
91	85◄─►108	gemini-1.5-pro-002	1352	±3	56,012	Google	Proprietary
92	82◄─►110	glm-4.5v	1352	±8	4,973	Z.ai	MIT
93	85◄─►112	amazon-nova-experimental-chat-10-20	1348	±7	7,940	Amazon	Proprietary
94	87◄─►110	o3-mini	1348	±3	58,808	OpenAI	Proprietary
95	81◄─►121	intellect-3	1348	±13	2,020	Prime Intellect	MIT
96	82◄─►121	hunyuan-turbos-20250226	1346	±12	2,250	Tencent	Proprietary
97	85◄─►116	ling-flash-2.0	1346	±7	7,157	Ant Group	MIT
98	88◄─►111	gpt-4o-2024-05-13	1346	±3	113,568	OpenAI	Proprietary
99	86◄─►116	step-3	1346	±7	6,638	StepFun	Apache 2.0
100	85◄─►118	minimax-m2	1345	±8	7,123	MiniMax	Apache 2.0
101	83◄─►121	llama-3.1-nemotron-ultra-253b-v1	1345	±12	2,573	Nvidia	Nvidia Open Model
102	85◄─►121	amazon-nova-experimental-chat-10-09	1345	±11	2,891	Amazon	Proprietary
103	86◄─►120	qwen-plus-0125	1345	±8	5,861	Alibaba	Proprietary
104	85◄─►120	qwen3-32b	1344	±9	3,943	Alibaba	Apache 2.0
105	86◄─►120	glm-4-plus-0111	1343	±8	5,806	Zhipu	Proprietary
106	92◄─►112	claude-3-5-sonnet-20240620	1343	±3	82,864	Anthropic	Proprietary
107	87◄─►124	gemma-3-12b-it	1340	±9	3,866	Google	Gemma
108	87◄─►125	nvidia-llama-3.3-nemotron-super-49b-v1.5	1340	±10	3,492	Nvidia	Nvidia Open
109	87◄─►127	hunyuan-turbo-0110	1339	±11	2,322	Tencent	Proprietary
110	92◄─►122	gpt-5-nano-high	1339	±7	8,390	OpenAI	Proprietary
111	97◄─►122	o1-mini	1336	±4	52,301	OpenAI	Proprietary
112	97◄─►122	llama-3.1-405b-instruct-bf16	1336	±4	41,932	Meta	Llama 3.1 Community
113	97◄─►123	gpt-4o-2024-08-06	1335	±4	45,787	OpenAI	Proprietary
114	97◄─►125	gemini-advanced-0514	1335	±5	50,654	Google	Proprietary
115	99◄─►123	grok-2-2024-08-13	1335	±4	63,725	xAI	Proprietary
116	100◄─►124	llama-3.1-405b-instruct-fp8	1334	±3	60,272	Meta	Llama 3.1 Community
117	94◄─►133	nova-2-lite	1334	±9	5,799	Amazon	Proprietary
118	99◄─►125	qwq-32b	1334	±4	26,269	Alibaba	Apache 2.0
119	95◄─►134	step-2-16k-exp-202412	1333	±9	4,895	StepFun	Proprietary
120	107◄─►135	yi-lightning	1329	±5	27,624	01 AI	Proprietary
121	110◄─►138	llama-4-maverick-17b-128e-instruct	1327	±4	41,199	Meta	Llama 4
122	114◄─►139	qwen3-30b-a3b	1326	±5	27,485	Alibaba	Apache 2.0
123	100◄─►148	llama-3.3-nemotron-49b-super-v1	1326	±12	2,243	Nvidia	Nvidia
124	103◄─►147	hunyuan-large-2025-02-10	1325	±10	3,760	Tencent	Proprietary
125	117◄─►139	gpt-4-turbo-2024-04-09	1325	±4	98,965	OpenAI	Proprietary
126	118◄─►142	claude-3-opus-20240229	1323	±3	196,368	Anthropic	Proprietary
127	118◄─►142	gemini-1.5-pro-001	1323	±4	79,769	Google	Proprietary
128	118◄─►142	claude-3-5-haiku-20241022	1323	±3	71,373	Anthropic	Proprietary
129	112◄─►148	deepseek-v2.5-1210	1323	±8	6,877	DeepSeek	DeepSeek
130	118◄─►146	llama-4-scout-17b-16e-instruct	1322	±5	31,193	Meta	Llama
131	117◄─►148	gpt-4.1-nano-2025-04-14	1320	±8	6,143	OpenAI	Proprietary
132	118◄─►148	ring-flash-2.0	1320	±7	7,278	Ant Group	MIT
133	122◄─►147	llama-3.3-70b-instruct	1319	±3	56,008	Meta	Llama-3.3
134	118◄─►148	step-1o-turbo-202506	1319	±7	9,661	StepFun	Proprietary
135	121◄─►148	glm-4-plus	1319	±5	26,342	Zhipu AI	Proprietary
136	121◄─►148	gemma-3n-e4b-it	1318	±5	23,470	Google	Gemma
137	121◄─►148	qwen-max-0919	1318	±6	16,598	Alibaba	Qwen
138	120◄─►149	gpt-oss-20b	1318	±6	10,848	OpenAI	Apache 2.0
139	124◄─►148	gpt-4o-mini-2024-07-18	1317	±3	69,291	OpenAI	Proprietary
140	127◄─►153	gpt-4-1106-preview	1314	±4	101,117	OpenAI	Proprietary
141	124◄─►154	qwen2.5-plus-1127	1314	±6	10,252	Alibaba	Proprietary
142	127◄─►153	gpt-4-0125-preview	1314	±4	94,534	OpenAI	Proprietary
143	127◄─►153	mistral-large-2407	1314	±4	45,968	Mistral	Mistral Research
144	127◄─►154	athene-v2-chat	1313	±4	24,880	NexusFlow	NexusFlow
145	130◄─►155	gemini-1.5-flash-002	1311	±4	35,180	Google	Proprietary
146	119◄─►159	mercury	1311	±14	1,965	Inception AI	Proprietary
147	124◄─►158	hunyuan-standard-2025-02-10	1310	±10	3,920	Tencent	Proprietary
148	140◄─►157	grok-2-mini-2024-08-13	1307	±4	52,789	xAI	Proprietary
149	140◄─►158	deepseek-v2.5	1307	±5	24,839	DeepSeek	DeepSeek
150	128◄─►162	olmo-3-32b-think	1306	±11	3,405	Allen AI	Apache 2.0
151	140◄─►158	athene-70b-0725	1305	±6	19,796	NexusFlow	CC-BY-NC-4.0
152	143◄─►158	mistral-large-2411	1305	±4	28,455	Mistral	MRL
153	140◄─►158	magistral-medium-2506	1305	±6	11,995	Mistral	Proprietary
154	145◄─►158	mistral-small-3.1-24b-instruct-2503	1303	±4	34,136	Mistral	Apache 2.0
155	139◄─►163	gemma-3-4b-it	1302	±9	4,195	Google	Gemma
156	146◄─►158	qwen2.5-72b-instruct	1302	±4	39,632	Alibaba	Qwen
157	146◄─►166	llama-3.1-nemotron-70b-instruct	1298	±8	7,216	Nvidia	Llama 3.1
158	147◄─►169	hunyuan-large-vision	1295	±9	5,598	Tencent	Proprietary
159	154◄─►166	llama-3.1-70b-instruct	1294	±4	56,003	Meta	Llama 3.1 Community
160	155◄─►171	jamba-1.5-large	1289	±7	8,730	AI21 Labs	Jamba Open
161	157◄─►170	amazon-nova-pro-v1.0	1288	±4	25,218	Amazon	Proprietary
162	156◄─►172	reka-core-20240904	1288	±7	7,380	Reka AI	Proprietary
163	157◄─►169	gemma-2-27b-it	1288	±3	76,195	Google	Gemma license
164	157◄─►171	gpt-4-0314	1288	±5	54,754	OpenAI	Proprietary
165	155◄─►177	llama-3.1-nemotron-51b-instruct	1287	±10	3,777	Nvidia	Llama 3.1
166	155◄─►177	llama-3.1-tulu-3-70b	1286	±10	2,881	Ai2	Llama 3.1
167	159◄─►172	gemini-1.5-flash-001	1285	±4	63,418	Google	Proprietary
168	159◄─►176	claude-3-sonnet-20240229	1282	±4	110,173	Anthropic	Proprietary
169	159◄─►177	gemma-2-9b-it-simpo	1279	±7	10,108	Princeton	MIT
170	162◄─►177	nemotron-4-340b-instruct	1279	±5	19,913	Nvidia	NVIDIA Open Model
171	161◄─►178	command-r-plus-08-2024	1278	±7	9,931	Cohere	CC-BY-NC-4.0
172	166◄─►177	llama-3-70b-instruct	1277	±3	158,908	Meta	Llama 3 Community
173	166◄─►177	gpt-4-0613	1276	±4	89,612	OpenAI	Proprietary
174	164◄─►182	glm-4-0520	1274	±7	9,857	Zhipu AI	Proprietary
175	166◄─►181	mistral-small-24b-instruct-2501	1274	±6	14,830	Mistral	Apache 2.0
176	166◄─►182	reka-flash-20240904	1273	±7	7,583	Reka AI	Proprietary
177	167◄─►186	qwen2.5-coder-32b-instruct	1270	±8	5,452	Alibaba	Apache 2.0
178	173◄─►186	c4ai-aya-expanse-32b	1267	±5	27,362	Cohere	CC-BY-NC-4.0
179	174◄─►186	gemma-2-9b-it	1265	±4	54,954	Google	Gemma license
180	174◄─►188	deepseek-coder-v2	1265	±6	15,242	DeepSeek AI	DeepSeek License
181	174◄─►187	command-r-plus	1264	±4	78,401	Cohere	CC-BY-NC-4.0
182	175◄─►188	qwen2-72b-instruct	1263	±5	37,688	Alibaba	Qianwen LICENSE
183	177◄─►188	claude-3-haiku-20240307	1262	±4	118,626	Anthropic	Proprietary
184	177◄─►188	amazon-nova-lite-v1.0	1260	±5	19,760	Amazon	Proprietary
185	177◄─►188	gemini-1.5-flash-8b-001	1260	±4	35,914	Google	Proprietary
186	180◄─►188	phi-4	1255	±4	24,354	Microsoft	MIT
187	177◄─►195	olmo-2-0325-32b-instruct	1252	±11	3,377	Allen AI	Apache-2.0
188	181◄─►192	command-r-08-2024	1252	±7	10,229	Cohere	CC-BY-NC-4.0
189	187◄─►197	mistral-large-2402	1243	±5	63,404	Mistral	Proprietary
190	187◄─►197	amazon-nova-micro-v1.0	1242	±5	19,774	Amazon	Proprietary
191	187◄─►202	jamba-1.5-mini	1240	±7	8,918	AI21 Labs	Jamba Open
192	187◄─►205	ministral-8b-2410	1237	±9	4,833	Mistral	MRL
193	188◄─►205	gemini-pro-dev-api	1236	±7	18,454	Google	Proprietary
194	189◄─►204	qwen1.5-110b-chat	1235	±5	26,679	Alibaba	Qianwen LICENSE
195	189◄─►205	qwen1.5-72b-chat	1235	±5	39,689	Alibaba	Qianwen LICENSE
196	188◄─►206	reka-flash-21b-20240226-online	1235	±7	15,606	Reka AI	Proprietary
197	188◄─►207	hunyuan-standard-256k	1234	±12	2,761	Tencent	Proprietary
198	191◄─►206	mixtral-8x22b-instruct-v0.1	1231	±4	52,214	Mistral	Apache 2.0
199	191◄─►207	command-r	1229	±5	54,710	Cohere	CC-BY-NC-4.0
200	191◄─►207	reka-flash-21b-20240226	1228	±6	25,026	Reka AI	Proprietary
201	192◄─►208	gpt-3.5-turbo-0125	1225	±5	67,214	OpenAI	Proprietary
202	192◄─►208	mistral-medium	1225	±5	34,893	Mistral	Proprietary
203	196◄─►208	llama-3-8b-instruct	1224	±4	106,055	Meta	Llama 3 Community
204	192◄─►209	c4ai-aya-expanse-8b	1224	±7	9,922	Cohere	CC-BY-NC-4.0
205	191◄─►212	gemini-pro	1223	±12	6,418	Google	Proprietary
206	191◄─►212	llama-3.1-tulu-3-8b	1222	±11	2,943	Ai2	Llama 3.1
207	198◄─►213	zephyr-orpo-141b-A35b-v0.1	1215	±11	4,712	HuggingFace	Apache 2.0
208	204◄─►212	yi-1.5-34b-chat	1214	±5	24,417	01 AI	Apache-2.0
209	205◄─►212	llama-3.1-8b-instruct	1212	±4	50,234	Meta	Llama 3.1 Community
210	201◄─►218	granite-3.1-8b-instruct	1210	±11	3,142	IBM	Apache 2.0
211	205◄─►217	qwen1.5-32b-chat	1207	±6	22,068	Alibaba	Qianwen LICENSE
212	205◄─►220	gpt-3.5-turbo-1106	1203	±9	16,760	OpenAI	Proprietary
213	209◄─►220	phi-3-medium-4k-instruct	1199	±5	25,301	Microsoft	MIT
214	210◄─►220	mixtral-8x7b-instruct-v0.1	1199	±4	74,303	Mistral	Apache 2.0
215	210◄─►220	gemma-2-2b-it	1199	±4	46,901	Google	Gemma license
216	210◄─►225	dbrx-instruct-preview	1197	±6	32,760	Databricks	DBRX LICENSE
217	210◄─►229	qwen1.5-14b-chat	1194	±7	18,066	Alibaba	Qianwen LICENSE
218	211◄─►229	internlm2_5-20b-chat	1193	±7	10,038	InternLM	Other
219	212◄─►235	wizardlm-70b	1187	±9	8,270	Microsoft	Llama 2 Community
220	212◄─►236	deepseek-llm-67b-chat	1186	±12	4,950	DeepSeek AI	DeepSeek License
221	216◄─►233	yi-34b-chat	1185	±7	15,624	01 AI	Yi License
222	216◄─►235	granite-3.0-8b-instruct	1184	±9	6,727	IBM	Apache 2.0
223	216◄─►235	openchat-3.5-0106	1184	±8	12,712	OpenChat	Apache-2.0
224	216◄─►236	openchat-3.5	1184	±10	8,009	OpenChat	Apache-2.0
225	217◄─►235	snowflake-arctic-instruct	1182	±6	33,272	Snowflake	Apache 2.0
226	216◄─►238	granite-3.1-2b-instruct	1181	±11	3,235	IBM	Apache 2.0
227	217◄─►236	gemma-1.1-7b-it	1181	±6	24,327	Google	Gemma license
228	217◄─►238	tulu-2-dpo-70b	1180	±10	6,579	AllenAI/UW	AI2 ImpACT Low-risk
229	217◄─►240	openhermes-2.5-mistral-7b	1178	±10	5,026	NousResearch	Apache-2.0
230	219◄─►239	vicuna-33b	1175	±6	22,613	LMSYS	Non-commercial
231	219◄─►240	starling-lm-7b-beta	1174	±7	16,190	Nexusflow	Apache-2.0
232	219◄─►240	phi-3-small-8k-instruct	1173	±6	17,983	Microsoft	MIT
233	220◄─►240	llama-2-70b-chat	1173	±5	38,767	Meta	Llama 2 Community
234	220◄─►243	starling-lm-7b-alpha	1170	±8	10,267	UC Berkeley	CC-BY-NC-4.0
235	224◄─►244	llama-3.2-3b-instruct	1168	±8	8,043	Meta	Llama 3.2
236	219◄─►245	nous-hermes-2-mixtral-8x7b-dpo	1167	±12	3,792	NousResearch	Apache-2.0
237	227◄─►250	qwq-32b-preview	1160	±11	3,256	Alibaba	Apache 2.0
238	227◄─►253	llama2-70b-steerlm-chat	1158	±13	3,605	Nvidia	Llama 2 Community
239	234◄─►250	granite-3.0-2b-instruct	1157	±8	6,922	IBM	Apache 2.0
240	230◄─►254	solar-10.7b-instruct-v1.0	1155	±13	4,187	Upstage AI	CC-BY-NC-4.0
241	229◄─►258	dolphin-2.2.1-mistral-7b	1154	±15	1,685	Cognitive Computations	Apache-2.0
242	234◄─►256	mpt-30b-chat	1153	±12	2,606	MosaicML	CC-BY-NC-SA-4.0
243	236◄─►254	mistral-7b-instruct-v0.2	1152	±7	19,603	Mistral	Apache-2.0
244	235◄─►254	wizardlm-13b	1152	±9	7,122	Microsoft	Llama 2 Community
245	234◄─►261	falcon-180b-chat	1149	±17	1,312	TII	Falcon-180B TII License
246	237◄─►259	qwen1.5-7b-chat	1145	±10	4,782	Alibaba	Qianwen LICENSE
247	237◄─►258	phi-3-mini-4k-instruct-june-2024	1144	±6	12,415	Microsoft	MIT
248	237◄─►258	llama-2-13b-chat	1144	±7	19,357	Meta	Llama 2 Community
249	237◄─►259	vicuna-13b	1143	±7	19,539	LMSYS	Llama 2 Community
250	237◄─►261	qwen-14b-chat	1141	±11	5,004	Alibaba	Qianwen LICENSE
251	239◄─►261	palm-2	1139	±9	8,634	Google	Proprietary
252	239◄─►261	codellama-34b-instruct	1138	±9	7,417	Meta	Llama 2 Community
253	240◄─►261	gemma-7b-it	1136	±9	9,034	Google	Gemma license
254	243◄─►262	zephyr-7b-beta	1133	±9	11,220	HuggingFace	MIT
255	244◄─►262	phi-3-mini-128k-instruct	1133	±7	21,024	Microsoft	MIT
256	247◄─►262	phi-3-mini-4k-instruct	1130	±6	20,539	Microsoft	MIT
257	239◄─►266	zephyr-7b-alpha	1130	±16	1,803	HuggingFace	MIT
258	243◄─►265	guanaco-33b	1130	±12	2,955	UW	Non-commercial
259	249◄─►266	stripedhyena-nous-7b	1122	±11	5,214	Together AI	Apache 2.0
260	244◄─►267	codellama-70b-instruct	1120	±18	1,151	Meta	Llama 2 Community
261	249◄─►266	smollm2-1.7b-instruct	1120	±14	2,244	HuggingFace	Apache 2.0
262	254◄─►266	vicuna-7b	1117	±9	6,972	LMSYS	Llama 2 Community
263	257◄─►266	gemma-1.1-2b-it	1115	±8	11,035	Google	Gemma license
264	257◄─►266	llama-3.2-1b-instruct	1114	±8	8,166	Meta	Llama 3.2
265	257◄─►267	mistral-7b-instruct	1112	±9	9,042	Mistral	Apache 2.0
266	258◄─►267	llama-2-7b-chat	1110	±7	14,272	Meta	Llama 2 Community
267	267◄─►269	qwen1.5-4b-chat	1092	±9	7,662	Alibaba	Qianwen LICENSE
268	264◄─►271	gemma-2b-it	1092	±12	4,817	Google	Gemma license
269	267◄─►274	olmo-7b-instruct	1076	±11	6,412	Allen AI	Apache-2.0
270	268◄─►274	koala-13b	1073	±10	6,998	UC Berkeley	Non-commercial
271	269◄─►274	alpaca-13b	1069	±11	5,828	Stanford	Non-commercial
272	268◄─►275	gpt4all-13b-snoozy	1067	±15	1,773	Nomic AI	Non-commercial
273	269◄─►275	mpt-7b-chat	1064	±12	3,977	MosaicML	CC-BY-NC-SA-4.0
274	269◄─►275	chatglm3-6b	1058	±12	4,692	Tsinghua	Apache-2.0
275	272◄─►277	RWKV-4-Raven-14B	1044	±11	4,898	RWKV	Apache 2.0
276	275◄─►277	chatglm2-6b	1027	±14	2,683	Tsinghua	Apache-2.0
277	275◄─►277	oasst-pythia-12b	1024	±11	6,343	OpenAssistant	Apache 2.0
278	278◄─►281	chatglm-6b	998	±13	4,968	Tsinghua	Non-commercial
279	278◄─►281	fastchat-t5-3b	993	±12	4,270	LMSYS	Apache 2.0
280	278◄─►281	dolly-v2-12b	981	±14	3,471	Databricks	MIT
281	278◄─►282	llama-13b	973	±16	2,441	Meta	Non-commercial
282	281◄─►282	stablelm-tuned-alpha-7b	954	±13	3,325	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

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

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)