Text Arena

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

Last Updated

Dec 5, 2025

Total Votes

4,722,035

Total Models

280

/

Style Control

	Rank Spread (Upper-Lower)
1	1◄─►2	gemini-3-pro	1491	±7	13,801	Google	Proprietary
2	1◄─►3	grok-4.1-thinking	1481	±7	14,412	xAI	Proprietary
3	2◄─►6	claude-opus-4-5-20251101-thinking-32k	1471	±8	7,980	Anthropic	Proprietary
4	3◄─►6	grok-4.1	1463	±7	14,324	xAI	Proprietary
5	3◄─►6	claude-opus-4-5-20251101	1462	±8	8,733	Anthropic	Proprietary
6	3◄─►10	gpt-5.1-high	1457	±7	11,949	OpenAI	Proprietary
7	6◄─►11	gemini-2.5-pro	1451	±4	74,939	Google	Proprietary
8	6◄─►12	claude-sonnet-4-5-20250929-thinking-32k	1448	±5	25,961	Anthropic	Proprietary
9	6◄─►12	claude-opus-4-1-20250805-thinking-16k	1448	±4	41,812	Anthropic	Proprietary
10	6◄─►15	claude-sonnet-4-5-20250929	1445	±5	21,104	Anthropic	Proprietary
11	7◄─►17	gpt-4.5-preview-2025-02-27	1443	±6	14,644	OpenAI	Proprietary
12	8◄─►17	claude-opus-4-1-20250805	1441	±4	54,843	Anthropic	Proprietary
13	10◄─►17	chatgpt-4o-latest-20250326	1440	±3	61,196	OpenAI	Proprietary
14	10◄─►19	gpt-5-high	1437	±5	32,890	OpenAI	Proprietary
15	10◄─►23	gpt-5.1	1436	±7	12,836	OpenAI	Proprietary
16	11◄─►21	o3-2025-04-16	1434	±4	61,592	OpenAI	Proprietary
17	11◄─►24	qwen3-max-preview	1433	±5	28,132	Alibaba	Proprietary
18	14◄─►39	kimi-k2-thinking-turbo	1428	±6	13,647	Moonshot	Modified MIT
19	14◄─►39	grok-4-1-fast-reasoning	1427	±8	6,975	xAI	Proprietary
20	15◄─►39	glm-4.6	1426	±5	22,680	Z.ai	MIT
21	17◄─►39	gpt-5-chat	1425	±4	32,135	OpenAI	Proprietary
22	16◄─►39	qwen3-max-2025-09-23	1424	±6	9,256	Alibaba	Proprietary
23	18◄─►39	claude-opus-4-20250514-thinking-16k	1423	±4	37,874	Anthropic	Proprietary
24	16◄─►39	deepseek-v3.2-exp	1423	±7	11,969	DeepSeek AI	MIT
25	15◄─►45	mistral-large-3	1422	±10	4,393	Mistral	Apache 2.0
26	18◄─►39	qwen3-235b-a22b-instruct-2507	1421	±4	49,337	Alibaba	Apache 2.0
27	18◄─►42	deepseek-v3.2-exp-thinking	1421	±7	9,225	DeepSeek AI	MIT
28	18◄─►45	grok-4-fast-chat	1420	±8	7,059	xAI	Proprietary
29	18◄─►47	deepseek-v3.2-thinking	1418	±10	3,983	DeepSeek AI	MIT
30	18◄─►46	kimi-k2-0905-preview	1418	±7	11,841	Moonshot	Modified MIT
31	18◄─►45	deepseek-r1-0528	1418	±6	19,240	DeepSeek	MIT
32	18◄─►47	ernie-5.0-preview-1022	1417	±9	4,704	Baidu	Proprietary
33	18◄─►45	kimi-k2-0711-preview	1417	±5	28,667	Moonshot	Modified MIT
34	18◄─►46	deepseek-v3.1	1417	±6	15,255	DeepSeek	MIT
35	18◄─►46	deepseek-v3.1-thinking	1416	±7	11,985	DeepSeek	MIT
36	18◄─►50	deepseek-v3.1-terminus	1415	±10	3,746	DeepSeek AI	MIT
37	18◄─►47	qwen3-vl-235b-a22b-instruct	1415	±7	8,535	Alibaba	Apache 2.0
38	18◄─►52	deepseek-v3.1-terminus-thinking	1414	±10	3,522	DeepSeek AI	MIT
39	18◄─►56	deepseek-v3.2	1413	±10	4,475	DeepSeek AI	MIT
40	25◄─►47	claude-opus-4-20250514	1412	±4	45,676	Anthropic	Proprietary
41	26◄─►47	gpt-4.1-2025-04-14	1412	±4	52,587	OpenAI	Proprietary
42	26◄─►48	mistral-medium-2508	1411	±4	43,452	Mistral	Proprietary
43	27◄─►50	grok-3-preview-02-24	1410	±4	34,126	xAI	Proprietary
44	27◄─►52	grok-4-0709	1409	±4	42,573	xAI	Proprietary
45	27◄─►53	glm-4.5	1409	±5	24,825	Z.ai	MIT
46	31◄─►52	gemini-2.5-flash	1408	±3	74,323	Google	Proprietary
47	34◄─►58	gemini-2.5-flash-preview-09-2025	1405	±5	27,425	Google	Proprietary
48	39◄─►59	grok-4-fast-reasoning	1402	±5	18,884	xAI	Proprietary
49	40◄─►59	claude-haiku-4-5-20251001	1402	±5	24,230	Anthropic	Proprietary
50	42◄─►59	o1-2024-12-17	1401	±4	28,039	OpenAI	Proprietary
51	42◄─►61	qwen3-next-80b-a3b-instruct	1400	±5	23,118	Alibaba	Apache 2.0
52	40◄─►63	longcat-flash-chat	1400	±6	11,502	Meituan	MIT
53	46◄─►62	claude-sonnet-4-20250514-thinking-32k	1399	±4	36,214	Anthropic	Proprietary
54	45◄─►62	qwen3-235b-a22b-no-thinking	1399	±5	39,377	Alibaba	Apache 2.0
55	46◄─►66	qwen3-235b-a22b-thinking-2507	1397	±6	9,346	Alibaba	Apache 2.0
56	47◄─►66	deepseek-r1	1396	±5	18,718	DeepSeek	MIT
57	47◄─►68	qwen3-vl-235b-a22b-thinking	1394	±7	7,986	Alibaba	Apache 2.0
58	48◄─►67	gpt-5-mini-high	1393	±5	27,450	OpenAI	Proprietary
59	51◄─►67	deepseek-v3-0324	1392	±4	46,784	DeepSeek	MIT
60	46◄─►73	hunyuan-vision-1.5-thinking	1391	±12	2,212	Tencent	Proprietary
61	52◄─►68	o4-mini-2025-04-16	1391	±4	46,845	OpenAI	Proprietary
62	51◄─►70	mai-1-preview	1390	±5	18,180	Microsoft AI	Proprietary
63	54◄─►71	claude-sonnet-4-20250514	1389	±4	41,654	Anthropic	Proprietary
64	55◄─►72	o1-preview	1387	±5	31,505	OpenAI	Proprietary
65	55◄─►72	claude-3-7-sonnet-20250219-thinking-32k	1387	±4	39,911	Anthropic	Proprietary
66	57◄─►72	qwen3-coder-480b-a35b-instruct	1385	±5	23,154	Alibaba	Apache 2.0
67	54◄─►75	hunyuan-t1-20250711	1385	±9	4,819	Tencent	Proprietary
68	59◄─►74	mistral-medium-2505	1383	±5	34,527	Mistral	Proprietary
69	61◄─►74	qwen3-30b-a3b-instruct-2507	1382	±5	24,196	Alibaba	Apache 2.0
70	62◄─►75	gpt-4.1-mini-2025-04-14	1381	±4	40,494	OpenAI	Proprietary
71	61◄─►78	hunyuan-turbos-20250416	1380	±6	11,130	Tencent	Proprietary
72	63◄─►76	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1379	±4	27,328	Google	Proprietary
73	66◄─►79	gemini-2.5-flash-lite-preview-06-17-thinking	1375	±4	33,970	Google	Proprietary
74	67◄─►80	qwen3-235b-a22b	1374	±5	27,168	Alibaba	Apache 2.0
75	69◄─►80	qwen2.5-max	1373	±4	33,548	Alibaba	Proprietary
76	71◄─►80	claude-3-5-sonnet-20241022	1372	±3	89,848	Anthropic	Proprietary
77	71◄─►83	claude-3-7-sonnet-20250219	1371	±4	44,561	Anthropic	Proprietary
78	72◄─►83	glm-4.5-air	1370	±4	31,673	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	36,884	MiniMax	Apache 2.0
81	77◄─►86	gemma-3-27b-it	1365	±4	49,316	Google	Gemma
82	77◄─►90	o3-mini-high	1363	±5	18,735	OpenAI	Proprietary
83	77◄─►91	grok-3-mini-high	1362	±5	17,591	xAI	Proprietary
84	79◄─►93	gemini-2.0-flash-001	1360	±4	45,109	Google	Proprietary
85	79◄─►101	deepseek-v3	1357	±5	21,994	DeepSeek	DeepSeek
86	79◄─►101	grok-3-mini-beta	1357	±5	23,794	xAI	Proprietary
87	82◄─►106	mistral-small-2506	1355	±5	18,329	Mistral	Apache 2.0
88	84◄─►106	gemini-2.0-flash-lite-preview-02-05	1353	±4	25,215	Google	Proprietary
89	84◄─►107	gpt-oss-120b	1353	±4	31,271	OpenAI	Apache 2.0
90	85◄─►106	command-a-03-2025	1352	±3	57,830	Cohere	CC-BY-NC-4.0
91	82◄─►109	glm-4.5v	1352	±8	4,978	Z.ai	MIT
92	85◄─►107	gemini-1.5-pro-002	1351	±3	56,012	Google	Proprietary
93	82◄─►109	amazon-nova-experimental-chat-10-20	1350	±8	5,939	Amazon	Proprietary
94	87◄─►109	o3-mini	1348	±3	58,812	OpenAI	Proprietary
95	82◄─►118	hunyuan-turbos-20250226	1346	±12	2,250	Tencent	Proprietary
96	85◄─►111	ling-flash-2.0	1346	±7	7,158	Ant Group	MIT
97	85◄─►115	minimax-m2	1346	±8	7,123	MiniMax	Apache 2.0
98	85◄─►113	step-3	1346	±7	6,642	StepFun	Apache 2.0
99	83◄─►119	llama-3.1-nemotron-ultra-253b-v1	1346	±12	2,573	Nvidia	Nvidia Open Model
100	85◄─►119	amazon-nova-experimental-chat-10-09	1345	±11	2,892	Amazon	Proprietary
101	90◄─►109	gpt-4o-2024-05-13	1345	±3	113,568	OpenAI	Proprietary
102	85◄─►118	qwen3-32b	1345	±9	3,943	Alibaba	Apache 2.0
103	85◄─►118	qwen-plus-0125	1345	±8	5,861	Alibaba	Proprietary
104	87◄─►118	glm-4-plus-0111	1343	±8	5,806	Zhipu	Proprietary
105	92◄─►111	claude-3-5-sonnet-20240620	1342	±3	82,864	Anthropic	Proprietary
106	87◄─►121	gemma-3-12b-it	1340	±9	3,866	Google	Gemma
107	87◄─►123	nvidia-llama-3.3-nemotron-super-49b-v1.5	1340	±10	3,492	Nvidia	Nvidia Open
108	87◄─►124	hunyuan-turbo-0110	1339	±11	2,322	Tencent	Proprietary
109	92◄─►120	gpt-5-nano-high	1339	±7	8,387	OpenAI	Proprietary
110	96◄─►120	llama-3.1-405b-instruct-bf16	1335	±4	41,932	Meta	Llama 3.1 Community
111	97◄─►120	o1-mini	1335	±4	52,301	OpenAI	Proprietary
112	98◄─►123	gpt-4o-2024-08-06	1334	±4	45,787	OpenAI	Proprietary
113	100◄─►122	grok-2-2024-08-13	1334	±4	63,725	xAI	Proprietary
114	99◄─►123	qwq-32b	1334	±4	26,273	Alibaba	Apache 2.0
115	98◄─►123	gemini-advanced-0514	1334	±5	50,654	Google	Proprietary
116	100◄─►123	llama-3.1-405b-instruct-fp8	1333	±3	60,272	Meta	Llama 3.1 Community
117	96◄─►134	step-2-16k-exp-202412	1332	±9	4,895	StepFun	Proprietary
118	106◄─►135	yi-lightning	1328	±5	27,624	01 AI	Proprietary
119	109◄─►135	llama-4-maverick-17b-128e-instruct	1327	±4	41,202	Meta	Llama 4
120	110◄─►138	qwen3-30b-a3b	1326	±5	27,492	Alibaba	Apache 2.0
121	100◄─►146	llama-3.3-nemotron-49b-super-v1	1326	±12	2,243	Nvidia	Nvidia
122	104◄─►145	hunyuan-large-2025-02-10	1325	±10	3,760	Tencent	Proprietary
123	116◄─►140	gpt-4-turbo-2024-04-09	1324	±4	98,965	OpenAI	Proprietary
124	117◄─►141	claude-3-5-haiku-20241022	1322	±3	71,378	Anthropic	Proprietary
125	117◄─►141	llama-4-scout-17b-16e-instruct	1322	±5	31,199	Meta	Llama
126	110◄─►146	deepseek-v2.5-1210	1322	±8	6,877	DeepSeek	DeepSeek
127	117◄─►141	claude-3-opus-20240229	1322	±3	196,368	Anthropic	Proprietary
128	117◄─►141	gemini-1.5-pro-001	1322	±4	79,769	Google	Proprietary
129	116◄─►146	gpt-4.1-nano-2025-04-14	1321	±8	6,143	OpenAI	Proprietary
130	117◄─►146	ring-flash-2.0	1320	±7	7,282	Ant Group	MIT
131	117◄─►146	step-1o-turbo-202506	1320	±7	9,665	StepFun	Proprietary
132	120◄─►145	llama-3.3-70b-instruct	1319	±3	56,011	Meta	Llama-3.3
133	118◄─►146	gemma-3n-e4b-it	1318	±5	23,471	Google	Gemma
134	120◄─►146	glm-4-plus	1318	±5	26,342	Zhipu AI	Proprietary
135	117◄─►147	gpt-oss-20b	1318	±6	10,849	OpenAI	Apache 2.0
136	120◄─►147	qwen-max-0919	1317	±6	16,598	Alibaba	Qwen
137	122◄─►146	gpt-4o-mini-2024-07-18	1316	±3	69,291	OpenAI	Proprietary
138	121◄─►152	qwen2.5-plus-1127	1314	±6	10,252	Alibaba	Proprietary
139	126◄─►151	gpt-4-1106-preview	1313	±4	101,117	OpenAI	Proprietary
140	126◄─►151	mistral-large-2407	1313	±4	45,968	Mistral	Mistral Research
141	126◄─►151	gpt-4-0125-preview	1313	±4	94,534	OpenAI	Proprietary
142	126◄─►152	athene-v2-chat	1313	±4	24,880	NexusFlow	NexusFlow
143	117◄─►156	olmo-3-32b-think	1312	±12	2,551	Allen AI	Apache 2.0
144	117◄─►156	mercury	1311	±14	1,967	Inception AI	Proprietary
145	121◄─►156	hunyuan-standard-2025-02-10	1310	±10	3,920	Tencent	Proprietary
146	128◄─►153	gemini-1.5-flash-002	1310	±4	35,180	Google	Proprietary
147	138◄─►156	grok-2-mini-2024-08-13	1307	±4	52,789	xAI	Proprietary
148	138◄─►156	deepseek-v2.5	1306	±5	24,839	DeepSeek	DeepSeek
149	138◄─►156	magistral-medium-2506	1305	±6	11,999	Mistral	Proprietary
150	141◄─►156	mistral-large-2411	1305	±4	28,455	Mistral	MRL
151	138◄─►156	athene-70b-0725	1305	±6	19,796	NexusFlow	CC-BY-NC-4.0
152	142◄─►156	mistral-small-3.1-24b-instruct-2503	1303	±4	34,140	Mistral	Apache 2.0
153	136◄─►161	gemma-3-4b-it	1303	±9	4,195	Google	Gemma
154	144◄─►156	qwen2.5-72b-instruct	1302	±4	39,632	Alibaba	Qwen
155	144◄─►164	llama-3.1-nemotron-70b-instruct	1297	±8	7,216	Nvidia	Llama 3.1
156	144◄─►165	hunyuan-large-vision	1295	±9	5,599	Tencent	Proprietary
157	154◄─►164	llama-3.1-70b-instruct	1293	±4	56,003	Meta	Llama 3.1 Community
158	155◄─►167	amazon-nova-pro-v1.0	1288	±4	25,218	Amazon	Proprietary
159	154◄─►169	jamba-1.5-large	1288	±7	8,730	AI21 Labs	Jamba Open
160	155◄─►167	gemma-2-27b-it	1287	±3	76,195	Google	Gemma license
161	154◄─►169	reka-core-20240904	1287	±7	7,380	Reka AI	Proprietary
162	155◄─►169	gpt-4-0314	1286	±5	54,754	OpenAI	Proprietary
163	154◄─►175	llama-3.1-nemotron-51b-instruct	1286	±10	3,777	Nvidia	Llama 3.1
164	154◄─►175	llama-3.1-tulu-3-70b	1286	±10	2,881	Ai2	Llama 3.1
165	157◄─►170	gemini-1.5-flash-001	1284	±4	63,418	Google	Proprietary
166	158◄─►174	claude-3-sonnet-20240229	1281	±4	110,173	Anthropic	Proprietary
167	158◄─►175	gemma-2-9b-it-simpo	1278	±7	10,108	Princeton	MIT
168	160◄─►175	nemotron-4-340b-instruct	1278	±5	19,913	Nvidia	NVIDIA Open Model
169	160◄─►176	command-r-plus-08-2024	1277	±7	9,931	Cohere	CC-BY-NC-4.0
170	164◄─►175	llama-3-70b-instruct	1276	±3	158,908	Meta	Llama 3 Community
171	164◄─►176	gpt-4-0613	1275	±4	89,612	OpenAI	Proprietary
172	164◄─►178	mistral-small-24b-instruct-2501	1274	±6	14,830	Mistral	Apache 2.0
173	163◄─►180	glm-4-0520	1273	±7	9,857	Zhipu AI	Proprietary
174	164◄─►180	reka-flash-20240904	1273	±7	7,583	Reka AI	Proprietary
175	165◄─►184	qwen2.5-coder-32b-instruct	1269	±8	5,452	Alibaba	Apache 2.0
176	170◄─►184	c4ai-aya-expanse-32b	1267	±5	27,362	Cohere	CC-BY-NC-4.0
177	172◄─►184	gemma-2-9b-it	1264	±4	54,954	Google	Gemma license
178	172◄─►186	deepseek-coder-v2	1263	±6	15,242	DeepSeek AI	DeepSeek License
179	173◄─►185	command-r-plus	1263	±4	78,401	Cohere	CC-BY-NC-4.0
180	173◄─►186	qwen2-72b-instruct	1262	±5	37,688	Alibaba	Qianwen LICENSE
181	175◄─►186	claude-3-haiku-20240307	1261	±4	118,626	Anthropic	Proprietary
182	175◄─►186	amazon-nova-lite-v1.0	1260	±5	19,760	Amazon	Proprietary
183	175◄─►186	gemini-1.5-flash-8b-001	1259	±4	35,914	Google	Proprietary
184	178◄─►186	phi-4	1255	±4	24,354	Microsoft	MIT
185	175◄─►191	olmo-2-0325-32b-instruct	1252	±11	3,377	Allen AI	Apache-2.0
186	179◄─►190	command-r-08-2024	1251	±7	10,229	Cohere	CC-BY-NC-4.0
187	185◄─►195	mistral-large-2402	1242	±5	63,404	Mistral	Proprietary
188	185◄─►195	amazon-nova-micro-v1.0	1241	±5	19,774	Amazon	Proprietary
189	185◄─►200	jamba-1.5-mini	1239	±7	8,918	AI21 Labs	Jamba Open
190	185◄─►203	ministral-8b-2410	1237	±9	4,833	Mistral	MRL
191	187◄─►202	qwen1.5-110b-chat	1234	±5	26,679	Alibaba	Qianwen LICENSE
192	187◄─►203	gemini-pro-dev-api	1234	±7	18,454	Google	Proprietary
193	187◄─►203	qwen1.5-72b-chat	1234	±5	39,689	Alibaba	Qianwen LICENSE
194	187◄─►204	reka-flash-21b-20240226-online	1233	±7	15,606	Reka AI	Proprietary
195	186◄─►205	hunyuan-standard-256k	1233	±12	2,761	Tencent	Proprietary
196	189◄─►204	mixtral-8x22b-instruct-v0.1	1230	±4	52,214	Mistral	Apache 2.0
197	189◄─►205	command-r	1228	±5	54,710	Cohere	CC-BY-NC-4.0
198	189◄─►206	reka-flash-21b-20240226	1227	±6	25,026	Reka AI	Proprietary
199	191◄─►206	gpt-3.5-turbo-0125	1224	±5	67,214	OpenAI	Proprietary
200	190◄─►207	mistral-medium	1224	±5	34,893	Mistral	Proprietary
201	190◄─►207	c4ai-aya-expanse-8b	1223	±7	9,922	Cohere	CC-BY-NC-4.0
202	194◄─►206	llama-3-8b-instruct	1223	±4	106,055	Meta	Llama 3 Community
203	189◄─►209	llama-3.1-tulu-3-8b	1222	±11	2,943	Ai2	Llama 3.1
204	189◄─►210	gemini-pro	1222	±12	6,418	Google	Proprietary
205	196◄─►211	zephyr-orpo-141b-A35b-v0.1	1214	±11	4,712	HuggingFace	Apache 2.0
206	201◄─►210	yi-1.5-34b-chat	1213	±5	24,417	01 AI	Apache-2.0
207	203◄─►210	llama-3.1-8b-instruct	1211	±4	50,234	Meta	Llama 3.1 Community
208	198◄─►216	granite-3.1-8b-instruct	1210	±11	3,142	IBM	Apache 2.0
209	203◄─►216	qwen1.5-32b-chat	1205	±6	22,068	Alibaba	Qianwen LICENSE
210	204◄─►218	gpt-3.5-turbo-1106	1202	±9	16,760	OpenAI	Proprietary
211	207◄─►218	phi-3-medium-4k-instruct	1198	±5	25,301	Microsoft	MIT
212	208◄─►218	gemma-2-2b-it	1198	±4	46,901	Google	Gemma license
213	208◄─►218	mixtral-8x7b-instruct-v0.1	1198	±4	74,303	Mistral	Apache 2.0
214	208◄─►223	dbrx-instruct-preview	1196	±6	32,760	Databricks	DBRX LICENSE
215	208◄─►226	qwen1.5-14b-chat	1193	±7	18,066	Alibaba	Qianwen LICENSE
216	208◄─►227	internlm2_5-20b-chat	1192	±7	10,038	InternLM	Other
217	210◄─►233	wizardlm-70b	1185	±9	8,270	Microsoft	Llama 2 Community
218	210◄─►234	deepseek-llm-67b-chat	1184	±12	4,950	DeepSeek AI	DeepSeek License
219	214◄─►231	yi-34b-chat	1184	±7	15,624	01 AI	Yi License
220	214◄─►233	granite-3.0-8b-instruct	1184	±9	6,727	IBM	Apache 2.0
221	214◄─►233	openchat-3.5-0106	1183	±8	12,712	OpenChat	Apache-2.0
222	214◄─►234	openchat-3.5	1182	±10	8,009	OpenChat	Apache-2.0
223	214◄─►235	granite-3.1-2b-instruct	1181	±11	3,235	IBM	Apache 2.0
224	215◄─►233	snowflake-arctic-instruct	1180	±6	33,272	Snowflake	Apache 2.0
225	216◄─►234	gemma-1.1-7b-it	1180	±6	24,327	Google	Gemma license
226	215◄─►236	tulu-2-dpo-70b	1179	±10	6,579	AllenAI/UW	AI2 ImpACT Low-risk
227	215◄─►238	openhermes-2.5-mistral-7b	1176	±10	5,026	NousResearch	Apache-2.0
228	217◄─►237	vicuna-33b	1174	±6	22,613	LMSYS	Non-commercial
229	217◄─►238	starling-lm-7b-beta	1173	±7	16,190	Nexusflow	Apache-2.0
230	217◄─►238	phi-3-small-8k-instruct	1172	±6	17,983	Microsoft	MIT
231	218◄─►238	llama-2-70b-chat	1172	±5	38,767	Meta	Llama 2 Community
232	218◄─►241	starling-lm-7b-alpha	1168	±8	10,267	UC Berkeley	CC-BY-NC-4.0
233	222◄─►242	llama-3.2-3b-instruct	1167	±8	8,043	Meta	Llama 3.2
234	217◄─►243	nous-hermes-2-mixtral-8x7b-dpo	1166	±12	3,792	NousResearch	Apache-2.0
235	225◄─►248	qwq-32b-preview	1160	±11	3,256	Alibaba	Apache 2.0
236	226◄─►250	llama2-70b-steerlm-chat	1157	±13	3,605	Nvidia	Llama 2 Community
237	232◄─►247	granite-3.0-2b-instruct	1157	±8	6,922	IBM	Apache 2.0
238	228◄─►252	solar-10.7b-instruct-v1.0	1154	±13	4,187	Upstage AI	CC-BY-NC-4.0
239	227◄─►256	dolphin-2.2.1-mistral-7b	1152	±15	1,685	Cognitive Computations	Apache-2.0
240	234◄─►251	mistral-7b-instruct-v0.2	1151	±7	19,603	Mistral	Apache-2.0
241	232◄─►255	mpt-30b-chat	1151	±12	2,606	MosaicML	CC-BY-NC-SA-4.0
242	233◄─►252	wizardlm-13b	1150	±9	7,122	Microsoft	Llama 2 Community
243	232◄─►259	falcon-180b-chat	1147	±17	1,312	TII	Falcon-180B TII License
244	235◄─►257	qwen1.5-7b-chat	1144	±10	4,782	Alibaba	Qianwen LICENSE
245	235◄─►256	phi-3-mini-4k-instruct-june-2024	1143	±6	12,415	Microsoft	MIT
246	235◄─►256	llama-2-13b-chat	1143	±7	19,357	Meta	Llama 2 Community
247	236◄─►257	vicuna-13b	1142	±7	19,539	LMSYS	Llama 2 Community
248	235◄─►259	qwen-14b-chat	1139	±11	5,004	Alibaba	Qianwen LICENSE
249	237◄─►259	codellama-34b-instruct	1137	±9	7,417	Meta	Llama 2 Community
250	237◄─►259	palm-2	1137	±9	8,634	Google	Proprietary
251	238◄─►259	gemma-7b-it	1135	±9	9,034	Google	Gemma license
252	241◄─►260	zephyr-7b-beta	1132	±9	11,220	HuggingFace	MIT
253	241◄─►260	phi-3-mini-128k-instruct	1131	±7	21,024	Microsoft	MIT
254	245◄─►260	phi-3-mini-4k-instruct	1129	±6	20,539	Microsoft	MIT
255	239◄─►264	zephyr-7b-alpha	1129	±16	1,803	HuggingFace	MIT
256	241◄─►264	guanaco-33b	1128	±12	2,955	UW	Non-commercial
257	247◄─►264	stripedhyena-nous-7b	1121	±11	5,214	Together AI	Apache 2.0
258	242◄─►265	codellama-70b-instruct	1119	±18	1,151	Meta	Llama 2 Community
259	247◄─►264	smollm2-1.7b-instruct	1118	±14	2,244	HuggingFace	Apache 2.0
260	252◄─►264	vicuna-7b	1115	±9	6,972	LMSYS	Llama 2 Community
261	255◄─►264	gemma-1.1-2b-it	1114	±8	11,035	Google	Gemma license
262	255◄─►264	llama-3.2-1b-instruct	1113	±8	8,166	Meta	Llama 3.2
263	255◄─►265	mistral-7b-instruct	1111	±9	9,042	Mistral	Apache 2.0
264	255◄─►265	llama-2-7b-chat	1109	±7	14,272	Meta	Llama 2 Community
265	262◄─►269	gemma-2b-it	1091	±12	4,817	Google	Gemma license
266	265◄─►267	qwen1.5-4b-chat	1091	±9	7,662	Alibaba	Qianwen LICENSE
267	265◄─►272	olmo-7b-instruct	1075	±11	6,412	Allen AI	Apache-2.0
268	266◄─►272	koala-13b	1070	±10	6,998	UC Berkeley	Non-commercial
269	267◄─►272	alpaca-13b	1066	±11	5,828	Stanford	Non-commercial
270	266◄─►273	gpt4all-13b-snoozy	1065	±15	1,773	Nomic AI	Non-commercial
271	267◄─►273	mpt-7b-chat	1061	±12	3,977	MosaicML	CC-BY-NC-SA-4.0
272	267◄─►273	chatglm3-6b	1057	±12	4,692	Tsinghua	Apache-2.0
273	270◄─►275	RWKV-4-Raven-14B	1041	±11	4,898	RWKV	Apache 2.0
274	273◄─►275	chatglm2-6b	1026	±14	2,683	Tsinghua	Apache-2.0
275	273◄─►275	oasst-pythia-12b	1022	±11	6,343	OpenAssistant	Apache 2.0
276	276◄─►279	chatglm-6b	996	±13	4,968	Tsinghua	Non-commercial
277	276◄─►279	fastchat-t5-3b	991	±12	4,270	LMSYS	Apache 2.0
278	276◄─►280	dolly-v2-12b	978	±14	3,471	Databricks	MIT
279	276◄─►280	llama-13b	971	±16	2,441	Meta	Non-commercial
280	278◄─►280	stablelm-tuned-alpha-7b	952	±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)