Text Arena

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

Last Updated

Dec 23, 2025

Total Votes

1,408,596

Total Models

291

/

Style Control

	Rank Spread
1	1◄─►5	claude-opus-4-5-20251101-thinking-32k	1519	±10	4,689	Anthropic	Proprietary
2	1◄─►5	gemini-3-pro	1515	±8	7,020	Google	Proprietary
3	1◄─►9	grok-4.1-thinking	1508	±8	7,214	xAI	Proprietary
4	1◄─►11	claude-opus-4-5-20251101	1507	±10	4,939	Anthropic	Proprietary
5	1◄─►12	gemini-3-flash	1502	±14	1,793	Google	Proprietary
6	3◄─►12	claude-sonnet-4-5-20250929-thinking-32k	1500	±6	11,263	Anthropic	Proprietary
7	3◄─►15	gemini-3-flash (thinking-minimal)	1493	±13	1,966	Google	Proprietary
8	5◄─►13	claude-opus-4-1-20250805-thinking-16k	1491	±6	16,228	Anthropic	Proprietary
9	4◄─►14	grok-4.1	1491	±8	7,663	xAI	Proprietary
10	4◄─►14	claude-sonnet-4-5-20250929	1491	±7	9,668	Anthropic	Proprietary
11	3◄─►27	ernie-5.0-preview-1203	1484	±18	1,048	Baidu	Proprietary
12	3◄─►37	gpt-5.2	1483	±21	835	OpenAI	Proprietary
13	8◄─►18	claude-opus-4-1-20250805	1480	±5	20,634	Anthropic	Proprietary
14	7◄─►37	gpt-5.2-high	1474	±13	2,054	OpenAI	Proprietary
15	10◄─►32	gpt-5.1-high	1473	±9	6,083	OpenAI	Proprietary
16	11◄─►35	qwen3-max-preview	1470	±7	9,513	Alibaba	Proprietary
17	11◄─►44	ernie-5.0-preview-1103	1467	±12	2,498	Baidu	Proprietary
18	11◄─►41	kimi-k2-thinking-turbo	1467	±8	6,666	Moonshot	Modified MIT
19	12◄─►41	claude-opus-4-20250514-thinking-16k	1465	±6	12,377	Anthropic	Proprietary
20	12◄─►44	gpt-5.1	1465	±8	6,695	OpenAI	Proprietary
21	12◄─►45	qwen3-max-2025-09-23	1464	±10	3,386	Alibaba	Proprietary
22	12◄─►41	gemini-2.5-pro	1463	±5	27,162	Google	Proprietary
23	12◄─►43	qwen3-235b-a22b-instruct-2507	1462	±5	18,862	Alibaba	Apache 2.0
24	12◄─►43	chatgpt-4o-latest-20250326	1462	±5	21,810	OpenAI	Proprietary
25	12◄─►49	deepseek-v3.2-exp-thinking	1458	±10	3,205	DeepSeek AI	MIT
26	12◄─►55	grok-4-fast-chat	1457	±12	2,296	xAI	Proprietary
27	12◄─►51	gpt-4.5-preview-2025-02-27	1457	±10	3,370	OpenAI	Proprietary
28	15◄─►47	claude-haiku-4-5-20251001	1457	±7	10,702	Anthropic	Proprietary
29	13◄─►53	deepseek-v3.2-exp	1456	±10	4,171	DeepSeek AI	MIT
30	13◄─►53	grok-4-1-fast-reasoning	1456	±9	4,630	xAI	Proprietary
31	13◄─►55	qwen3-vl-235b-a22b-instruct	1455	±10	3,420	Alibaba	Apache 2.0
32	14◄─►50	deepseek-r1-0528	1455	±8	5,760	DeepSeek	MIT
33	14◄─►55	kimi-k2-0905-preview	1455	±10	3,936	Moonshot	Modified MIT
34	13◄─►55	mistral-large-3	1454	±10	3,472	Mistral	Apache 2.0
35	17◄─►50	gpt-5-high	1454	±7	11,085	OpenAI	Proprietary
36	13◄─►56	deepseek-v3.2-thinking	1454	±11	3,062	DeepSeek AI	MIT
37	14◄─►55	deepseek-v3.2	1454	±10	3,919	DeepSeek AI	MIT
38	17◄─►50	glm-4.6	1454	±7	9,980	Z.ai	MIT
39	17◄─►53	kimi-k2-0711-preview	1453	±7	9,355	Moonshot	Modified MIT
40	20◄─►49	o3-2025-04-16	1453	±5	19,849	OpenAI	Proprietary
41	15◄─►55	longcat-flash-chat	1453	±10	3,915	Meituan	MIT
42	20◄─►54	gpt-5-chat	1452	±6	10,796	OpenAI	Proprietary
43	22◄─►60	deepseek-v3.1-thinking	1447	±10	3,583	DeepSeek	MIT
44	25◄─►60	glm-4.5	1443	±7	8,324	Z.ai	MIT
45	25◄─►61	deepseek-v3.1	1443	±9	4,837	DeepSeek	MIT
46	26◄─►60	qwen3-next-80b-a3b-instruct	1443	±7	8,110	Alibaba	Apache 2.0
47	26◄─►60	claude-sonnet-4-20250514-thinking-32k	1443	±6	11,976	Anthropic	Proprietary
48	17◄─►70	deepseek-v3.1-terminus-thinking	1442	±17	1,189	DeepSeek AI	MIT
49	28◄─►60	mistral-medium-2508	1442	±6	16,982	Mistral	Proprietary
50	31◄─►60	gpt-4.1-2025-04-14	1441	±5	16,993	OpenAI	Proprietary
51	32◄─►61	claude-opus-4-20250514	1441	±6	15,019	Anthropic	Proprietary
52	42◄─►63	qwen3-235b-a22b-no-thinking	1437	±6	12,918	Alibaba	Apache 2.0
53	35◄─►71	qwen3-vl-235b-a22b-thinking	1435	±11	2,840	Alibaba	Apache 2.0
54	24◄─►85	mimo-v2-flash (non-thinking)	1434	±19	890	Xiaomi	MIT
55	43◄─►68	qwen3-coder-480b-a35b-instruct	1434	±7	8,078	Alibaba	Apache 2.0
56	43◄─►70	grok-3-preview-02-24	1432	±7	9,493	xAI	Proprietary
57	43◄─►79	qwen3-235b-a22b-thinking-2507	1431	±11	3,040	Alibaba	Apache 2.0
58	43◄─►79	deepseek-r1	1429	±9	3,963	DeepSeek	MIT
59	36◄─►86	deepseek-v3.1-terminus	1429	±16	1,313	DeepSeek AI	MIT
60	49◄─►77	qwen3-30b-a3b-instruct-2507	1428	±7	8,214	Alibaba	Apache 2.0
61	51◄─►79	claude-sonnet-4-20250514	1427	±6	13,929	Anthropic	Proprietary
62	32◄─►92	hunyuan-vision-1.5-thinking	1426	±21	773	Tencent	Proprietary
63	51◄─►85	grok-4-fast-reasoning	1424	±8	6,770	xAI	Proprietary
64	52◄─►85	grok-4-0709	1422	±6	14,500	xAI	Proprietary
65	52◄─►85	o1-2024-12-17	1422	±8	6,597	OpenAI	Proprietary
66	52◄─►85	deepseek-v3-0324	1421	±6	14,775	DeepSeek	MIT
67	53◄─►85	o4-mini-2025-04-16	1421	±6	15,218	OpenAI	Proprietary
68	52◄─►85	gemini-2.5-flash-preview-09-2025	1421	±6	11,924	Google	Proprietary
69	56◄─►85	gemini-2.5-flash	1419	±5	26,653	Google	Proprietary
70	53◄─►86	mistral-medium-2505	1419	±7	10,941	Mistral	Proprietary
71	52◄─►88	mai-1-preview	1419	±8	5,692	Microsoft AI	Proprietary
72	55◄─►86	gpt-4.1-mini-2025-04-14	1418	±6	12,954	OpenAI	Proprietary
73	56◄─►88	claude-3-7-sonnet-20250219-thinking-32k	1417	±6	11,846	Anthropic	Proprietary
74	56◄─►91	qwen3-235b-a22b	1416	±7	8,211	Alibaba	Apache 2.0
75	56◄─►91	gpt-5-mini-high	1415	±7	9,039	OpenAI	Proprietary
76	60◄─►91	glm-4.5-air	1413	±6	10,704	Z.ai	MIT
77	56◄─►96	hunyuan-turbos-20250416	1412	±11	3,147	Tencent	Proprietary
78	60◄─►96	qwen3-next-80b-a3b-thinking	1410	±9	4,854	Alibaba	Apache 2.0
79	60◄─►96	o3-mini-high	1409	±9	4,348	OpenAI	Proprietary
80	57◄─►104	hunyuan-t1-20250711	1407	±15	1,588	Tencent	Proprietary
81	71◄─►94	claude-3-5-sonnet-20241022	1407	±4	25,508	Anthropic	Proprietary
82	68◄─►97	o1-preview	1406	±8	8,220	OpenAI	Proprietary
83	71◄─►96	claude-3-7-sonnet-20250219	1405	±6	13,239	Anthropic	Proprietary
84	60◄─►103	ling-flash-2.0	1405	±12	2,567	Ant Group	MIT
85	56◄─►106	amazon-nova-experimental-chat-11-10	1404	±17	1,150	Amazon	Proprietary
86	73◄─►97	minimax-m1	1404	±6	11,831	MiniMax	Apache 2.0
87	60◄─►106	intellect-3	1403	±14	1,753	Prime Intellect	MIT
88	76◄─►104	mistral-small-2506	1399	±8	6,096	Mistral	Apache 2.0
89	77◄─►104	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1398	±6	11,895	Google	Proprietary
90	60◄─►116	qwen3-32b	1397	±19	842	Alibaba	Apache 2.0
91	73◄─►112	glm-4.5v	1396	±14	1,757	Z.ai	MIT
92	57◄─►123	hunyuan-turbos-20250226	1396	±25	474	Tencent	Proprietary
93	78◄─►106	qwen2.5-max	1395	±7	8,814	Alibaba	Proprietary
94	77◄─►111	amazon-nova-experimental-chat-10-20	1393	±10	3,954	Amazon	Proprietary
95	78◄─►118	step-3	1389	±13	2,187	StepFun	Apache 2.0
96	84◄─►111	o3-mini	1389	±5	17,074	OpenAI	Proprietary
97	73◄─►132	llama-3.1-nemotron-ultra-253b-v1	1387	±24	589	Nvidia	Nvidia Open Model
98	85◄─►114	gemini-2.5-flash-lite-preview-06-17-thinking	1386	±6	11,110	Google	Proprietary
99	84◄─►122	nova-2-lite	1385	±11	3,426	Amazon	Proprietary
100	88◄─►116	gpt-oss-120b	1384	±6	10,542	OpenAI	Apache 2.0
101	88◄─►122	deepseek-v3	1383	±8	5,188	DeepSeek	DeepSeek
102	84◄─►124	minimax-m2	1382	±12	2,503	MiniMax	Apache 2.0
103	82◄─►132	amazon-nova-experimental-chat-10-09	1381	±18	1,003	Amazon	Proprietary
104	84◄─►130	nvidia-llama-3.3-nemotron-super-49b-v1.5	1381	±17	1,214	Nvidia	Nvidia Open
105	91◄─►122	command-a-03-2025	1379	±5	18,374	Cohere	CC-BY-NC-4.0
106	84◄─►132	qwen-plus-0125	1379	±15	1,421	Alibaba	Proprietary
107	93◄─►122	gemma-3-27b-it	1377	±6	14,794	Google	Gemma
108	91◄─►124	grok-3-mini-high	1377	±8	5,988	xAI	Proprietary
109	91◄─►124	grok-3-mini-beta	1377	±7	7,721	xAI	Proprietary
110	91◄─►124	qwq-32b	1377	±7	7,593	Alibaba	Apache 2.0
111	91◄─►132	ring-flash-2.0	1375	±12	2,589	Ant Group	MIT
112	94◄─►127	o1-mini	1373	±6	13,223	OpenAI	Proprietary
113	84◄─►147	hunyuan-turbo-0110	1373	±23	523	Tencent	Proprietary
114	95◄─►127	claude-3-5-sonnet-20240620	1372	±6	22,242	Anthropic	Proprietary
115	97◄─►132	qwen3-30b-a3b	1370	±7	8,446	Alibaba	Apache 2.0
116	94◄─►138	gpt-5-nano-high	1370	±11	2,877	OpenAI	Proprietary
117	98◄─►132	gemini-2.0-flash-001	1370	±6	12,477	Google	Proprietary
118	107◄─►138	claude-3-5-haiku-20241022	1364	±5	20,204	Anthropic	Proprietary
119	95◄─►147	nvidia-nemotron-3-nano-30b-a3b-bf16	1363	±14	1,735	Nvidia	NVIDIA Open Model
120	97◄─►147	deepseek-v2.5-1210	1363	±14	1,689	DeepSeek	DeepSeek
121	107◄─►139	llama-3.1-405b-instruct-bf16	1362	±6	10,316	Meta	Llama 3.1 Community
122	98◄─►152	gpt-4.1-nano-2025-04-14	1361	±15	1,455	OpenAI	Proprietary
123	103◄─►146	gpt-oss-20b	1361	±10	3,674	OpenAI	Apache 2.0
124	110◄─►143	gpt-4o-2024-05-13	1359	±5	31,453	OpenAI	Proprietary
125	109◄─►145	llama-4-maverick-17b-128e-instruct	1358	±6	12,788	Meta	Llama 4
126	108◄─►146	yi-lightning	1358	±8	7,069	01 AI	Proprietary
127	98◄─►161	hunyuan-large-2025-02-10	1356	±20	828	Tencent	Proprietary
128	107◄─►157	olmo-3-32b-think	1355	±14	1,977	Allen AI	Apache 2.0
129	116◄─►147	gemini-1.5-pro-002	1355	±6	14,455	Google	Proprietary
130	116◄─►152	gemini-2.0-flash-lite-preview-02-05	1354	±8	5,697	Google	Proprietary
131	98◄─►166	mercury	1354	±22	690	Inception AI	Proprietary
132	116◄─►150	llama-3.1-405b-instruct-fp8	1353	±6	15,834	Meta	Llama 3.1 Community
133	116◄─►152	athene-v2-chat	1352	±8	6,190	NexusFlow	NexusFlow
134	116◄─►160	step-1o-turbo-202506	1350	±11	2,949	StepFun	Proprietary
135	109◄─►163	step-2-16k-exp-202412	1350	±16	1,203	StepFun	Proprietary
136	118◄─►155	llama-4-scout-17b-16e-instruct	1350	±7	9,854	Meta	Llama
137	116◄─►159	magistral-medium-2506	1350	±10	4,139	Mistral	Proprietary
138	119◄─►153	grok-2-2024-08-13	1349	±6	16,655	xAI	Proprietary
139	110◄─►162	glm-4-plus-0111	1349	±15	1,406	Zhipu	Proprietary
140	118◄─►159	deepseek-v2.5	1348	±8	6,702	DeepSeek	DeepSeek
141	102◄─►171	llama-3.3-nemotron-49b-super-v1	1347	±25	494	Nvidia	Nvidia
142	120◄─►160	gpt-4o-2024-08-06	1346	±7	11,872	OpenAI	Proprietary
143	119◄─►165	qwen2.5-plus-1127	1344	±11	2,392	Alibaba	Proprietary
144	123◄─►160	mistral-small-3.1-24b-instruct-2503	1344	±6	11,228	Mistral	Apache 2.0
145	121◄─►165	qwen-max-0919	1342	±9	4,415	Alibaba	Qwen
146	127◄─►162	mistral-large-2407	1342	±7	12,148	Mistral	Mistral Research
147	127◄─►161	gemini-1.5-pro-001	1342	±6	21,448	Google	Proprietary
148	127◄─►162	qwen2.5-72b-instruct	1342	±6	10,462	Alibaba	Qwen
149	128◄─►165	gemini-advanced-0514	1340	±8	13,794	Google	Proprietary
150	131◄─►163	claude-3-opus-20240229	1339	±5	55,070	Anthropic	Proprietary
151	128◄─►166	glm-4-plus	1339	±8	7,103	Zhipu AI	Proprietary
152	132◄─►165	llama-3.3-70b-instruct	1338	±5	15,119	Meta	Llama-3.3
153	133◄─►166	gpt-4o-mini-2024-07-18	1337	±5	17,875	OpenAI	Proprietary
154	132◄─►167	gemma-3n-e4b-it	1336	±8	6,773	Google	Gemma
155	133◄─►167	gpt-4-turbo-2024-04-09	1335	±6	27,636	OpenAI	Proprietary
156	119◄─►174	gemma-3-12b-it	1334	±19	869	Google	Gemma
157	120◄─►176	hunyuan-standard-2025-02-10	1333	±19	880	Tencent	Proprietary
158	136◄─►169	mistral-large-2411	1332	±7	6,831	Mistral	MRL
159	134◄─►171	athene-70b-0725	1332	±9	5,038	NexusFlow	CC-BY-NC-4.0
160	143◄─►171	grok-2-mini-2024-08-13	1328	±6	13,867	xAI	Proprietary
161	141◄─►172	amazon-nova-pro-v1.0	1328	±7	6,171	Amazon	Proprietary
162	134◄─►176	hunyuan-large-vision	1327	±14	1,867	Tencent	Proprietary
163	146◄─►176	deepseek-coder-v2	1324	±10	4,352	DeepSeek AI	DeepSeek License
164	139◄─►180	llama-3.1-nemotron-70b-instruct	1324	±13	2,081	Nvidia	Llama 3.1
165	153◄─►174	gpt-4-1106-preview	1323	±6	26,490	OpenAI	Proprietary
166	155◄─►176	gemini-1.5-flash-002	1321	±7	9,237	Google	Proprietary
167	150◄─►182	ibm-granite-h-small	1319	±13	2,148	IBM	Apache 2.0
168	156◄─►176	gpt-4-0125-preview	1319	±6	25,646	OpenAI	Proprietary
169	146◄─►182	qwen2.5-coder-32b-instruct	1318	±15	1,380	Alibaba	Apache 2.0
170	156◄─►177	llama-3.1-70b-instruct	1318	±6	14,821	Meta	Llama 3.1 Community
171	162◄─►182	gemma-2-27b-it	1310	±5	19,968	Google	Gemma license
172	155◄─►189	llama-3.1-nemotron-51b-instruct	1309	±18	1,056	Nvidia	Llama 3.1
173	159◄─►186	jamba-1.5-large	1309	±12	2,342	AI21 Labs	Jamba Open
174	168◄─►183	claude-3-sonnet-20240229	1306	±6	31,525	Anthropic	Proprietary
175	168◄─►183	gemini-1.5-flash-001	1305	±7	17,531	Google	Proprietary
176	162◄─►187	mistral-small-24b-instruct-2501	1305	±10	3,482	Mistral	Apache 2.0
177	168◄─►187	gpt-4-0314	1304	±8	14,566	OpenAI	Proprietary
178	160◄─►196	gemma-3-4b-it	1300	±19	988	Google	Gemma
179	167◄─►194	reka-core-20240904	1300	±13	2,009	Reka AI	Proprietary
180	169◄─►193	nemotron-4-340b-instruct	1298	±9	5,420	Nvidia	NVIDIA Open Model
181	160◄─►199	llama-3.1-tulu-3-70b	1297	±20	713	Ai2	Llama 3.1
182	169◄─►195	glm-4-0520	1295	±12	2,849	Zhipu AI	Proprietary
183	172◄─►195	amazon-nova-lite-v1.0	1294	±9	4,888	Amazon	Proprietary
184	174◄─►196	c4ai-aya-expanse-32b	1289	±8	7,312	Cohere	CC-BY-NC-4.0
185	174◄─►196	phi-4	1289	±8	5,588	Microsoft	MIT
186	177◄─►195	llama-3-70b-instruct	1289	±6	45,156	Meta	Llama 3 Community
187	178◄─►198	gpt-4-0613	1285	±7	23,834	OpenAI	Proprietary
188	174◄─►203	reka-flash-20240904	1285	±12	1,979	Reka AI	Proprietary
189	178◄─►198	claude-3-haiku-20240307	1284	±6	34,338	Anthropic	Proprietary
190	177◄─►204	gemma-2-9b-it-simpo	1282	±12	2,540	Princeton	MIT
191	180◄─►202	gemma-2-9b-it	1280	±6	14,614	Google	Gemma license
192	179◄─►203	qwen2-72b-instruct	1280	±7	10,320	Alibaba	Qianwen LICENSE
193	175◄─►211	hunyuan-standard-256k	1276	±21	739	Tencent	Proprietary
194	178◄─►210	ministral-8b-2410	1275	±16	1,254	Mistral	MRL
195	186◄─►205	gemini-1.5-flash-8b-001	1273	±7	9,615	Google	Proprietary
196	182◄─►209	command-r-plus-08-2024	1272	±11	2,715	Cohere	CC-BY-NC-4.0
197	186◄─►208	amazon-nova-micro-v1.0	1270	±9	4,686	Amazon	Proprietary
198	189◄─►206	command-r-plus	1269	±7	22,723	Cohere	CC-BY-NC-4.0
199	189◄─►208	mistral-large-2402	1269	±7	17,553	Mistral	Proprietary
200	178◄─►217	olmo-2-0325-32b-instruct	1268	±21	743	Allen AI	Apache-2.0
201	188◄─►211	command-r-08-2024	1267	±11	2,850	Cohere	CC-BY-NC-4.0
202	189◄─►212	jamba-1.5-mini	1263	±12	2,293	AI21 Labs	Jamba Open
203	190◄─►211	reka-flash-21b-20240226-online	1263	±11	4,695	Reka AI	Proprietary
204	193◄─►216	qwen1.5-110b-chat	1258	±9	7,693	Alibaba	Qianwen LICENSE
205	194◄─►217	qwen1.5-72b-chat	1256	±8	10,769	Alibaba	Qianwen LICENSE
206	198◄─►217	mixtral-8x22b-instruct-v0.1	1253	±7	14,428	Mistral	Apache 2.0
207	197◄─►222	reka-flash-21b-20240226	1252	±9	7,460	Reka AI	Proprietary
208	195◄─►224	c4ai-aya-expanse-8b	1250	±12	2,474	Cohere	CC-BY-NC-4.0
209	192◄─►227	granite-3.1-8b-instruct	1250	±21	784	IBM	Apache 2.0
210	199◄─►224	gemini-pro-dev-api	1247	±12	4,917	Google	Proprietary
211	202◄─►224	gpt-3.5-turbo-0125	1245	±7	19,022	OpenAI	Proprietary
212	203◄─►224	llama-3.1-8b-instruct	1244	±6	13,144	Meta	Llama 3.1 Community
213	195◄─►230	llama-3.1-tulu-3-8b	1243	±20	762	Ai2	Llama 3.1
214	204◄─►224	llama-3-8b-instruct	1242	±6	29,702	Meta	Llama 3 Community
215	203◄─►226	mistral-medium	1242	±9	9,023	Mistral	Proprietary
216	203◄─►226	qwen1.5-32b-chat	1241	±9	6,365	Alibaba	Qianwen LICENSE
217	207◄─►226	command-r	1239	±7	15,789	Cohere	CC-BY-NC-4.0
218	207◄─►228	yi-1.5-34b-chat	1236	±9	6,466	01 AI	Apache-2.0
219	203◄─►232	zephyr-orpo-141b-A35b-v0.1	1234	±17	1,346	HuggingFace	Apache 2.0
220	207◄─►232	internlm2_5-20b-chat	1233	±12	2,728	InternLM	Other
221	208◄─►232	qwen1.5-14b-chat	1230	±11	5,263	Alibaba	Qianwen LICENSE
222	208◄─►235	gpt-3.5-turbo-1106	1227	±13	4,129	OpenAI	Proprietary
223	207◄─►236	gemini-pro	1227	±19	1,416	Google	Proprietary
224	216◄─►232	mixtral-8x7b-instruct-v0.1	1224	±7	20,169	Mistral	Apache 2.0
225	213◄─►235	dbrx-instruct-preview	1224	±9	9,368	Databricks	DBRX LICENSE
226	207◄─►239	granite-3.1-2b-instruct	1223	±20	829	IBM	Apache 2.0
227	217◄─►236	phi-3-medium-4k-instruct	1220	±8	6,663	Microsoft	MIT
228	213◄─►239	granite-3.0-8b-instruct	1218	±15	1,828	IBM	Apache 2.0
229	218◄─►238	starling-lm-7b-beta	1216	±11	4,848	Nexusflow	Apache-2.0
230	219◄─►238	gemma-1.1-7b-it	1213	±9	7,075	Google	Gemma license
231	219◄─►241	openchat-3.5-0106	1210	±12	3,465	OpenChat	Apache-2.0
232	218◄─►251	deepseek-llm-67b-chat	1205	±19	1,220	DeepSeek AI	DeepSeek License
233	223◄─►245	snowflake-arctic-instruct	1205	±10	9,224	Snowflake	Apache 2.0
234	223◄─►245	yi-34b-chat	1204	±11	4,136	01 AI	Yi License
235	227◄─►245	gemma-2-2b-it	1199	±7	11,854	Google	Gemma license
236	223◄─►255	openchat-3.5	1199	±16	1,881	OpenChat	Apache-2.0
237	227◄─►251	phi-3-small-8k-instruct	1197	±10	5,154	Microsoft	MIT
238	225◄─►257	tulu-2-dpo-70b	1196	±17	1,496	AllenAI/UW	AI2 ImpACT Low-risk
239	232◄─►258	vicuna-33b	1187	±10	5,532	LMSYS	Non-commercial
240	229◄─►264	openhermes-2.5-mistral-7b	1186	±18	1,192	NousResearch	Apache-2.0
241	231◄─►264	wizardlm-70b	1186	±15	1,940	Microsoft	Llama 2 Community
242	231◄─►264	granite-3.0-2b-instruct	1185	±14	1,930	IBM	Apache 2.0
243	232◄─►264	starling-lm-7b-alpha	1184	±13	2,611	UC Berkeley	CC-BY-NC-4.0
244	235◄─►260	llama-2-70b-chat	1182	±8	10,194	Meta	Llama 2 Community
245	232◄─►266	qwen1.5-7b-chat	1179	±17	1,282	Alibaba	Qianwen LICENSE
246	235◄─►265	phi-3-mini-4k-instruct-june-2024	1179	±11	3,115	Microsoft	MIT
247	232◄─►266	nous-hermes-2-mixtral-8x7b-dpo	1178	±19	993	NousResearch	Apache-2.0
248	237◄─►265	mistral-7b-instruct-v0.2	1175	±10	5,237	Mistral	Apache-2.0
249	237◄─►266	llama-3.2-3b-instruct	1173	±13	2,166	Meta	Llama 3.2
250	235◄─►270	qwen-14b-chat	1170	±18	1,173	Alibaba	Qianwen LICENSE
251	235◄─►270	solar-10.7b-instruct-v1.0	1168	±21	982	Upstage AI	CC-BY-NC-4.0
252	235◄─►273	mpt-30b-chat	1167	±25	574	MosaicML	CC-BY-NC-SA-4.0
253	239◄─►270	gemma-7b-it	1165	±14	2,377	Google	Gemma license
254	237◄─►273	qwq-32b-preview	1165	±21	823	Alibaba	Apache 2.0
255	241◄─►269	phi-3-mini-4k-instruct	1162	±10	5,727	Microsoft	MIT
256	241◄─►270	vicuna-13b	1161	±11	4,699	LMSYS	Llama 2 Community
257	240◄─►273	codellama-34b-instruct	1160	±15	1,770	Meta	Llama 2 Community
258	235◄─►277	codellama-70b-instruct	1160	±32	326	Meta	Llama 2 Community
259	237◄─►277	zephyr-7b-alpha	1157	±29	406	HuggingFace	MIT
260	240◄─►275	llama2-70b-steerlm-chat	1156	±21	877	Nvidia	Llama 2 Community
261	241◄─►273	wizardlm-13b	1156	±16	1,619	Microsoft	Llama 2 Community
262	245◄─►273	gemma-1.1-2b-it	1156	±12	3,196	Google	Gemma license
263	247◄─►273	llama-2-13b-chat	1155	±10	4,919	Meta	Llama 2 Community
264	238◄─►277	dolphin-2.2.1-mistral-7b	1153	±28	366	Cognitive Computations	Apache-2.0
265	238◄─►278	falcon-180b-chat	1148	±33	309	TII	Falcon-180B TII License
266	241◄─►278	smollm2-1.7b-instruct	1146	±27	578	HuggingFace	Apache 2.0
267	250◄─►277	zephyr-7b-beta	1143	±14	2,601	HuggingFace	MIT
268	250◄─►277	palm-2	1142	±15	2,077	Google	Proprietary
269	251◄─►277	phi-3-mini-128k-instruct	1140	±11	6,070	Microsoft	MIT
270	250◄─►278	stripedhyena-nous-7b	1136	±18	1,324	Together AI	Apache 2.0
271	255◄─►278	vicuna-7b	1130	±16	1,601	LMSYS	Llama 2 Community
272	255◄─►278	gemma-2b-it	1130	±18	1,286	Google	Gemma license
273	255◄─►278	mistral-7b-instruct	1130	±16	2,096	Mistral	Apache 2.0
274	261◄─►278	llama-3.2-1b-instruct	1125	±14	2,183	Meta	Llama 3.2
275	262◄─►280	qwen1.5-4b-chat	1117	±15	2,199	Alibaba	Qianwen LICENSE
276	261◄─►280	guanaco-33b	1115	±24	635	UW	Non-commercial
277	262◄─►280	olmo-7b-instruct	1114	±18	1,476	Allen AI	Apache-2.0
278	268◄─►280	llama-2-7b-chat	1110	±11	3,721	Meta	Llama 2 Community
279	275◄─►282	chatglm3-6b	1085	±20	1,084	Tsinghua	Apache-2.0
280	275◄─►284	gpt4all-13b-snoozy	1074	±30	422	Nomic AI	Non-commercial
281	279◄─►284	koala-13b	1072	±18	1,574	UC Berkeley	Non-commercial
282	279◄─►285	mpt-7b-chat	1055	±22	883	MosaicML	CC-BY-NC-SA-4.0
283	280◄─►286	RWKV-4-Raven-14B	1038	±20	1,073	RWKV	Apache 2.0
284	280◄─►287	chatglm2-6b	1032	±25	653	Tsinghua	Apache-2.0
285	282◄─►287	oasst-pythia-12b	1018	±19	1,409	OpenAssistant	Apache 2.0
286	283◄─►289	alpaca-13b	1007	±20	1,335	Stanford	Non-commercial
287	284◄─►290	chatglm-6b	995	±20	1,162	Tsinghua	Non-commercial
288	286◄─►290	stablelm-tuned-alpha-7b	968	±24	742	Stability AI	CC-BY-NC-SA-4.0
289	286◄─►290	fastchat-t5-3b	967	±21	955	LMSYS	Apache 2.0
290	287◄─►290	dolly-v2-12b	962	±24	824	Databricks	MIT
291	291◄─►291	llama-13b	902	±30	566	Meta	Non-commercial

Text Arena

Default Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

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

Confidence Intervals on Model Strength (via Bootstrapping)

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