Text Arena

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

Last Updated

Nov 26, 2025

Total Votes

782,800

Total Models

272

/

Style Control

	Rank Spread (Upper-Lower)
1	1◄─►7	claude-opus-4-5-20251101-thinking-32k	1535	±24	602	Anthropic	Proprietary
2	1◄─►7	gemini-3-pro	1526	±13	2,128	Google	Proprietary
3	1◄─►6	claude-sonnet-4-5-20250929-thinking-32k	1525	±9	4,801	Anthropic	Proprietary
4	1◄─►9	claude-opus-4-1-20250805-thinking-16k	1515	±8	7,395	Anthropic	Proprietary
5	1◄─►12	grok-4.1-thinking	1511	±14	1,984	xAI	Proprietary
6	1◄─►14	claude-opus-4-5-20251101	1509	±20	922	Anthropic	Proprietary
7	2◄─►12	claude-sonnet-4-5-20250929	1504	±11	3,542	Anthropic	Proprietary
8	4◄─►12	claude-opus-4-1-20250805	1501	±7	9,981	Anthropic	Proprietary
9	4◄─►21	gpt-5.1-high	1495	±15	1,543	OpenAI	Proprietary
10	5◄─►15	claude-opus-4-20250514-thinking-16k	1495	±8	6,742	Anthropic	Proprietary
11	4◄─►21	grok-4.1	1494	±13	2,084	xAI	Proprietary
12	5◄─►27	gpt-5.1	1490	±14	1,745	OpenAI	Proprietary
13	8◄─►28	qwen3-max-preview	1481	±9	5,414	Alibaba	Proprietary
14	8◄─►37	kimi-k2-thinking-turbo	1479	±13	2,007	Moonshot	Modified MIT
15	9◄─►32	claude-haiku-4-5-20251001	1478	±9	4,402	Anthropic	Proprietary
16	10◄─►40	qwen3-max-2025-09-23	1474	±13	2,041	Alibaba	Proprietary
17	10◄─►40	longcat-flash-chat	1474	±13	2,248	Meituan	MIT
18	12◄─►37	qwen3-235b-a22b-instruct-2507	1472	±7	8,845	Alibaba	Apache 2.0
19	10◄─►43	deepseek-v3.2-exp	1472	±13	2,030	DeepSeek AI	MIT
20	10◄─►45	deepseek-v3.2-exp-thinking	1471	±13	1,930	DeepSeek AI	MIT
21	12◄─►37	gemini-2.5-pro	1471	±6	13,390	Google	Proprietary
22	12◄─►40	gpt-5-high	1470	±8	6,477	OpenAI	Proprietary
23	12◄─►40	claude-sonnet-4-20250514-thinking-32k	1469	±8	6,510	Anthropic	Proprietary
24	12◄─►49	kimi-k2-0905-preview	1467	±13	2,227	Moonshot	Modified MIT
25	12◄─►52	qwen3-vl-235b-a22b-instruct	1464	±14	1,821	Alibaba	Apache 2.0
26	14◄─►50	glm-4.6	1463	±10	4,045	Z.ai	MIT
27	15◄─►46	chatgpt-4o-latest-20250326	1463	±6	10,578	OpenAI	Proprietary
28	13◄─►51	deepseek-r1-0528	1462	±11	2,785	DeepSeek	MIT
29	15◄─►49	claude-opus-4-20250514	1461	±7	8,006	Anthropic	Proprietary
30	10◄─►67	grok-4-1-fast-reasoning	1459	±25	562	xAI	Proprietary
31	15◄─►52	gpt-5-chat	1459	±8	6,035	OpenAI	Proprietary
32	15◄─►53	kimi-k2-0711-preview	1458	±9	5,310	Moonshot	Modified MIT
33	10◄─►68	deepseek-v3.1-terminus-thinking	1457	±24	639	DeepSeek AI	MIT
34	18◄─►52	o3-2025-04-16	1457	±6	11,953	OpenAI	Proprietary
35	14◄─►55	gpt-4.5-preview-2025-02-27	1456	±13	1,944	OpenAI	Proprietary
36	14◄─►56	deepseek-v3.1-thinking	1456	±14	1,897	DeepSeek	MIT
37	18◄─►55	glm-4.5	1455	±9	4,781	Z.ai	MIT
38	14◄─►62	grok-4-fast	1454	±16	1,264	xAI	Proprietary
39	15◄─►61	qwen3-vl-235b-a22b-thinking	1454	±14	1,636	Alibaba	Apache 2.0
40	22◄─►54	gpt-4.1-2025-04-14	1454	±7	9,422	OpenAI	Proprietary
41	18◄─►55	qwen3-coder-480b-a35b-instruct	1453	±9	4,370	Alibaba	Apache 2.0
42	22◄─►55	mistral-medium-2508	1452	±7	8,000	Mistral	Proprietary
43	24◄─►56	claude-3-7-sonnet-20250219-thinking-32k	1449	±8	6,251	Anthropic	Proprietary
44	23◄─►65	deepseek-v3.1	1447	±12	2,647	DeepSeek	MIT
45	27◄─►61	claude-sonnet-4-20250514	1446	±7	7,519	Anthropic	Proprietary
46	25◄─►65	qwen3-next-80b-a3b-instruct	1445	±9	4,829	Alibaba	Apache 2.0
47	25◄─►70	deepseek-r1	1443	±12	2,336	DeepSeek	MIT
48	29◄─►65	qwen3-235b-a22b-no-thinking	1443	±8	7,057	Alibaba	Apache 2.0
49	32◄─►68	grok-3-preview-02-24	1442	±8	5,510	xAI	Proprietary
50	25◄─►73	qwen3-235b-a22b-thinking-2507	1441	±15	1,631	Alibaba	Apache 2.0
51	33◄─►71	grok-4-fast-reasoning	1438	±10	3,966	xAI	Proprietary
52	34◄─►71	qwen3-30b-a3b-instruct-2507	1437	±9	4,689	Alibaba	Apache 2.0
53	23◄─►83	deepseek-v3.1-terminus	1437	±21	774	DeepSeek AI	MIT
54	28◄─►84	ernie-5.0-preview-1022	1434	±19	922	Baidu	Proprietary
55	40◄─►73	grok-4-0709	1433	±7	8,315	xAI	Proprietary
56	22◄─►87	hunyuan-vision-1.5-thinking	1433	±27	436	Tencent	Proprietary
57	43◄─►73	claude-3-5-sonnet-20241022	1432	±5	15,093	Anthropic	Proprietary
58	40◄─►74	gpt-4.1-mini-2025-04-14	1432	±8	7,042	OpenAI	Proprietary
59	38◄─►79	o3-mini-high	1432	±11	2,602	OpenAI	Proprietary
60	40◄─►77	qwen3-235b-a22b	1432	±9	4,398	Alibaba	Apache 2.0
61	40◄─►79	o1-2024-12-17	1430	±9	3,987	OpenAI	Proprietary
62	42◄─►79	gpt-5-mini-high	1430	±9	5,574	OpenAI	Proprietary
63	43◄─►77	o4-mini-2025-04-16	1429	±7	8,860	OpenAI	Proprietary
64	43◄─►78	mistral-medium-2505	1429	±8	5,948	Mistral	Proprietary
65	40◄─►82	mai-1-preview	1428	±11	2,787	Microsoft AI	Proprietary
66	46◄─►80	claude-3-7-sonnet-20250219	1427	±7	7,251	Anthropic	Proprietary
67	47◄─►82	glm-4.5-air	1426	±8	6,186	Z.ai	MIT
68	49◄─►82	deepseek-v3-0324	1425	±7	8,485	DeepSeek	MIT
69	46◄─►84	qwen3-next-80b-a3b-thinking	1423	±12	2,696	Alibaba	Apache 2.0
70	49◄─►84	gemini-2.5-flash-preview-09-2025	1423	±9	4,873	Google	Proprietary
71	55◄─►84	gemini-2.5-flash	1419	±6	12,766	Google	Proprietary
72	56◄─►86	minimax-m1	1416	±8	6,644	MiniMax	Apache 2.0
73	56◄─►87	o1-preview	1415	±9	5,137	OpenAI	Proprietary
74	63◄─►86	o3-mini	1413	±6	9,586	OpenAI	Proprietary
75	52◄─►91	ling-flash-2.0	1413	±15	1,557	Ant Group	MIT
76	58◄─►90	mistral-small-2506	1411	±10	3,383	Mistral	Apache 2.0
77	50◄─►112	qwen3-32b	1405	±25	513	Alibaba	Apache 2.0
78	62◄─►111	step-3	1404	±17	1,236	StepFun	Apache 2.0
79	56◄─►111	amazon-nova-experimental-chat-10-20	1403	±20	865	Amazon	Proprietary
80	59◄─►111	glm-4.5v	1402	±19	986	Z.ai	MIT
81	71◄─►104	qwen2.5-max	1400	±8	5,210	Alibaba	Proprietary
82	52◄─►125	hunyuan-turbos-20250226	1397	±31	277	Tencent	Proprietary
83	67◄─►115	hunyuan-t1-20250711	1396	±20	811	Tencent	Proprietary
84	75◄─►110	claude-3-5-sonnet-20240620	1396	±7	13,637	Anthropic	Proprietary
85	66◄─►118	nvidia-llama-3.3-nemotron-super-49b-v1.5	1396	±22	678	Nvidia	Nvidia Open
86	75◄─►111	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1393	±9	4,876	Google	Proprietary
87	73◄─►114	hunyuan-turbos-20250416	1393	±14	1,819	Tencent	Proprietary
88	75◄─►117	ring-flash-2.0	1390	±15	1,553	Ant Group	MIT
89	63◄─►131	llama-3.1-nemotron-ultra-253b-v1	1390	±30	367	Nvidia	Nvidia Open Model
90	77◄─►112	gpt-oss-120b	1389	±8	6,563	OpenAI	Apache 2.0
91	77◄─►112	command-a-03-2025	1387	±6	10,377	Cohere	CC-BY-NC-4.0
92	77◄─►114	grok-3-mini-high	1387	±10	3,372	xAI	Proprietary
93	71◄─►128	amazon-nova-experimental-chat-10-09	1387	±24	562	Amazon	Proprietary
94	77◄─►116	deepseek-v3	1386	±10	3,299	DeepSeek	DeepSeek
95	77◄─►114	o1-mini	1386	±7	8,495	OpenAI	Proprietary
96	77◄─►119	magistral-medium-2506	1385	±12	2,296	Mistral	Proprietary
97	77◄─►117	qwq-32b	1384	±9	4,106	Alibaba	Apache 2.0
98	77◄─►117	grok-3-mini-beta	1384	±9	4,335	xAI	Proprietary
99	77◄─►117	qwen3-30b-a3b	1384	±9	4,610	Alibaba	Apache 2.0
100	78◄─►115	gemini-2.5-flash-lite-preview-06-17-thinking	1384	±8	6,129	Google	Proprietary
101	78◄─►114	claude-3-5-haiku-20241022	1383	±6	11,338	Anthropic	Propretary
102	77◄─►127	gpt-5-nano-high	1381	±15	1,675	OpenAI	Proprietary
103	77◄─►133	qwen-plus-0125	1377	±18	896	Alibaba	Proprietary
104	78◄─►131	minimax-m2	1375	±15	1,648	MiniMax	Apache 2.0
105	78◄─►136	deepseek-v2.5-1210	1373	±17	1,084	DeepSeek	DeepSeek
106	86◄─►127	llama-3.1-405b-instruct-bf16	1372	±7	6,273	Meta	Llama 3.1 Community
107	78◄─►138	gpt-4.1-nano-2025-04-14	1372	±19	808	OpenAI	Proprietary
108	86◄─►127	llama-4-maverick-17b-128e-instruct	1372	±8	7,111	Meta	Llama 4
109	76◄─►151	hunyuan-turbo-0110	1370	±30	304	Tencent	Proprietary
110	77◄─►149	mercury	1369	±28	407	Inception AI	Proprietary
111	83◄─►136	gpt-oss-20b	1369	±13	2,130	OpenAI	Apache 2.0
112	79◄─►145	step-2-16k-exp-202412	1368	±20	742	StepFun	Proprietary
113	90◄─►135	yi-lightning	1367	±9	4,320	01 AI	Proprietary
114	98◄─►131	gpt-4o-2024-05-13	1367	±6	19,568	OpenAI	Proprietary
115	93◄─►135	athene-v2-chat	1367	±9	4,028	NexusFlow	NexusFlow
116	97◄─►135	deepseek-v2.5	1366	±9	4,262	DeepSeek	DeepSeek
117	99◄─►134	llama-3.1-405b-instruct-fp8	1366	±7	9,742	Meta	Llama 3.1 Community
118	78◄─►151	hunyuan-large-2025-02-10	1365	±25	521	Tencent	Proprietary
119	99◄─►136	gemini-2.0-flash-001	1363	±7	7,118	Google	Proprietary
120	77◄─►154	llama-3.3-nemotron-49b-super-v1	1362	±31	287	Nvidia	Nvidia
121	99◄─►139	llama-4-scout-17b-16e-instruct	1361	±9	5,317	Meta	Llama
122	99◄─►143	mistral-small-3.1-24b-instruct-2503	1359	±8	6,233	Mistral	Apache 2.0
123	100◄─►140	gemma-3-27b-it	1359	±7	8,330	Google	Gemma
124	100◄─►143	gpt-4o-2024-08-06	1359	±8	7,329	OpenAI	Proprietary
125	92◄─►151	hunyuan-large-vision	1357	±19	989	Tencent	Proprietary
126	103◄─►143	grok-2-2024-08-13	1357	±7	10,386	xAI	Proprietary
127	99◄─►149	qwen2.5-plus-1127	1355	±14	1,556	Alibaba	Proprietary
128	104◄─►145	gemini-1.5-pro-002	1355	±7	9,194	Google	Proprietary
129	99◄─►151	step-1o-turbo-202506	1354	±15	1,579	StepFun	Proprietary
130	104◄─►146	qwen2.5-72b-instruct	1353	±7	6,697	Alibaba	Qwen
131	112◄─►147	claude-3-opus-20240229	1351	±6	33,838	Anthropic	Proprietary
132	109◄─►148	mistral-large-2407	1351	±8	7,610	Mistral	Mistral Research
133	104◄─►151	qwen-max-0919	1351	±11	2,764	Alibaba	Qwen
134	107◄─►149	glm-4-plus	1350	±9	4,460	Zhipu AI	Proprietary
135	107◄─►151	athene-70b-0725	1349	±11	3,135	NexusFlow	CC-BY-NC-4.0
136	115◄─►149	gpt-4o-mini-2024-07-18	1347	±6	10,981	OpenAI	Proprietary
137	115◄─►151	gemini-1.5-pro-001	1346	±7	12,782	Google	Proprietary
138	118◄─►151	gpt-4-turbo-2024-04-09	1344	±7	17,155	OpenAI	Proprietary
139	117◄─►153	mistral-large-2411	1343	±9	4,243	Mistral	MRL
140	121◄─►152	llama-3.3-70b-instruct	1343	±6	8,853	Meta	Llama-3.3
141	118◄─►154	gemini-2.0-flash-lite-preview-02-05	1342	±10	3,484	Google	Proprietary
142	108◄─►160	qwen2.5-coder-32b-instruct	1340	±18	873	Alibaba	Apache 2.0
143	121◄─►154	amazon-nova-pro-v1.0	1340	±9	3,875	Amazon	Proprietary
144	118◄─►157	deepseek-coder-v2	1340	±12	2,676	DeepSeek AI	DeepSeek License
145	124◄─►156	gemini-advanced-0514	1337	±9	8,170	Google	Proprietary
146	125◄─►155	gpt-4-1106-preview	1336	±7	15,648	OpenAI	Proprietary
147	130◄─►157	grok-2-mini-2024-08-13	1334	±7	8,664	xAI	Proprietary
148	138◄─►158	llama-3.1-70b-instruct	1331	±7	9,422	Meta	Llama 3.1 Community
149	123◄─►169	glm-4-plus-0111	1329	±18	896	Zhipu	Proprietary
150	116◄─►172	hunyuan-standard-2025-02-10	1329	±24	549	Tencent	Proprietary
151	139◄─►163	gpt-4-0125-preview	1328	±7	15,337	OpenAI	Proprietary
152	126◄─►169	llama-3.1-nemotron-70b-instruct	1327	±15	1,313	Nvidia	Llama 3.1
153	140◄─►166	gpt-4-0314	1325	±9	8,336	OpenAI	Proprietary
154	130◄─►180	gemma-3-12b-it	1317	±23	545	Google	Gemma
155	149◄─►172	claude-3-sonnet-20240229	1314	±7	18,944	Anthropic	Proprietary
156	148◄─►172	gemini-1.5-flash-002	1314	±8	5,909	Google	Proprietary
157	145◄─►179	reka-core-20240904	1313	±15	1,221	Reka AI	Proprietary
158	149◄─►176	gemma-3n-e4b-it	1311	±10	3,620	Google	Gemma
159	148◄─►178	mistral-small-24b-instruct-2501	1310	±12	2,094	Mistral	Apache 2.0
160	147◄─►180	jamba-1.5-large	1310	±14	1,442	AI21 Labs	Jamba Open
161	150◄─►175	gpt-4-0613	1310	±8	13,770	OpenAI	Proprietary
162	150◄─►176	gemini-1.5-flash-001	1308	±7	10,699	Google	Proprietary
163	143◄─►184	llama-3.1-nemotron-51b-instruct	1308	±22	665	Nvidia	Llama 3.1
164	144◄─►186	llama-3.1-tulu-3-70b	1305	±24	452	Ai2	Llama 3.1
165	150◄─►180	glm-4-0520	1305	±14	1,728	Zhipu AI	Proprietary
166	151◄─►180	phi-4	1304	±10	3,320	Microsoft	MIT
167	153◄─►178	gemma-2-27b-it	1304	±6	12,115	Google	Gemma license
168	151◄─►180	nemotron-4-340b-instruct	1304	±11	3,275	Nvidia	NVIDIA Open Model
169	153◄─►179	llama-3-70b-instruct	1303	±7	28,216	Meta	Llama 3 Community
170	151◄─►180	amazon-nova-lite-v1.0	1303	±10	3,093	Amazon	Proprietary
171	156◄─►180	claude-3-haiku-20240307	1298	±7	20,968	Anthropic	Proprietary
172	149◄─►196	hunyuan-standard-256k	1297	±25	499	Tencent	Proprietary
173	157◄─►186	qwen2-72b-instruct	1293	±9	6,267	Alibaba	Qianwen LICENSE
174	159◄─►186	mistral-large-2402	1291	±8	10,458	Mistral	Proprietary
175	159◄─►187	c4ai-aya-expanse-32b	1290	±9	4,696	Cohere	CC-BY-NC-4.0
176	156◄─►194	reka-flash-20240904	1289	±15	1,210	Reka AI	Proprietary
177	163◄─►194	amazon-nova-micro-v1.0	1286	±10	2,998	Amazon	Proprietary
178	153◄─►204	granite-3.1-8b-instruct	1285	±26	484	IBM	Apache 2.0
179	156◄─►208	olmo-2-0325-32b-instruct	1278	±27	430	Allen AI	Apache-2.0
180	170◄─►202	command-r-08-2024	1277	±13	1,788	Cohere	CC-BY-NC-4.0
181	170◄─►202	command-r-plus-08-2024	1277	±14	1,680	Cohere	CC-BY-NC-4.0
182	171◄─►201	qwen1.5-110b-chat	1276	±10	4,790	Alibaba	Qianwen LICENSE
183	161◄─►208	gemma-3-4b-it	1274	±24	607	Google	Gemma
184	171◄─►203	reka-flash-21b-20240226-online	1274	±13	2,898	Reka AI	Proprietary
185	174◄─►202	mixtral-8x22b-instruct-v0.1	1273	±8	8,819	Mistral	Apache 2.0
186	170◄─►208	ministral-8b-2410	1272	±19	840	Mistral	MRL
187	170◄─►206	gemma-2-9b-it-simpo	1272	±15	1,478	Princeton	MIT
188	175◄─►202	gemini-1.5-flash-8b-001	1271	±8	6,088	Google	Proprietary
189	175◄─►203	qwen1.5-72b-chat	1271	±9	6,381	Alibaba	Qianwen LICENSE
190	175◄─►202	gpt-3.5-turbo-0125	1271	±8	11,175	OpenAI	Proprietary
191	175◄─►202	gemma-2-9b-it	1270	±7	8,942	Google	Gemma license
192	175◄─►203	command-r-plus	1269	±8	13,991	Cohere	CC-BY-NC-4.0
193	175◄─►209	jamba-1.5-mini	1264	±15	1,351	AI21 Labs	Jamba Open
194	177◄─►208	reka-flash-21b-20240226	1263	±11	4,769	Reka AI	Proprietary
195	178◄─►211	mistral-medium	1258	±10	5,162	Mistral	Proprietary
196	178◄─►211	qwen1.5-32b-chat	1257	±11	3,942	Alibaba	Qianwen LICENSE
197	177◄─►213	gpt-3.5-turbo-1106	1257	±16	2,125	OpenAI	Proprietary
198	179◄─►208	llama-3.1-8b-instruct	1257	±7	8,605	Meta	Llama 3.1 Community
199	178◄─►213	c4ai-aya-expanse-8b	1254	±14	1,574	Cohere	CC-BY-NC-4.0
200	175◄─►219	llama-3.1-tulu-3-8b	1251	±25	479	Ai2	Llama 3.1
201	189◄─►213	llama-3-8b-instruct	1250	±7	18,445	Meta	Llama 3 Community
202	178◄─►220	granite-3.1-2b-instruct	1248	±24	514	IBM	Apache 2.0
203	189◄─►216	dbrx-instruct-preview	1247	±11	5,532	Databricks	DBRX LICENSE
204	188◄─►216	internlm2_5-20b-chat	1246	±14	1,693	InternLM	Other
205	178◄─►221	gemini-pro	1245	±24	678	Google	Proprietary
206	190◄─►216	yi-1.5-34b-chat	1244	±10	3,856	01 AI	Apache-2.0
207	185◄─►221	zephyr-orpo-141b-A35b-v0.1	1241	±21	833	HuggingFace	Apache 2.0
208	196◄─►218	command-r	1239	±9	9,680	Cohere	CC-BY-NC-4.0
209	190◄─►222	granite-3.0-8b-instruct	1236	±18	1,114	IBM	Apache 2.0
210	195◄─►221	gemini-pro-dev-api	1236	±14	2,688	Google	Proprietary
211	196◄─►220	qwen1.5-14b-chat	1236	±13	3,224	Alibaba	Qianwen LICENSE
212	198◄─►218	mixtral-8x7b-instruct-v0.1	1235	±8	11,818	Mistral	Apache 2.0
213	198◄─►222	starling-lm-7b-beta	1232	±13	2,965	Nexusflow	Apache-2.0
214	201◄─►223	phi-3-medium-4k-instruct	1227	±10	3,989	Microsoft	MIT
215	201◄─►226	openchat-3.5-0106	1225	±14	2,008	OpenChat	Apache-2.0
216	204◄─►226	snowflake-arctic-instruct	1220	±11	5,752	Snowflake	Apache 2.0
217	207◄─►230	gemma-1.1-7b-it	1215	±10	4,361	Google	Gemma license
218	201◄─►238	deepseek-llm-67b-chat	1214	±24	650	DeepSeek AI	DeepSeek License
219	204◄─►240	tulu-2-dpo-70b	1210	±21	805	AllenAI/UW	AI2 ImpACT Low-risk
220	206◄─►240	qwen1.5-7b-chat	1206	±21	773	Alibaba	Qianwen LICENSE
221	209◄─►240	granite-3.0-2b-instruct	1205	±17	1,135	IBM	Apache 2.0
222	212◄─►240	starling-lm-7b-alpha	1203	±16	1,398	UC Berkeley	CC-BY-NC-4.0
223	215◄─►240	yi-34b-chat	1201	±13	2,350	01 AI	Yi License
224	215◄─►238	phi-3-small-8k-instruct	1201	±12	3,238	Microsoft	MIT
225	214◄─►243	openchat-3.5	1198	±20	974	OpenChat	Apache-2.0
226	217◄─►243	phi-3-mini-4k-instruct-june-2024	1194	±14	1,851	Microsoft	MIT
227	218◄─►240	gemma-2-2b-it	1193	±8	7,316	Google	Gemma license
228	215◄─►247	qwen-14b-chat	1192	±24	599	Alibaba	Qianwen LICENSE
229	218◄─►243	vicuna-33b	1188	±13	2,880	LMSYS	Non-commercial
230	217◄─►249	wizardlm-70b	1187	±20	994	Microsoft	Llama 2 Community
231	218◄─►244	phi-3-mini-4k-instruct	1184	±12	3,466	Microsoft	MIT
232	217◄─►253	openhermes-2.5-mistral-7b	1182	±23	590	NousResearch	Apache-2.0
233	218◄─►246	mistral-7b-instruct-v0.2	1182	±12	3,126	Mistral	Apache-2.0
234	217◄─►254	solar-10.7b-instruct-v1.0	1179	±27	483	Upstage AI	CC-BY-NC-4.0
235	226◄─►250	llama-2-70b-chat	1175	±10	5,730	Meta	Llama 2 Community
236	220◄─►253	llama-3.2-3b-instruct	1173	±16	1,352	Meta	Llama 3.2
237	218◄─►255	qwq-32b-preview	1172	±24	566	Alibaba	Apache 2.0
238	218◄─►255	nous-hermes-2-mixtral-8x7b-dpo	1171	±24	576	NousResearch	Apache-2.0
239	226◄─►253	gemma-1.1-2b-it	1170	±14	1,968	Google	Gemma license
240	226◄─►254	gemma-7b-it	1166	±17	1,387	Google	Gemma license
241	218◄─►259	zephyr-7b-alpha	1164	±40	202	HuggingFace	MIT
242	218◄─►258	mpt-30b-chat	1161	±35	259	MosaicML	CC-BY-NC-SA-4.0
243	230◄─►255	llama-2-13b-chat	1158	±13	2,636	Meta	Llama 2 Community
244	230◄─►255	vicuna-13b	1158	±14	2,398	LMSYS	Llama 2 Community
245	220◄─►259	smollm2-1.7b-instruct	1156	±33	355	HuggingFace	Apache 2.0
246	229◄─►258	codellama-34b-instruct	1154	±20	855	Meta	Llama 2 Community
247	234◄─►258	phi-3-mini-128k-instruct	1151	±13	3,914	Microsoft	MIT
248	233◄─►258	zephyr-7b-beta	1147	±18	1,258	HuggingFace	MIT
249	232◄─►258	palm-2	1147	±21	921	Google	Proprietary
250	232◄─►259	wizardlm-13b	1146	±22	737	Microsoft	Llama 2 Community
251	234◄─►258	llama-3.2-1b-instruct	1146	±16	1,347	Meta	Llama 3.2
252	231◄─►259	llama2-70b-steerlm-chat	1141	±28	467	Nvidia	Llama 2 Community
253	234◄─►259	mistral-7b-instruct	1140	±20	1,034	Mistral	Apache 2.0
254	237◄─►260	gemma-2b-it	1134	±22	744	Google	Gemma license
255	243◄─►261	qwen1.5-4b-chat	1126	±17	1,288	Alibaba	Qianwen LICENSE
256	239◄─►261	vicuna-7b	1125	±23	729	LMSYS	Llama 2 Community
257	243◄─►261	stripedhyena-nous-7b	1121	±22	708	Together AI	Apache 2.0
258	243◄─►264	guanaco-33b	1108	±36	265	UW	Non-commercial
259	249◄─►263	olmo-7b-instruct	1103	±22	775	Allen AI	Apache-2.0
260	254◄─►262	llama-2-7b-chat	1099	±14	1,959	Meta	Llama 2 Community
261	255◄─►266	chatglm3-6b	1084	±26	537	Tsinghua	Apache-2.0
262	258◄─►268	mpt-7b-chat	1059	±32	397	MosaicML	CC-BY-NC-SA-4.0
263	259◄─►267	koala-13b	1058	±24	748	UC Berkeley	Non-commercial
264	260◄─►268	RWKV-4-Raven-14B	1052	±27	507	RWKV	Apache 2.0
265	261◄─►269	oasst-pythia-12b	1043	±25	714	OpenAssistant	Apache 2.0
266	262◄─►269	chatglm-6b	1028	±28	552	Tsinghua	Non-commercial
267	261◄─►269	chatglm2-6b	1025	±35	293	Tsinghua	Apache-2.0
268	263◄─►270	stablelm-tuned-alpha-7b	997	±33	363	Stability AI	CC-BY-NC-SA-4.0
269	265◄─►270	alpaca-13b	992	±27	627	Stanford	Non-commercial
270	268◄─►271	dolly-v2-12b	955	±35	398	Databricks	MIT
271	270◄─►272	fastchat-t5-3b	900	±31	428	LMSYS	Apache 2.0
272	271◄─►272	llama-13b	873	±40	305	Meta	Non-commercial

Text Arena

Default Leaderboard Plots

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

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

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