Text Arena

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

Last Updated

Jan 12, 2026

Total Votes

511,079

Total Models

289

/

Style Control

	Rank Spread
1	1◄─►12	gpt-5.2-high	1492	±26	507	OpenAI	Proprietary
2	1◄─►20	ernie-5.0-0110	1487	±32	315	Baidu	Proprietary
3	1◄─►12	gemini-3-pro	1484	±14	1,818	Google	Proprietary
4	1◄─►25	gemini-3-flash (thinking-minimal)	1478	±27	424	Google	Proprietary
5	1◄─►16	claude-opus-4-5-20251101-thinking-32k	1476	±18	1,135	Anthropic	Proprietary
6	1◄─►19	gpt-5.1-high	1473	±16	1,434	OpenAI	Proprietary
7	1◄─►26	gemini-3-flash	1471	±21	785	Google	Proprietary
8	1◄─►26	claude-opus-4-5-20251101	1467	±17	1,230	Anthropic	Proprietary
9	1◄─►26	claude-sonnet-4-5-20250929-thinking-32k	1461	±13	2,206	Anthropic	Proprietary
10	1◄─►33	grok-4.1-thinking	1456	±15	1,608	xAI	Proprietary
11	3◄─►31	o3-2025-04-16	1454	±10	3,897	OpenAI	Proprietary
12	3◄─►31	gemini-2.5-pro	1452	±9	5,439	Google	Proprietary
13	3◄─►43	claude-opus-4-1-20250805-thinking-16k	1448	±11	3,065	Anthropic	Proprietary
14	1◄─►65	glm-4.7	1446	±26	471	Z.ai	MIT
15	1◄─►79	gpt-5.2	1446	±36	238	OpenAI	Proprietary
16	4◄─►59	qwen3-max-preview	1442	±15	1,541	Alibaba	Proprietary
17	6◄─►59	gpt-5-high	1440	±14	1,947	OpenAI	Proprietary
18	6◄─►61	grok-4.1	1439	±14	2,058	xAI	Proprietary
19	7◄─►61	grok-4-0709	1438	±12	2,320	xAI	Proprietary
20	10◄─►59	claude-opus-4-1-20250805	1438	±9	4,090	Anthropic	Proprietary
21	6◄─►65	kimi-k2-thinking-turbo	1436	±15	1,551	Moonshot	Modified MIT
22	3◄─►76	qwen3-max-2025-09-23	1436	±23	590	Alibaba	Proprietary
23	6◄─►73	deepseek-v3.2	1433	±18	1,204	DeepSeek	MIT
24	3◄─►82	deepseek-v3.2-exp-thinking	1431	±27	480	DeepSeek	MIT
25	4◄─►86	grok-4-fast-chat	1429	±29	407	xAI	Proprietary
26	13◄─►75	claude-sonnet-4-5-20250929	1427	±13	2,119	Anthropic	Proprietary
27	10◄─►82	deepseek-v3.2-exp	1427	±21	791	DeepSeek	MIT
28	13◄─►76	glm-4.6	1426	±14	1,954	Z.ai	MIT
29	14◄─►73	qwen3-235b-a22b-instruct-2507	1426	±10	3,724	Alibaba	Apache 2.0
30	10◄─►82	longcat-flash-chat	1425	±22	702	Meituan	MIT
31	12◄─►81	qwen3-next-80b-a3b-instruct	1425	±17	1,239	Alibaba	Apache 2.0
32	12◄─►86	deepseek-v3.1-thinking	1422	±22	676	DeepSeek	MIT
33	14◄─►81	claude-opus-4-20250514-thinking-16k	1422	±12	2,362	Anthropic	Proprietary
34	14◄─►81	o4-mini-2025-04-16	1419	±10	3,051	OpenAI	Proprietary
35	14◄─►82	glm-4.5	1419	±15	1,458	Z.ai	MIT
36	14◄─►86	deepseek-v3.1	1419	±18	1,011	DeepSeek	MIT
37	14◄─►86	mistral-large-3	1418	±18	1,031	Mistral	Apache 2.0
38	13◄─►90	ernie-5.0-preview-1103	1418	±22	661	Baidu	Proprietary
39	13◄─►87	deepseek-v3.2-thinking	1418	±20	889	DeepSeek	MIT
40	14◄─►82	gpt-5-chat	1418	±14	1,825	OpenAI	Proprietary
41	14◄─►82	gpt-5.1	1418	±14	1,695	OpenAI	Proprietary
42	13◄─►90	kimi-k2-0905-preview	1417	±21	764	Moonshot	Modified MIT
43	14◄─►87	grok-4-fast-reasoning	1417	±18	1,091	xAI	Proprietary
44	5◄─►104	deepseek-v3.1-terminus-thinking	1417	±40	203	DeepSeek	MIT
45	14◄─►82	gemini-2.5-flash-preview-09-2025	1416	±13	1,964	Google	Proprietary
46	14◄─►87	grok-4-1-fast-reasoning	1416	±17	1,262	xAI	Proprietary
47	13◄─►92	qwen3-vl-235b-a22b-instruct	1415	±23	718	Alibaba	Apache 2.0
48	6◄─►103	amazon-nova-experimental-chat-12-10	1415	±38	222	Amazon	Proprietary
49	13◄─►94	ernie-5.0-preview-1203	1414	±25	528	Baidu	Proprietary
50	14◄─►87	gpt-4.5-preview-2025-02-27	1414	±15	1,384	OpenAI	Proprietary
51	14◄─►87	gpt-5-mini-high	1414	±15	1,468	OpenAI	Proprietary
52	19◄─►82	gemini-2.5-flash	1414	±8	5,629	Google	Proprietary
53	10◄─►103	ernie-5.0-preview-1022	1413	±34	269	Baidu	Proprietary
54	17◄─►87	deepseek-r1	1413	±14	1,609	DeepSeek	MIT
55	13◄─►98	qwen3-vl-235b-a22b-thinking	1412	±29	422	Alibaba	Apache 2.0
56	19◄─►86	o1-2024-12-17	1412	±11	2,980	OpenAI	Proprietary
57	13◄─►99	minimax-m2.1-preview	1411	±28	435	MiniMax	MIT
58	19◄─►90	o3-mini-high	1410	±13	1,906	OpenAI	Proprietary
59	10◄─►108	hunyuan-t1-20250711	1408	±38	242	Tencent	Proprietary
60	14◄─►99	qwen3-235b-a22b-thinking-2507	1407	±24	507	Alibaba	Apache 2.0
61	21◄─►92	claude-sonnet-4-20250514-thinking-32k	1407	±12	2,134	Anthropic	Proprietary
62	21◄─►91	claude-opus-4-20250514	1406	±11	2,922	Anthropic	Proprietary
63	23◄─►92	mistral-medium-2508	1405	±10	3,484	Mistral	Proprietary
64	14◄─►105	qwen3-32b	1403	±30	316	Alibaba	Apache 2.0
65	23◄─►94	minimax-m1	1402	±13	2,017	MiniMax	Apache 2.0
66	27◄─►92	chatgpt-4o-latest-20250326	1402	±8	5,276	OpenAI	Proprietary
67	17◄─►104	amazon-nova-experimental-chat-11-10	1401	±25	526	Amazon	Proprietary
68	21◄─►100	deepseek-r1-0528	1400	±19	921	DeepSeek	MIT
69	21◄─►101	qwen3-next-80b-a3b-thinking	1400	±19	836	Alibaba	Apache 2.0
70	24◄─►96	qwen3-235b-a22b	1399	±14	1,649	Alibaba	Apache 2.0
71	13◄─►114	deepseek-v3.1-terminus	1399	±39	219	DeepSeek	MIT
72	21◄─►102	mai-1-preview	1399	±19	899	Microsoft AI	Proprietary
73	19◄─►106	mimo-v2-flash (non-thinking)	1399	±26	457	Xiaomi	MIT
74	26◄─►95	qwen3-235b-a22b-no-thinking	1398	±12	2,545	Alibaba	Apache 2.0
75	21◄─►103	amazon-nova-experimental-chat-10-20	1397	±20	811	Amazon	Proprietary
76	14◄─►114	nvidia-llama-3.3-nemotron-super-49b-v1.5	1397	±39	196	Nvidia	Nvidia Open
77	27◄─►97	claude-haiku-4-5-20251001	1397	±13	2,175	Anthropic	Proprietary
78	26◄─►100	glm-4.5-air	1396	±15	1,574	Z.ai	MIT
79	26◄─►104	grok-3-mini-high	1394	±18	1,012	xAI	Proprietary
80	30◄─►102	kimi-k2-0711-preview	1393	±14	1,800	Moonshot	Modified MIT
81	38◄─►101	claude-sonnet-4-20250514	1391	±11	2,627	Anthropic	Proprietary
82	38◄─►104	gpt-oss-120b	1389	±14	1,831	OpenAI	Apache 2.0
83	43◄─►103	claude-3-7-sonnet-20250219-thinking-32k	1389	±11	2,879	Anthropic	Proprietary
84	49◄─►103	o1-preview	1388	±9	4,570	OpenAI	Proprietary
85	21◄─►115	intellect-3	1388	±31	338	Prime Intellect	MIT
86	38◄─►107	qwen3-30b-a3b-instruct-2507	1387	±15	1,451	Alibaba	Apache 2.0
87	53◄─►103	o3-mini	1386	±8	4,826	OpenAI	Proprietary
88	21◄─►120	llama-3.1-nemotron-ultra-253b-v1	1382	±37	209	Nvidia	Nvidia Open Model
89	52◄─►110	qwen3-coder-480b-a35b-instruct	1381	±14	1,709	Alibaba	Apache 2.0
90	57◄─►108	grok-3-preview-02-24	1381	±11	2,781	xAI	Proprietary
91	60◄─►110	gpt-4.1-2025-04-14	1376	±10	3,371	OpenAI	Proprietary
92	61◄─►111	deepseek-v3-0324	1375	±10	3,296	DeepSeek	MIT
93	59◄─►114	grok-3-mini-beta	1374	±14	1,633	xAI	Proprietary
94	62◄─►114	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1372	±12	2,397	Google	Proprietary
95	63◄─►114	gemini-2.5-flash-lite-preview-06-17-thinking	1371	±12	2,196	Google	Proprietary
96	38◄─►120	step-3	1370	±31	349	StepFun	Apache 2.0
97	71◄─►114	qwen2.5-max	1370	±10	3,368	Alibaba	Proprietary
98	67◄─►115	qwq-32b	1368	±13	1,775	Alibaba	Apache 2.0
99	82◄─►114	o1-mini	1365	±7	7,502	OpenAI	Proprietary
100	57◄─►121	ling-flash-2.0	1364	±27	459	Ant Group	MIT
101	49◄─►126	glm-4.5v	1364	±34	277	Z.ai	MIT
102	49◄─►128	minimax-m2	1363	±35	303	MiniMax	Apache 2.0
103	83◄─►116	claude-3-7-sonnet-20250219	1363	±10	3,470	Anthropic	Proprietary
104	81◄─►120	qwen3-30b-a3b	1360	±13	1,796	Alibaba	Apache 2.0
105	86◄─►117	gemini-2.0-flash-001	1359	±9	4,183	Google	Proprietary
106	65◄─►123	nvidia-nemotron-3-nano-30b-a3b-bf16	1359	±23	680	Nvidia	NVIDIA Open Model
107	86◄─►120	gpt-4.1-mini-2025-04-14	1358	±11	2,807	OpenAI	Proprietary
108	88◄─►120	mistral-medium-2505	1354	±12	2,362	Mistral	Proprietary
109	69◄─►128	ring-flash-2.0	1353	±27	465	Ant Group	MIT
110	84◄─►125	hunyuan-turbos-20250416	1352	±19	881	Tencent	Proprietary
111	96◄─►120	claude-3-5-sonnet-20241022	1351	±6	10,169	Anthropic	Proprietary
112	77◄─►131	gpt-5-nano-high	1351	±26	501	OpenAI	Proprietary
113	89◄─►128	mistral-small-2506	1344	±17	1,093	Mistral	Apache 2.0
114	99◄─►121	claude-3-5-sonnet-20240620	1344	±7	11,360	Anthropic	Proprietary
115	89◄─►131	nova-2-lite	1343	±20	847	Amazon	Proprietary
116	89◄─►137	gpt-oss-20b	1341	±22	700	OpenAI	Apache 2.0
117	100◄─►125	gemini-1.5-pro-002	1341	±7	7,610	Google	Proprietary
118	106◄─►138	gemini-2.0-flash-lite-preview-02-05	1329	±10	2,804	Google	Proprietary
119	100◄─►148	qwen-plus-0125	1329	±19	733	Alibaba	Proprietary
120	109◄─►138	gemma-3-27b-it	1327	±9	3,709	Google	Gemma
121	109◄─►143	llama-4-maverick-17b-128e-instruct	1325	±11	2,968	Meta	Llama 4
122	98◄─►167	olmo-3-32b-think	1323	±32	317	Allen AI	Apache 2.0
123	112◄─►143	llama-3.1-405b-instruct-fp8	1322	±7	8,484	Meta	Llama 3.1 Community
124	100◄─►162	gemma-3-12b-it	1321	±27	389	Google	Gemma
125	115◄─►147	llama-3.1-405b-instruct-bf16	1318	±8	5,207	Meta	Llama 3.1 Community
126	108◄─►160	step-2-16k-exp-202412	1317	±20	640	StepFun	Proprietary
127	112◄─►153	llama-4-scout-17b-16e-instruct	1317	±13	2,041	Meta	Llama
128	115◄─►150	athene-v2-chat	1316	±9	3,413	NexusFlow	NexusFlow
129	115◄─►153	deepseek-v3	1315	±10	2,724	DeepSeek	DeepSeek
130	117◄─►148	claude-3-opus-20240229	1314	±6	25,771	Anthropic	Proprietary
131	117◄─►153	command-a-03-2025	1314	±9	4,126	Cohere	CC-BY-NC-4.0
132	118◄─►153	gpt-4o-2024-08-06	1311	±8	6,827	OpenAI	Proprietary
133	117◄─►155	yi-lightning	1310	±9	3,922	01 AI	Proprietary
134	111◄─►167	step-1o-turbo-202506	1309	±22	647	StepFun	Proprietary
135	117◄─►161	qwen2.5-plus-1127	1309	±13	1,406	Alibaba	Proprietary
136	122◄─►154	gpt-4o-2024-05-13	1308	±6	15,102	OpenAI	Proprietary
137	122◄─►158	gpt-4-1106-preview	1306	±7	13,306	OpenAI	Proprietary
138	120◄─►160	gemini-advanced-0514	1306	±9	6,393	Google	Proprietary
139	108◄─►179	hunyuan-turbos-20250226	1306	±31	238	Tencent	Proprietary
140	123◄─►161	gpt-4-0125-preview	1302	±7	12,375	OpenAI	Proprietary
141	117◄─►176	glm-4-plus-0111	1301	±19	720	Zhipu	Proprietary
142	125◄─►166	qwen2.5-72b-instruct	1300	±8	5,419	Alibaba	Qwen
143	125◄─►166	llama-3.3-70b-instruct	1300	±7	5,871	Meta	Llama-3.3
144	126◄─►166	gpt-4-turbo-2024-04-09	1299	±7	13,219	OpenAI	Proprietary
145	126◄─►167	gemini-1.5-pro-001	1298	±7	10,486	Google	Proprietary
146	117◄─►179	hunyuan-large-2025-02-10	1297	±24	497	Tencent	Proprietary
147	130◄─►167	grok-2-2024-08-13	1296	±7	8,953	xAI	Proprietary
148	122◄─►177	deepseek-v2.5-1210	1296	±17	1,033	DeepSeek	DeepSeek
149	126◄─►173	qwen-max-0919	1295	±12	2,250	Alibaba	Qwen
150	120◄─►180	hunyuan-standard-2025-02-10	1293	±24	499	Tencent	Proprietary
151	132◄─►173	gemini-1.5-flash-002	1291	±8	4,791	Google	Proprietary
152	120◄─►181	magistral-medium-2506	1291	±25	589	Mistral	Proprietary
153	133◄─►173	mistral-large-2407	1291	±8	6,662	Mistral	Mistral Research
154	132◄─►176	glm-4-plus	1291	±10	3,600	Zhipu AI	Proprietary
155	132◄─►176	deepseek-v2.5	1291	±9	3,651	DeepSeek	DeepSeek
156	120◄─►187	hunyuan-large-vision	1288	±29	375	Tencent	Proprietary
157	137◄─►176	claude-3-5-haiku-20241022	1287	±7	6,468	Anthropic	Proprietary
158	138◄─►179	mistral-large-2411	1285	±9	3,563	Mistral	MRL
159	138◄─►179	gpt-4-0314	1284	±9	7,050	OpenAI	Proprietary
160	120◄─►190	ibm-granite-h-small	1284	±31	364	IBM	Apache 2.0
161	122◄─►190	hunyuan-turbo-0110	1283	±31	243	Tencent	Proprietary
162	133◄─►184	llama-3.1-nemotron-70b-instruct	1282	±17	1,041	Nvidia	Llama 3.1
163	138◄─►180	mistral-small-3.1-24b-instruct-2503	1281	±13	2,241	Mistral	Apache 2.0
164	145◄─►179	gpt-4o-mini-2024-07-18	1279	±6	9,347	OpenAI	Proprietary
165	131◄─►189	gpt-4.1-nano-2025-04-14	1279	±23	582	OpenAI	Proprietary
166	145◄─►181	qwen2-72b-instruct	1276	±9	4,835	Alibaba	Qianwen LICENSE
167	145◄─►180	gpt-4-0613	1276	±8	11,183	OpenAI	Proprietary
168	148◄─►180	grok-2-mini-2024-08-13	1275	±7	7,264	xAI	Proprietary
169	138◄─►190	qwen2.5-coder-32b-instruct	1273	±19	725	Alibaba	Apache 2.0
170	135◄─►191	llama-3.1-nemotron-51b-instruct	1273	±22	507	Nvidia	Llama 3.1
171	145◄─►187	deepseek-coder-v2	1273	±13	1,858	DeepSeek	DeepSeek License
172	148◄─►185	amazon-nova-pro-v1.0	1273	±10	2,976	Amazon	Proprietary
173	152◄─►183	llama-3.1-70b-instruct	1272	±7	7,680	Meta	Llama 3.1 Community
174	145◄─►189	gemma-3n-e4b-it	1270	±14	1,674	Google	Gemma
175	153◄─►189	phi-4	1268	±10	2,756	Microsoft	MIT
176	141◄─►195	llama-3.1-tulu-3-70b	1267	±25	396	Ai2	Llama 3.1
177	153◄─►191	mistral-small-24b-instruct-2501	1264	±13	1,677	Mistral	Apache 2.0
178	158◄─►190	athene-70b-0725	1262	±10	2,921	NexusFlow	CC-BY-NC-4.0
179	164◄─►190	llama-3-70b-instruct	1259	±7	20,940	Meta	Llama 3 Community
180	164◄─►191	gemini-1.5-flash-001	1258	±8	8,387	Google	Proprietary
181	145◄─►203	gemma-3-4b-it	1257	±28	423	Google	Gemma
182	166◄─►191	claude-3-sonnet-20240229	1256	±8	13,761	Anthropic	Proprietary
183	162◄─►194	nemotron-4-340b-instruct	1256	±12	2,352	Nvidia	NVIDIA Open Model
184	148◄─►207	hunyuan-standard-256k	1254	±28	361	Tencent	Proprietary
185	165◄─►202	glm-4-0520	1250	±15	1,191	Zhipu AI	Proprietary
186	167◄─►202	reka-core-20240904	1248	±14	1,207	Reka AI	Proprietary
187	169◄─►199	amazon-nova-lite-v1.0	1248	±11	2,510	Amazon	Proprietary
188	167◄─►203	jamba-1.5-large	1247	±15	1,147	AI21 Labs	Jamba Open
189	172◄─►199	mistral-large-2402	1246	±9	7,987	Mistral	Proprietary
190	177◄─►197	gemma-2-27b-it	1246	±6	10,171	Google	Gemma license
191	181◄─►213	reka-flash-20240904	1234	±14	1,284	Reka AI	Proprietary
192	182◄─►208	c4ai-aya-expanse-32b	1234	±9	3,854	Cohere	CC-BY-NC-4.0
193	183◄─►207	claude-3-haiku-20240307	1233	±7	14,985	Anthropic	Proprietary
194	181◄─►215	command-r-plus-08-2024	1232	±14	1,467	Cohere	CC-BY-NC-4.0
195	183◄─►209	gemini-1.5-flash-8b-001	1231	±8	5,039	Google	Proprietary
196	169◄─►227	olmo-2-0325-32b-instruct	1231	±28	375	Allen AI	Apache-2.0
197	184◄─►210	mixtral-8x22b-instruct-v0.1	1230	±9	6,777	Mistral	Apache 2.0
198	184◄─►216	amazon-nova-micro-v1.0	1228	±11	2,454	Amazon	Proprietary
199	186◄─►220	qwen1.5-110b-chat	1224	±11	3,188	Alibaba	Qianwen LICENSE
200	188◄─►220	mistral-medium	1223	±10	4,406	Mistral	Proprietary
201	181◄─►230	qwq-32b-preview	1220	±24	481	Alibaba	Apache 2.0
202	190◄─►226	phi-3-medium-4k-instruct	1218	±10	3,238	Microsoft	MIT
203	192◄─►221	gemma-2-9b-it	1218	±7	7,111	Google	Gemma license
204	186◄─►230	ministral-8b-2410	1216	±20	683	Mistral	MRL
205	190◄─►226	yi-1.5-34b-chat	1216	±11	2,983	01 AI	Apache-2.0
206	194◄─►226	command-r-plus	1215	±8	9,769	Cohere	CC-BY-NC-4.0
207	190◄─►230	reka-flash-21b-20240226-online	1213	±14	2,028	Reka AI	Proprietary
208	196◄─►229	qwen1.5-72b-chat	1210	±9	5,325	Alibaba	Qianwen LICENSE
209	186◄─►233	llama-3.1-tulu-3-8b	1210	±26	361	Ai2	Llama 3.1
210	193◄─►230	internlm2_5-20b-chat	1210	±15	1,388	InternLM	Other
211	195◄─►230	command-r-08-2024	1207	±13	1,601	Cohere	CC-BY-NC-4.0
212	195◄─►230	gemma-2-9b-it-simpo	1205	±15	1,285	Princeton	MIT
213	197◄─►230	gpt-3.5-turbo-1106	1203	±15	2,134	OpenAI	Proprietary
214	198◄─►230	qwen1.5-32b-chat	1203	±11	2,649	Alibaba	Qianwen LICENSE
215	198◄─►231	c4ai-aya-expanse-8b	1202	±15	1,311	Cohere	CC-BY-NC-4.0
216	200◄─►230	reka-flash-21b-20240226	1201	±11	3,363	Reka AI	Proprietary
217	190◄─►239	granite-3.1-2b-instruct	1200	±26	393	IBM	Apache 2.0
218	201◄─►230	gpt-3.5-turbo-0125	1200	±8	8,625	OpenAI	Proprietary
219	198◄─►236	granite-3.0-8b-instruct	1198	±19	875	IBM	Apache 2.0
220	196◄─►237	zephyr-orpo-141b-A35b-v0.1	1198	±22	589	HuggingFace	Apache 2.0
221	198◄─►237	gemini-pro	1197	±19	993	Google	Proprietary
222	201◄─►232	dbrx-instruct-preview	1197	±11	4,002	Databricks	DBRX LICENSE
223	201◄─►234	phi-3-mini-4k-instruct-june-2024	1196	±13	1,568	Microsoft	MIT
224	201◄─►233	phi-3-small-8k-instruct	1196	±12	2,092	Microsoft	MIT
225	201◄─►236	gemini-pro-dev-api	1194	±14	2,274	Google	Proprietary
226	205◄─►231	llama-3-8b-instruct	1194	±7	14,251	Meta	Llama 3 Community
227	195◄─►245	granite-3.1-8b-instruct	1194	±28	385	IBM	Apache 2.0
228	206◄─►232	llama-3.1-8b-instruct	1194	±8	7,137	Meta	Llama 3.1 Community
229	205◄─►233	mixtral-8x7b-instruct-v0.1	1193	±8	9,662	Mistral	Apache 2.0
230	204◄─►241	jamba-1.5-mini	1188	±16	1,094	AI21 Labs	Jamba Open
231	220◄─►243	command-r	1176	±9	6,684	Cohere	CC-BY-NC-4.0
232	216◄─►248	granite-3.0-2b-instruct	1169	±19	907	IBM	Apache 2.0
233	224◄─►247	qwen1.5-14b-chat	1169	±13	2,184	Alibaba	Qianwen LICENSE
234	223◄─►248	llama-3.2-3b-instruct	1167	±16	1,136	Meta	Llama 3.2
235	228◄─►248	snowflake-arctic-instruct	1164	±11	4,793	Snowflake	Apache 2.0
236	230◄─►247	gemma-2-2b-it	1163	±8	6,603	Google	Gemma license
237	228◄─►250	starling-lm-7b-beta	1161	±14	1,973	Nexusflow	Apache-2.0
238	226◄─►256	wizardlm-70b	1160	±19	903	Microsoft	Llama 2 Community
239	229◄─►250	openchat-3.5-0106	1159	±13	1,726	OpenChat	Apache-2.0
240	230◄─►250	gemma-1.1-7b-it	1158	±11	3,039	Google	Gemma license
241	224◄─►256	deepseek-llm-67b-chat	1158	±23	576	DeepSeek	DeepSeek License
242	218◄─►264	smollm2-1.7b-instruct	1154	±33	271	HuggingFace	Apache 2.0
243	231◄─►256	yi-34b-chat	1154	±13	2,044	01 AI	Yi License
244	232◄─►256	phi-3-mini-4k-instruct	1153	±12	2,563	Microsoft	MIT
245	229◄─►259	openhermes-2.5-mistral-7b	1153	±20	697	NousResearch	Apache-2.0
246	231◄─►262	tulu-2-dpo-70b	1148	±19	888	AllenAI/UW	AI2 ImpACT Low-risk
247	234◄─►262	phi-3-mini-128k-instruct	1141	±13	2,813	Microsoft	MIT
248	237◄─►262	llama-2-70b-chat	1138	±10	4,740	Meta	Llama 2 Community
249	240◄─►265	mistral-7b-instruct-v0.2	1130	±12	2,605	Mistral	Apache-2.0
250	240◄─►266	starling-lm-7b-alpha	1129	±15	1,300	UC Berkeley	CC-BY-NC-4.0
251	240◄─►266	llama-3.2-1b-instruct	1127	±16	1,162	Meta	Llama 3.2
252	232◄─►272	dolphin-2.2.1-mistral-7b	1127	±32	219	Cognitive Computations	Apache-2.0
253	237◄─►268	qwen-14b-chat	1126	±23	534	Alibaba	Qianwen LICENSE
254	240◄─►266	openchat-3.5	1126	±18	945	OpenChat	Apache-2.0
255	240◄─►268	qwen1.5-7b-chat	1123	±20	690	Alibaba	Qianwen LICENSE
256	245◄─►267	vicuna-33b	1118	±12	2,663	LMSYS	Non-commercial
257	240◄─►273	llama2-70b-steerlm-chat	1117	±27	440	Nvidia	Llama 2 Community
258	244◄─►271	gemma-7b-it	1117	±16	1,120	Google	Gemma license
259	244◄─►272	palm-2	1114	±19	901	Google	Proprietary
260	248◄─►271	llama-2-13b-chat	1112	±13	2,218	Meta	Llama 2 Community
261	244◄─►273	solar-10.7b-instruct-v1.0	1111	±22	604	Upstage AI	CC-BY-NC-4.0
262	245◄─►273	codellama-34b-instruct	1110	±19	770	Meta	Llama 2 Community
263	248◄─►273	gemma-1.1-2b-it	1106	±16	1,355	Google	Gemma license
264	245◄─►277	mpt-30b-chat	1097	±34	242	MosaicML	CC-BY-NC-SA-4.0
265	249◄─►275	nous-hermes-2-mixtral-8x7b-dpo	1097	±21	628	NousResearch	Apache-2.0
266	256◄─►275	llama-2-7b-chat	1088	±14	1,656	Meta	Llama 2 Community
267	254◄─►276	qwen1.5-4b-chat	1086	±17	988	Alibaba	Qianwen LICENSE
268	253◄─►277	stripedhyena-nous-7b	1086	±20	676	Together AI	Apache 2.0
269	256◄─►276	zephyr-7b-beta	1085	±17	1,250	HuggingFace	MIT
270	258◄─►275	vicuna-13b	1084	±13	2,146	LMSYS	Llama 2 Community
271	256◄─►277	mistral-7b-instruct	1083	±19	974	Mistral	Apache 2.0
272	250◄─►277	guanaco-33b	1082	±32	280	UW	Non-commercial
273	260◄─►277	gemma-2b-it	1069	±22	596	Google	Gemma license
274	264◄─►277	wizardlm-13b	1066	±20	669	Microsoft	Llama 2 Community
275	264◄─►277	olmo-7b-instruct	1057	±19	848	Allen AI	Apache-2.0
276	267◄─►278	vicuna-7b	1049	±21	658	LMSYS	Llama 2 Community
277	269◄─►278	chatglm3-6b	1043	±23	576	Tsinghua	Apache-2.0
278	276◄─►286	gpt4all-13b-snoozy	999	±37	211	Nomic AI	Non-commercial
279	278◄─►286	alpaca-13b	989	±23	652	Stanford	Non-commercial
280	278◄─►286	mpt-7b-chat	984	±25	471	MosaicML	CC-BY-NC-SA-4.0
281	278◄─►286	RWKV-4-Raven-14B	983	±24	544	RWKV	Apache 2.0
282	278◄─►286	koala-13b	982	±21	751	UC Berkeley	Non-commercial
283	278◄─►286	chatglm-6b	978	±25	525	Tsinghua	Non-commercial
284	278◄─►288	chatglm2-6b	972	±35	227	Tsinghua	Apache-2.0
285	278◄─►288	oasst-pythia-12b	959	±22	687	OpenAssistant	Apache 2.0
286	278◄─►289	dolly-v2-12b	948	±29	370	Databricks	MIT
287	284◄─►289	fastchat-t5-3b	920	±26	462	LMSYS	Apache 2.0
288	284◄─►289	llama-13b	917	±33	252	Meta	Non-commercial
289	286◄─►289	stablelm-tuned-alpha-7b	892	±29	353	Stability AI	CC-BY-NC-SA-4.0

Text Arena

Default Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

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)