Text Arena

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

Last Updated

Jan 9, 2026

Total Votes

854,203

Total Models

289

/

Style Control

	Rank Spread
1	1◄─►2	claude-opus-4-5-20251101-thinking-32k	1542	±11	3,418	Anthropic	Proprietary
2	1◄─►7	claude-sonnet-4-5-20250929-thinking-32k	1524	±8	7,641	Anthropic	Proprietary
3	2◄─►10	gemini-3-pro	1519	±9	5,267	Google	Proprietary
4	2◄─►11	claude-opus-4-5-20251101	1516	±11	3,747	Anthropic	Proprietary
5	2◄─►10	claude-opus-4-1-20250805-thinking-16k	1514	±7	9,912	Anthropic	Proprietary
6	2◄─►16	grok-4.1-thinking	1508	±9	5,062	xAI	Proprietary
7	3◄─►16	claude-sonnet-4-5-20250929	1506	±8	6,731	Anthropic	Proprietary
8	2◄─►18	gemini-3-flash	1504	±13	2,075	Google	Proprietary
9	5◄─►16	claude-opus-4-1-20250805	1501	±6	12,876	Anthropic	Proprietary
10	3◄─►23	gemini-3-flash (thinking-minimal)	1499	±17	1,182	Google	Proprietary
11	6◄─►19	claude-opus-4-20250514-thinking-16k	1495	±8	6,711	Anthropic	Proprietary
12	3◄─►31	gpt-5.2-high	1494	±17	1,277	OpenAI	Proprietary
13	6◄─►22	grok-4.1	1493	±9	5,788	xAI	Proprietary
14	6◄─►23	gpt-5.1-high	1492	±10	4,258	OpenAI	Proprietary
15	6◄─►38	glm-4.7	1487	±16	1,399	Z.ai	MIT
16	9◄─►35	kimi-k2-thinking-turbo	1484	±9	4,758	Moonshot	Modified MIT
17	6◄─►62	gpt-5.2	1478	±26	526	OpenAI	Proprietary
18	11◄─►44	gpt-5.1	1477	±9	4,775	OpenAI	Proprietary
19	10◄─►51	qwen3-max-2025-09-23	1475	±13	2,033	Alibaba	Proprietary
20	12◄─►45	claude-haiku-4-5-20251001	1475	±8	7,402	Anthropic	Proprietary
21	11◄─►51	longcat-flash-chat	1474	±13	2,245	Meituan	MIT
22	11◄─►54	deepseek-v3.2-exp-thinking	1472	±13	1,915	DeepSeek AI	MIT
23	14◄─►52	gpt-5-high	1470	±8	6,455	OpenAI	Proprietary
24	15◄─►51	claude-sonnet-4-20250514-thinking-32k	1469	±8	6,479	Anthropic	Proprietary
25	15◄─►50	qwen3-235b-a22b-instruct-2507	1469	±6	11,715	Alibaba	Apache 2.0
26	14◄─►56	deepseek-v3.2-exp	1469	±12	2,519	DeepSeek AI	MIT
27	16◄─►49	gemini-2.5-pro	1469	±6	16,221	Google	Proprietary
28	14◄─►57	mistral-large-3	1468	±11	2,897	Mistral	Apache 2.0
29	14◄─►58	deepseek-v3.2	1467	±11	3,497	DeepSeek AI	MIT
30	14◄─►62	kimi-k2-0905-preview	1466	±13	2,259	Moonshot	Modified MIT
31	14◄─►64	ernie-5.0-preview-1203	1465	±16	1,380	Baidu	Proprietary
32	14◄─►64	ernie-5.0-preview-1103	1464	±14	1,676	Baidu	Proprietary
33	15◄─►62	deepseek-v3.2-thinking	1464	±12	2,387	DeepSeek AI	MIT
34	17◄─►55	chatgpt-4o-latest-20250326	1464	±6	13,636	OpenAI	Proprietary
35	15◄─►64	qwen3-vl-235b-a22b-instruct	1463	±13	2,334	Alibaba	Apache 2.0
36	9◄─►82	qwen3-max-preview	1463	±31	330	Alibaba	Proprietary
37	16◄─►62	deepseek-r1-0528	1462	±11	2,775	DeepSeek	MIT
38	17◄─►61	claude-opus-4-20250514	1462	±7	7,979	Anthropic	Proprietary
39	17◄─►62	glm-4.6	1461	±8	6,609	Z.ai	MIT
40	18◄─►62	gpt-5-chat	1460	±8	6,008	OpenAI	Proprietary
41	19◄─►64	kimi-k2-0711-preview	1458	±8	5,300	Moonshot	Modified MIT
42	14◄─►79	deepseek-v3.1-terminus-thinking	1458	±24	638	DeepSeek AI	MIT
43	17◄─►66	gpt-4.5-preview-2025-02-27	1457	±13	1,944	OpenAI	Proprietary
44	21◄─►63	o3-2025-04-16	1457	±6	11,905	OpenAI	Proprietary
45	16◄─►70	minimax-m2.1-preview	1457	±17	1,195	MiniMax	MIT
46	17◄─►67	deepseek-v3.1-thinking	1456	±13	1,894	DeepSeek	MIT
47	19◄─►66	qwen3-coder-480b-a35b-instruct	1455	±9	4,973	Alibaba	Apache 2.0
48	17◄─►72	grok-4-fast-chat	1455	±16	1,258	xAI	Proprietary
49	20◄─►66	glm-4.5	1454	±9	4,772	Z.ai	MIT
50	25◄─►65	gpt-4.1-2025-04-14	1454	±7	9,384	OpenAI	Proprietary
51	19◄─►67	grok-4-1-fast-reasoning	1454	±10	3,767	xAI	Proprietary
52	25◄─►65	mistral-medium-2508	1453	±6	10,868	Mistral	Proprietary
53	19◄─►72	qwen3-vl-235b-a22b-thinking	1453	±14	1,623	Alibaba	Apache 2.0
54	28◄─►67	claude-3-7-sonnet-20250219-thinking-32k	1449	±8	6,242	Anthropic	Proprietary
55	26◄─►77	deepseek-v3.1	1447	±12	2,638	DeepSeek	MIT
56	31◄─►72	claude-sonnet-4-20250514	1446	±7	7,495	Anthropic	Proprietary
57	30◄─►74	qwen3-next-80b-a3b-instruct	1446	±9	4,809	Alibaba	Apache 2.0
58	37◄─►77	qwen3-235b-a22b-no-thinking	1443	±8	7,043	Alibaba	Apache 2.0
59	30◄─►82	deepseek-r1	1443	±12	2,336	DeepSeek	MIT
60	38◄─►79	grok-3-preview-02-24	1442	±8	5,498	xAI	Proprietary
61	30◄─►86	qwen3-235b-a22b-thinking-2507	1441	±15	1,629	Alibaba	Apache 2.0
62	29◄─►87	mimo-v2-flash (non-thinking)	1441	±16	1,318	Xiaomi	MIT
63	44◄─►83	qwen3-30b-a3b-instruct-2507	1438	±9	4,669	Alibaba	Apache 2.0
64	42◄─►83	grok-4-fast-reasoning	1438	±9	3,953	xAI	Proprietary
65	27◄─►97	deepseek-v3.1-terminus	1437	±21	773	DeepSeek AI	MIT
66	24◄─►100	hunyuan-vision-1.5-thinking	1434	±27	432	Tencent	Proprietary
67	51◄─►86	grok-4-0709	1433	±7	8,275	xAI	Proprietary
68	50◄─►86	gpt-4.1-mini-2025-04-14	1432	±7	7,022	OpenAI	Proprietary
69	50◄─►89	qwen3-235b-a22b	1432	±9	4,388	Alibaba	Apache 2.0
70	47◄─►91	o3-mini-high	1432	±11	2,602	OpenAI	Proprietary
71	55◄─►86	claude-3-5-sonnet-20241022	1431	±5	15,088	Anthropic	Proprietary
72	50◄─►91	o1-2024-12-17	1430	±9	3,989	OpenAI	Proprietary
73	54◄─►90	mistral-medium-2505	1430	±8	5,925	Mistral	Proprietary
74	55◄─►89	o4-mini-2025-04-16	1430	±7	8,832	OpenAI	Proprietary
75	54◄─►91	gpt-5-mini-high	1429	±9	5,557	OpenAI	Proprietary
76	51◄─►95	mai-1-preview	1429	±11	2,783	Microsoft AI	Proprietary
77	57◄─►93	claude-3-7-sonnet-20250219	1428	±7	7,243	Anthropic	Proprietary
78	59◄─►95	glm-4.5-air	1426	±8	6,163	Z.ai	MIT
79	59◄─►95	deepseek-v3-0324	1425	±7	8,448	DeepSeek	MIT
80	59◄─►96	gemini-2.5-flash-preview-09-2025	1425	±8	6,876	Google	Proprietary
81	57◄─►98	qwen3-next-80b-a3b-thinking	1423	±11	2,687	Alibaba	Apache 2.0
82	63◄─►96	gemini-2.5-flash	1423	±6	15,626	Google	Proprietary
83	55◄─►101	amazon-nova-experimental-chat-11-10	1422	±15	1,493	Amazon	Proprietary
84	68◄─►99	minimax-m1	1417	±8	6,627	MiniMax	Apache 2.0
85	68◄─►101	o1-preview	1415	±9	5,137	OpenAI	Proprietary
86	75◄─►100	o3-mini	1414	±6	9,568	OpenAI	Proprietary
87	63◄─►105	ling-flash-2.0	1413	±15	1,546	Ant Group	MIT
88	70◄─►103	mistral-small-2506	1412	±10	3,371	Mistral	Apache 2.0
89	74◄─►109	amazon-nova-experimental-chat-10-20	1408	±12	2,330	Amazon	Proprietary
90	67◄─►125	intellect-3	1406	±19	988	Prime Intellect	MIT
91	61◄─►126	qwen3-32b	1405	±25	513	Alibaba	Apache 2.0
92	74◄─►125	step-3	1404	±17	1,236	StepFun	Apache 2.0
93	71◄─►125	glm-4.5v	1403	±19	987	Z.ai	MIT
94	83◄─►118	qwen2.5-max	1400	±8	5,201	Alibaba	Proprietary
95	63◄─►141	hunyuan-turbos-20250226	1397	±31	277	Tencent	Proprietary
96	82◄─►125	nova-2-lite	1397	±12	2,524	Amazon	Proprietary
97	80◄─►129	hunyuan-t1-20250711	1397	±20	811	Tencent	Proprietary
98	78◄─►134	nvidia-llama-3.3-nemotron-super-49b-v1.5	1396	±22	674	Nvidia	Nvidia Open
99	87◄─►124	claude-3-5-sonnet-20240620	1395	±7	13,637	Anthropic	Proprietary
100	88◄─►125	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1393	±7	7,692	Google	Proprietary
101	85◄─►128	hunyuan-turbos-20250416	1393	±14	1,811	Tencent	Proprietary
102	75◄─►147	llama-3.1-nemotron-ultra-253b-v1	1390	±30	367	Nvidia	Nvidia Open Model
103	87◄─►134	ring-flash-2.0	1389	±15	1,543	Ant Group	MIT
104	89◄─►126	gpt-oss-120b	1389	±8	6,530	OpenAI	Apache 2.0
105	81◄─►143	amazon-nova-experimental-chat-10-09	1388	±24	558	Amazon	Proprietary
106	90◄─►126	command-a-03-2025	1388	±6	10,344	Cohere	CC-BY-NC-4.0
107	89◄─►129	grok-3-mini-high	1387	±10	3,356	xAI	Proprietary
108	90◄─►132	deepseek-v3	1386	±10	3,299	DeepSeek	DeepSeek
109	90◄─►129	o1-mini	1386	±7	8,495	OpenAI	Proprietary
110	89◄─►134	magistral-medium-2506	1385	±12	2,292	Mistral	Proprietary
111	90◄─►132	qwen3-30b-a3b	1384	±9	4,595	Alibaba	Apache 2.0
112	90◄─►133	grok-3-mini-beta	1384	±9	4,318	xAI	Proprietary
113	90◄─►133	qwq-32b	1384	±9	4,097	Alibaba	Apache 2.0
114	91◄─►132	gemini-2.5-flash-lite-preview-06-17-thinking	1384	±8	6,106	Google	Proprietary
115	91◄─►129	claude-3-5-haiku-20241022	1383	±6	11,322	Anthropic	Proprietary
116	90◄─►142	gpt-5-nano-high	1381	±15	1,674	OpenAI	Proprietary
117	90◄─►149	qwen-plus-0125	1377	±18	896	Alibaba	Proprietary
118	91◄─►144	minimax-m2	1377	±15	1,636	MiniMax	Apache 2.0
119	91◄─►152	deepseek-v2.5-1210	1373	±17	1,084	DeepSeek	DeepSeek
120	91◄─►153	gpt-4.1-nano-2025-04-14	1372	±19	808	OpenAI	Proprietary
121	100◄─►143	llama-3.1-405b-instruct-bf16	1372	±7	6,274	Meta	Llama 3.1 Community
122	101◄─►143	llama-4-maverick-17b-128e-instruct	1371	±7	7,089	Meta	Llama 4
123	88◄─►168	hunyuan-turbo-0110	1370	±30	304	Tencent	Proprietary
124	97◄─►152	gpt-oss-20b	1369	±13	2,130	OpenAI	Apache 2.0
125	92◄─►161	step-2-16k-exp-202412	1368	±20	742	StepFun	Proprietary
126	89◄─►168	mercury	1368	±28	406	Inception AI	Proprietary
127	105◄─►151	yi-lightning	1367	±10	4,320	01 AI	Proprietary
128	112◄─►147	gpt-4o-2024-05-13	1367	±6	19,568	OpenAI	Proprietary
129	108◄─►151	athene-v2-chat	1367	±9	4,028	NexusFlow	NexusFlow
130	110◄─►151	deepseek-v2.5	1366	±9	4,262	DeepSeek	DeepSeek
131	113◄─►150	llama-3.1-405b-instruct-fp8	1365	±7	9,742	Meta	Llama 3.1 Community
132	91◄─►168	hunyuan-large-2025-02-10	1365	±25	521	Tencent	Proprietary
133	105◄─►160	nvidia-nemotron-3-nano-30b-a3b-bf16	1363	±14	1,935	Nvidia	NVIDIA Open Model
134	113◄─►152	gemini-2.0-flash-001	1363	±7	7,107	Google	Proprietary
135	90◄─►171	llama-3.3-nemotron-49b-super-v1	1362	±31	287	Nvidia	Nvidia
136	100◄─►165	olmo-3-32b-think	1362	±19	1,060	Allen AI	Apache 2.0
137	113◄─►154	llama-4-scout-17b-16e-instruct	1361	±9	5,306	Meta	Llama
138	113◄─►157	mistral-small-3.1-24b-instruct-2503	1359	±8	6,216	Mistral	Apache 2.0
139	115◄─►156	gemma-3-27b-it	1359	±7	8,301	Google	Gemma
140	114◄─►159	gpt-4o-2024-08-06	1359	±8	7,329	OpenAI	Proprietary
141	105◄─►168	hunyuan-large-vision	1357	±19	984	Tencent	Proprietary
142	118◄─►159	grok-2-2024-08-13	1357	±7	10,386	xAI	Proprietary
143	113◄─►166	qwen2.5-plus-1127	1355	±14	1,556	Alibaba	Proprietary
144	113◄─►167	step-1o-turbo-202506	1355	±15	1,569	StepFun	Proprietary
145	119◄─►161	gemini-1.5-pro-002	1355	±7	9,194	Google	Proprietary
146	119◄─►162	qwen2.5-72b-instruct	1353	±7	6,697	Alibaba	Qwen
147	126◄─►163	claude-3-opus-20240229	1351	±6	33,838	Anthropic	Proprietary
148	123◄─►165	mistral-large-2407	1351	±8	7,610	Mistral	Mistral Research
149	119◄─►168	qwen-max-0919	1350	±11	2,764	Alibaba	Qwen
150	121◄─►166	glm-4-plus	1350	±9	4,460	Zhipu AI	Proprietary
151	121◄─►169	athene-70b-0725	1348	±11	3,135	NexusFlow	CC-BY-NC-4.0
152	129◄─►166	gpt-4o-mini-2024-07-18	1347	±6	10,981	OpenAI	Proprietary
153	130◄─►168	gemini-1.5-pro-001	1345	±7	12,782	Google	Proprietary
154	133◄─►169	gpt-4-turbo-2024-04-09	1344	±7	17,155	OpenAI	Proprietary
155	131◄─►170	mistral-large-2411	1343	±9	4,244	Mistral	MRL
156	135◄─►169	llama-3.3-70b-instruct	1343	±6	8,858	Meta	Llama-3.3
157	132◄─►171	gemini-2.0-flash-lite-preview-02-05	1342	±10	3,485	Google	Proprietary
158	122◄─►177	qwen2.5-coder-32b-instruct	1340	±19	873	Alibaba	Apache 2.0
159	136◄─►171	amazon-nova-pro-v1.0	1340	±9	3,875	Amazon	Proprietary
160	133◄─►174	deepseek-coder-v2	1339	±12	2,676	DeepSeek AI	DeepSeek License
161	139◄─►174	gemini-advanced-0514	1336	±9	8,170	Google	Proprietary
162	140◄─►172	gpt-4-1106-preview	1336	±7	15,648	OpenAI	Proprietary
163	145◄─►174	grok-2-mini-2024-08-13	1333	±7	8,664	xAI	Proprietary
164	152◄─►175	llama-3.1-70b-instruct	1331	±7	9,422	Meta	Llama 3.1 Community
165	138◄─►186	glm-4-plus-0111	1329	±18	896	Zhipu	Proprietary
166	131◄─►189	hunyuan-standard-2025-02-10	1329	±24	549	Tencent	Proprietary
167	155◄─►180	gpt-4-0125-preview	1328	±7	15,337	OpenAI	Proprietary
168	140◄─►187	ibm-granite-h-small	1327	±17	1,270	IBM	Apache 2.0
169	142◄─►186	llama-3.1-nemotron-70b-instruct	1327	±15	1,313	Nvidia	Llama 3.1
170	156◄─►183	gpt-4-0314	1325	±9	8,336	OpenAI	Proprietary
171	146◄─►197	gemma-3-12b-it	1317	±23	545	Google	Gemma
172	165◄─►189	claude-3-sonnet-20240229	1314	±7	18,944	Anthropic	Proprietary
173	164◄─►189	gemini-1.5-flash-002	1314	±8	5,909	Google	Proprietary
174	160◄─►196	reka-core-20240904	1313	±15	1,221	Reka AI	Proprietary
175	165◄─►193	gemma-3n-e4b-it	1311	±10	3,621	Google	Gemma
176	164◄─►195	mistral-small-24b-instruct-2501	1310	±12	2,094	Mistral	Apache 2.0
177	166◄─►192	gpt-4-0613	1310	±8	13,770	OpenAI	Proprietary
178	163◄─►197	jamba-1.5-large	1310	±14	1,442	AI21 Labs	Jamba Open
179	159◄─►200	llama-3.1-nemotron-51b-instruct	1308	±22	665	Nvidia	Llama 3.1
180	166◄─►193	gemini-1.5-flash-001	1308	±8	10,699	Google	Proprietary
181	160◄─►204	llama-3.1-tulu-3-70b	1305	±24	452	Ai2	Llama 3.1
182	166◄─►197	glm-4-0520	1305	±14	1,728	Zhipu AI	Proprietary
183	167◄─►197	phi-4	1304	±10	3,320	Microsoft	MIT
184	167◄─►197	nemotron-4-340b-instruct	1304	±11	3,275	Nvidia	NVIDIA Open Model
185	170◄─►196	gemma-2-27b-it	1304	±6	12,115	Google	Gemma license
186	170◄─►196	llama-3-70b-instruct	1303	±7	28,216	Meta	Llama 3 Community
187	167◄─►197	amazon-nova-lite-v1.0	1303	±10	3,093	Amazon	Proprietary
188	173◄─►197	claude-3-haiku-20240307	1298	±7	20,968	Anthropic	Proprietary
189	165◄─►213	hunyuan-standard-256k	1297	±25	499	Tencent	Proprietary
190	174◄─►203	qwen2-72b-instruct	1293	±9	6,267	Alibaba	Qianwen LICENSE
191	176◄─►203	mistral-large-2402	1291	±8	10,458	Mistral	Proprietary
192	176◄─►204	c4ai-aya-expanse-32b	1290	±9	4,696	Cohere	CC-BY-NC-4.0
193	173◄─►211	reka-flash-20240904	1288	±15	1,210	Reka AI	Proprietary
194	180◄─►211	amazon-nova-micro-v1.0	1285	±10	2,998	Amazon	Proprietary
195	169◄─►221	granite-3.1-8b-instruct	1285	±26	484	IBM	Apache 2.0
196	187◄─►219	command-r-08-2024	1277	±13	1,788	Cohere	CC-BY-NC-4.0
197	173◄─►225	olmo-2-0325-32b-instruct	1277	±27	431	Allen AI	Apache-2.0
198	187◄─►219	command-r-plus-08-2024	1277	±14	1,680	Cohere	CC-BY-NC-4.0
199	188◄─►218	qwen1.5-110b-chat	1276	±10	4,790	Alibaba	Qianwen LICENSE
200	177◄─►225	gemma-3-4b-it	1274	±24	607	Google	Gemma
201	188◄─►220	reka-flash-21b-20240226-online	1274	±13	2,898	Reka AI	Proprietary
202	190◄─►219	mixtral-8x22b-instruct-v0.1	1273	±9	8,819	Mistral	Apache 2.0
203	187◄─►225	ministral-8b-2410	1272	±19	840	Mistral	MRL
204	188◄─►223	gemma-2-9b-it-simpo	1271	±15	1,478	Princeton	MIT
205	192◄─►220	qwen1.5-72b-chat	1271	±10	6,381	Alibaba	Qianwen LICENSE
206	192◄─►219	gpt-3.5-turbo-0125	1271	±8	11,175	OpenAI	Proprietary
207	192◄─►219	gemini-1.5-flash-8b-001	1270	±8	6,088	Google	Proprietary
208	192◄─►219	gemma-2-9b-it	1269	±7	8,942	Google	Gemma license
209	192◄─►220	command-r-plus	1269	±8	13,991	Cohere	CC-BY-NC-4.0
210	192◄─►227	jamba-1.5-mini	1263	±15	1,351	AI21 Labs	Jamba Open
211	194◄─►225	reka-flash-21b-20240226	1263	±11	4,769	Reka AI	Proprietary
212	195◄─►228	mistral-medium	1258	±10	5,162	Mistral	Proprietary
213	195◄─►228	qwen1.5-32b-chat	1257	±11	3,942	Alibaba	Qianwen LICENSE
214	194◄─►230	gpt-3.5-turbo-1106	1257	±16	2,125	OpenAI	Proprietary
215	196◄─►226	llama-3.1-8b-instruct	1257	±7	8,605	Meta	Llama 3.1 Community
216	195◄─►230	c4ai-aya-expanse-8b	1254	±14	1,574	Cohere	CC-BY-NC-4.0
217	192◄─►236	llama-3.1-tulu-3-8b	1251	±25	479	Ai2	Llama 3.1
218	206◄─►230	llama-3-8b-instruct	1250	±7	18,445	Meta	Llama 3 Community
219	195◄─►237	granite-3.1-2b-instruct	1247	±24	514	IBM	Apache 2.0
220	206◄─►233	dbrx-instruct-preview	1247	±11	5,532	Databricks	DBRX LICENSE
221	205◄─►233	internlm2_5-20b-chat	1246	±14	1,693	InternLM	Other
222	195◄─►238	gemini-pro	1245	±24	678	Google	Proprietary
223	207◄─►233	yi-1.5-34b-chat	1244	±10	3,856	01 AI	Apache-2.0
224	202◄─►238	zephyr-orpo-141b-A35b-v0.1	1241	±21	833	HuggingFace	Apache 2.0
225	213◄─►235	command-r	1239	±9	9,680	Cohere	CC-BY-NC-4.0
226	211◄─►238	gemini-pro-dev-api	1236	±14	2,688	Google	Proprietary
227	207◄─►239	granite-3.0-8b-instruct	1236	±18	1,114	IBM	Apache 2.0
228	212◄─►237	qwen1.5-14b-chat	1236	±13	3,224	Alibaba	Qianwen LICENSE
229	215◄─►235	mixtral-8x7b-instruct-v0.1	1235	±8	11,818	Mistral	Apache 2.0
230	215◄─►239	starling-lm-7b-beta	1232	±13	2,965	Nexusflow	Apache-2.0
231	218◄─►240	phi-3-medium-4k-instruct	1227	±10	3,989	Microsoft	MIT
232	218◄─►243	openchat-3.5-0106	1225	±14	2,008	OpenChat	Apache-2.0
233	221◄─►243	snowflake-arctic-instruct	1220	±11	5,752	Snowflake	Apache 2.0
234	224◄─►247	gemma-1.1-7b-it	1214	±10	4,361	Google	Gemma license
235	218◄─►255	deepseek-llm-67b-chat	1214	±24	650	DeepSeek AI	DeepSeek License
236	221◄─►256	tulu-2-dpo-70b	1210	±21	805	AllenAI/UW	AI2 ImpACT Low-risk
237	223◄─►257	qwen1.5-7b-chat	1206	±21	773	Alibaba	Qianwen LICENSE
238	226◄─►257	granite-3.0-2b-instruct	1205	±18	1,135	IBM	Apache 2.0
239	229◄─►257	starling-lm-7b-alpha	1203	±16	1,398	UC Berkeley	CC-BY-NC-4.0
240	232◄─►257	yi-34b-chat	1201	±13	2,350	01 AI	Yi License
241	232◄─►255	phi-3-small-8k-instruct	1201	±12	3,238	Microsoft	MIT
242	231◄─►260	openchat-3.5	1198	±20	974	OpenChat	Apache-2.0
243	234◄─►260	phi-3-mini-4k-instruct-june-2024	1194	±14	1,851	Microsoft	MIT
244	235◄─►257	gemma-2-2b-it	1192	±8	7,316	Google	Gemma license
245	232◄─►266	qwen-14b-chat	1192	±24	599	Alibaba	Qianwen LICENSE
246	235◄─►260	vicuna-33b	1189	±13	2,880	LMSYS	Non-commercial
247	234◄─►266	wizardlm-70b	1187	±20	994	Microsoft	Llama 2 Community
248	235◄─►262	phi-3-mini-4k-instruct	1184	±12	3,466	Microsoft	MIT
249	234◄─►270	openhermes-2.5-mistral-7b	1182	±23	590	NousResearch	Apache-2.0
250	235◄─►263	mistral-7b-instruct-v0.2	1182	±12	3,126	Mistral	Apache-2.0
251	234◄─►271	solar-10.7b-instruct-v1.0	1179	±27	483	Upstage AI	CC-BY-NC-4.0
252	243◄─►267	llama-2-70b-chat	1174	±10	5,730	Meta	Llama 2 Community
253	237◄─►270	llama-3.2-3b-instruct	1173	±16	1,352	Meta	Llama 3.2
254	235◄─►272	qwq-32b-preview	1171	±24	566	Alibaba	Apache 2.0
255	235◄─►272	nous-hermes-2-mixtral-8x7b-dpo	1171	±24	576	NousResearch	Apache-2.0
256	243◄─►271	gemma-1.1-2b-it	1169	±14	1,968	Google	Gemma license
257	243◄─►272	gemma-7b-it	1166	±17	1,387	Google	Gemma license
258	235◄─►276	zephyr-7b-alpha	1164	±40	202	HuggingFace	MIT
259	235◄─►275	mpt-30b-chat	1162	±35	259	MosaicML	CC-BY-NC-SA-4.0
260	246◄─►273	vicuna-13b	1159	±14	2,398	LMSYS	Llama 2 Community
261	247◄─►272	llama-2-13b-chat	1158	±13	2,636	Meta	Llama 2 Community
262	238◄─►276	smollm2-1.7b-instruct	1156	±33	355	HuggingFace	Apache 2.0
263	246◄─►275	codellama-34b-instruct	1155	±20	855	Meta	Llama 2 Community
264	251◄─►275	phi-3-mini-128k-instruct	1151	±13	3,914	Microsoft	MIT
265	248◄─►275	palm-2	1148	±21	921	Google	Proprietary
266	250◄─►275	zephyr-7b-beta	1147	±18	1,258	HuggingFace	MIT
267	248◄─►276	wizardlm-13b	1146	±22	737	Microsoft	Llama 2 Community
268	251◄─►275	llama-3.2-1b-instruct	1146	±16	1,347	Meta	Llama 3.2
269	248◄─►276	llama2-70b-steerlm-chat	1141	±28	467	Nvidia	Llama 2 Community
270	251◄─►276	mistral-7b-instruct	1140	±20	1,034	Mistral	Apache 2.0
271	253◄─►277	gemma-2b-it	1133	±22	744	Google	Gemma license
272	255◄─►278	vicuna-7b	1126	±23	729	LMSYS	Llama 2 Community
273	260◄─►278	qwen1.5-4b-chat	1126	±17	1,288	Alibaba	Qianwen LICENSE
274	260◄─►278	stripedhyena-nous-7b	1121	±22	708	Together AI	Apache 2.0
275	259◄─►281	guanaco-33b	1109	±36	265	UW	Non-commercial
276	266◄─►281	olmo-7b-instruct	1103	±22	775	Allen AI	Apache-2.0
277	271◄─►280	llama-2-7b-chat	1099	±14	1,959	Meta	Llama 2 Community
278	272◄─►283	chatglm3-6b	1084	±26	537	Tsinghua	Apache-2.0
279	275◄─►285	mpt-7b-chat	1061	±32	397	MosaicML	CC-BY-NC-SA-4.0
280	275◄─►284	koala-13b	1061	±24	748	UC Berkeley	Non-commercial
281	276◄─►285	RWKV-4-Raven-14B	1054	±27	507	RWKV	Apache 2.0
282	278◄─►286	oasst-pythia-12b	1045	±25	714	OpenAssistant	Apache 2.0
283	279◄─►286	chatglm-6b	1030	±27	552	Tsinghua	Non-commercial
284	278◄─►287	chatglm2-6b	1025	±35	293	Tsinghua	Apache-2.0
285	280◄─►287	stablelm-tuned-alpha-7b	999	±33	363	Stability AI	CC-BY-NC-SA-4.0
286	282◄─►287	alpaca-13b	994	±27	627	Stanford	Non-commercial
287	284◄─►288	dolly-v2-12b	958	±34	398	Databricks	MIT
288	287◄─►289	fastchat-t5-3b	903	±31	428	LMSYS	Apache 2.0
289	288◄─►289	llama-13b	877	±40	305	Meta	Non-commercial

Text Arena

Default Leaderboard Plots

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

Battle Count for Each Combination of Models (without Ties)

Confidence Intervals on Model Strength (via Bootstrapping)

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