Text Arena

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

Last Updated

Dec 23, 2025

Total Votes

804,001

Total Models

290

/

Style Control

	Rank Spread
1	1◄─►4	gemini-3-pro	1478	±11	3,616	Google	Proprietary
2	1◄─►7	gemini-3-flash	1467	±20	972	Google	Proprietary
3	1◄─►11	claude-opus-4-5-20251101-thinking-32k	1457	±13	2,394	Anthropic	Proprietary
4	1◄─►16	gemini-3-flash (thinking-minimal)	1450	±19	978	Google	Proprietary
5	2◄─►15	grok-4.1-thinking	1446	±11	3,719	xAI	Proprietary
6	2◄─►15	claude-opus-4-5-20251101	1446	±12	2,458	Anthropic	Proprietary
7	3◄─►16	gemini-2.5-pro	1438	±6	14,366	Google	Proprietary
8	3◄─►16	claude-sonnet-4-5-20250929-thinking-32k	1437	±8	5,709	Anthropic	Proprietary
9	3◄─►18	gpt-5.1-high	1433	±11	3,137	OpenAI	Proprietary
10	4◄─►18	grok-4.1	1433	±10	3,829	xAI	Proprietary
11	3◄─►18	gpt-4.5-preview-2025-02-27	1433	±12	2,630	OpenAI	Proprietary
12	4◄─►18	claude-sonnet-4-5-20250929	1432	±9	4,756	Anthropic	Proprietary
13	4◄─►18	claude-opus-4-1-20250805-thinking-16k	1430	±7	8,438	Anthropic	Proprietary
14	6◄─►19	claude-opus-4-1-20250805	1426	±6	10,765	Anthropic	Proprietary
15	9◄─►20	chatgpt-4o-latest-20250326	1423	±6	12,006	OpenAI	Proprietary
16	2◄─►50	gpt-5.2	1419	±29	443	OpenAI	Proprietary
17	4◄─►47	ernie-5.0-preview-1203	1418	±25	550	Baidu	Proprietary
18	9◄─►24	claude-opus-4-20250514-thinking-16k	1415	±8	6,479	Anthropic	Proprietary
19	14◄─►38	gpt-5.1	1410	±11	3,405	OpenAI	Proprietary
20	16◄─►49	grok-4-1-fast-reasoning	1403	±12	2,397	xAI	Proprietary
21	16◄─►50	deepseek-v3.2-exp	1403	±13	2,075	DeepSeek AI	MIT
22	16◄─►47	gpt-5-high	1401	±8	5,976	OpenAI	Proprietary
23	15◄─►59	gpt-5.2-high	1399	±19	1,026	OpenAI	Proprietary
24	17◄─►49	claude-opus-4-20250514	1399	±7	7,815	Anthropic	Proprietary
25	17◄─►50	qwen3-max-preview	1398	±9	4,979	Alibaba	Proprietary
26	17◄─►49	gpt-4.1-2025-04-14	1398	±7	9,279	OpenAI	Proprietary
27	17◄─►52	grok-3-preview-02-24	1396	±8	5,985	xAI	Proprietary
28	17◄─►50	o3-2025-04-16	1396	±6	10,821	OpenAI	Proprietary
29	16◄─►55	deepseek-v3.2	1396	±14	1,987	DeepSeek AI	MIT
30	17◄─►53	kimi-k2-thinking-turbo	1395	±10	3,429	Moonshot	Modified MIT
31	17◄─►53	glm-4.6	1395	±9	4,909	Z.ai	MIT
32	17◄─►57	deepseek-v3.1-thinking	1393	±12	2,297	DeepSeek	MIT
33	17◄─►61	qwen3-max-2025-09-23	1392	±14	1,639	Alibaba	Proprietary
34	18◄─►55	gpt-5-chat	1391	±8	5,647	OpenAI	Proprietary
35	18◄─►57	o1-2024-12-17	1389	±8	5,217	OpenAI	Proprietary
36	18◄─►54	gemini-2.5-flash	1389	±6	14,145	Google	Proprietary
37	17◄─►64	deepseek-v3.2-exp-thinking	1388	±14	1,684	DeepSeek AI	MIT
38	17◄─►64	ernie-5.0-preview-1103	1388	±16	1,278	Baidu	Proprietary
39	18◄─►58	grok-4-0709	1387	±7	7,609	xAI	Proprietary
40	18◄─►63	deepseek-r1-0528	1386	±10	3,354	DeepSeek	MIT
41	17◄─►64	deepseek-v3.2-thinking	1386	±14	1,677	DeepSeek AI	MIT
42	18◄─►61	claude-sonnet-4-20250514-thinking-32k	1385	±8	6,262	Anthropic	Proprietary
43	20◄─►64	glm-4.5	1383	±9	4,376	Z.ai	MIT
44	18◄─►66	grok-4-fast-chat	1383	±16	1,349	xAI	Proprietary
45	23◄─►64	gemini-2.5-flash-preview-09-2025	1383	±8	5,963	Google	Proprietary
46	27◄─►64	claude-3-7-sonnet-20250219-thinking-32k	1381	±8	6,749	Anthropic	Proprietary
47	18◄─►66	kimi-k2-0905-preview	1381	±13	2,101	Moonshot	Modified MIT
48	27◄─►64	kimi-k2-0711-preview	1381	±9	5,063	Moonshot	Modified MIT
49	20◄─►65	deepseek-v3.1	1380	±11	2,805	DeepSeek	MIT
50	28◄─►64	deepseek-v3-0324	1380	±7	8,269	DeepSeek	MIT
51	17◄─►78	deepseek-v3.1-terminus-thinking	1379	±24	611	DeepSeek AI	MIT
52	17◄─►78	deepseek-v3.1-terminus	1377	±23	625	DeepSeek AI	MIT
53	33◄─►65	qwen3-235b-a22b-instruct-2507	1375	±7	9,741	Alibaba	Apache 2.0
54	30◄─►66	claude-haiku-4-5-20251001	1375	±9	5,370	Anthropic	Proprietary
55	36◄─►67	claude-sonnet-4-20250514	1372	±8	7,184	Anthropic	Proprietary
56	35◄─►69	o1-preview	1371	±9	4,835	OpenAI	Proprietary
57	33◄─►69	deepseek-r1	1371	±10	3,577	DeepSeek	MIT
58	37◄─►69	mistral-medium-2508	1371	±7	8,761	Mistral	Proprietary
59	39◄─►69	claude-3-7-sonnet-20250219	1369	±7	7,616	Anthropic	Proprietary
60	31◄─►78	mistral-large-3	1369	±14	1,847	Mistral	Apache 2.0
61	39◄─►76	grok-4-fast-reasoning	1367	±10	3,300	xAI	Proprietary
62	18◄─►89	hunyuan-vision-1.5-thinking	1365	±29	374	Tencent	Proprietary
63	50◄─►75	claude-3-5-sonnet-20241022	1363	±5	14,531	Anthropic	Proprietary
64	37◄─►81	qwen3-vl-235b-a22b-thinking	1363	±15	1,414	Alibaba	Apache 2.0
65	48◄─►78	gemini-2.5-flash-lite-preview-06-17-thinking	1361	±8	5,959	Google	Proprietary
66	40◄─►82	qwen3-vl-235b-a22b-instruct	1361	±15	1,584	Alibaba	Apache 2.0
67	53◄─►80	qwen3-235b-a22b-no-thinking	1358	±8	6,818	Alibaba	Apache 2.0
68	54◄─►85	mai-1-preview	1353	±11	3,039	Microsoft AI	Proprietary
69	58◄─►83	mistral-medium-2505	1352	±8	5,866	Mistral	Proprietary
70	58◄─►85	qwen3-coder-480b-a35b-instruct	1352	±9	4,344	Alibaba	Apache 2.0
71	58◄─►82	o4-mini-2025-04-16	1352	±7	8,281	OpenAI	Proprietary
72	58◄─►85	gpt-5-mini-high	1351	±9	4,839	OpenAI	Proprietary
73	59◄─►87	deepseek-v3	1348	±9	4,195	DeepSeek	DeepSeek
74	60◄─►87	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1347	±8	5,870	Google	Proprietary
75	64◄─►88	gpt-4.1-mini-2025-04-14	1345	±8	6,986	OpenAI	Proprietary
76	58◄─►99	qwen3-235b-a22b-thinking-2507	1344	±15	1,617	Alibaba	Apache 2.0
77	64◄─►89	gemini-2.0-flash-001	1344	±7	7,980	Google	Proprietary
78	60◄─►100	longcat-flash-chat	1342	±13	1,944	Meituan	MIT
79	58◄─►107	hunyuan-t1-20250711	1341	±19	888	Tencent	Proprietary
80	66◄─►98	qwen2.5-max	1339	±8	6,126	Alibaba	Proprietary
81	54◄─►117	mimo-v2-flash (non-thinking)	1338	±26	524	Xiaomi	MIT
82	69◄─►99	gemini-1.5-pro-002	1337	±7	9,285	Google	Proprietary
83	69◄─►99	gpt-4o-2024-05-13	1336	±7	17,663	OpenAI	Proprietary
84	65◄─►104	hunyuan-turbos-20250416	1336	±13	1,974	Tencent	Proprietary
85	68◄─►103	gemini-advanced-0514	1335	±9	7,568	Google	Proprietary
86	72◄─►107	qwen3-30b-a3b-instruct-2507	1332	±9	4,174	Alibaba	Apache 2.0
87	77◄─►105	command-a-03-2025	1329	±6	10,320	Cohere	CC-BY-NC-4.0
88	74◄─►110	qwen3-next-80b-a3b-instruct	1329	±9	4,128	Alibaba	Apache 2.0
89	77◄─►109	minimax-m1	1328	±8	6,545	MiniMax	Apache 2.0
90	77◄─►108	gemma-3-27b-it	1327	±7	8,417	Google	Gemma
91	77◄─►114	gemini-2.0-flash-lite-preview-02-05	1326	±9	4,523	Google	Proprietary
92	77◄─►113	glm-4.5-air	1326	±8	5,779	Z.ai	MIT
93	77◄─►116	qwen3-235b-a22b	1325	±9	4,905	Alibaba	Apache 2.0
94	77◄─►117	grok-3-mini-high	1324	±11	3,080	xAI	Proprietary
95	77◄─►116	gpt-4o-2024-08-06	1323	±8	7,050	OpenAI	Proprietary
96	77◄─►117	mistral-small-2506	1323	±10	3,309	Mistral	Apache 2.0
97	72◄─►128	glm-4.5v	1322	±19	877	Z.ai	MIT
98	75◄─►128	step-3	1320	±17	1,114	StepFun	Apache 2.0
99	81◄─►118	grok-3-mini-beta	1320	±9	4,034	xAI	Proprietary
100	88◄─►122	grok-2-2024-08-13	1314	±7	10,295	xAI	Proprietary
101	89◄─►124	gpt-4-turbo-2024-04-09	1313	±7	14,841	OpenAI	Proprietary
102	78◄─►140	intellect-3	1312	±19	1,038	Prime Intellect	MIT
103	85◄─►132	qwen3-next-80b-a3b-thinking	1311	±12	2,417	Alibaba	Apache 2.0
104	92◄─►128	claude-3-5-sonnet-20240620	1310	±7	13,201	Anthropic	Proprietary
105	90◄─►132	o3-mini-high	1309	±10	3,216	OpenAI	Proprietary
106	94◄─►130	gemini-1.5-pro-001	1307	±8	12,151	Google	Proprietary
107	82◄─►151	gemma-3-12b-it	1306	±21	700	Google	Gemma
108	87◄─►150	minimax-m2	1304	±17	1,225	MiniMax	Apache 2.0
109	98◄─►136	llama-3.1-405b-instruct-fp8	1303	±7	9,533	Meta	Llama 3.1 Community
110	82◄─►160	llama-3.1-nemotron-ultra-253b-v1	1302	±24	534	Nvidia	Nvidia Open Model
111	98◄─►137	o3-mini	1302	±6	10,533	OpenAI	Proprietary
112	92◄─►151	deepseek-v2.5-1210	1301	±16	1,218	DeepSeek	DeepSeek
113	82◄─►166	llama-3.3-nemotron-49b-super-v1	1301	±27	414	Nvidia	Nvidia
114	90◄─►154	step-2-16k-exp-202412	1301	±18	873	StepFun	Proprietary
115	85◄─►161	hunyuan-large-2025-02-10	1300	±22	646	Tencent	Proprietary
116	91◄─►153	glm-4-plus-0111	1300	±17	1,064	Zhipu	Proprietary
117	100◄─►140	claude-3-5-haiku-20241022	1299	±6	12,664	Anthropic	Proprietary
118	83◄─►166	hunyuan-turbo-0110	1299	±25	452	Tencent	Proprietary
119	84◄─►166	amazon-nova-experimental-chat-11-10	1298	±25	599	Amazon	Proprietary
120	100◄─►143	llama-4-maverick-17b-128e-instruct	1297	±7	7,186	Meta	Llama 4
121	103◄─►148	llama-3.1-405b-instruct-bf16	1295	±7	7,233	Meta	Llama 3.1 Community
122	100◄─►153	yi-lightning	1294	±10	3,985	01 AI	Proprietary
123	90◄─►174	amazon-nova-experimental-chat-10-09	1293	±25	471	Amazon	Proprietary
124	98◄─►162	qwen-plus-0125	1293	±17	1,092	Alibaba	Proprietary
125	99◄─►159	amazon-nova-experimental-chat-10-20	1293	±13	1,997	Amazon	Proprietary
126	104◄─►154	llama-4-scout-17b-16e-instruct	1291	±8	5,428	Meta	Llama
127	106◄─►154	gpt-4-1106-preview	1290	±8	15,245	OpenAI	Proprietary
128	106◄─►154	mistral-large-2407	1289	±8	6,999	Mistral	Mistral Research
129	103◄─►162	magistral-medium-2506	1289	±13	2,020	Mistral	Proprietary
130	98◄─►175	nvidia-llama-3.3-nemotron-super-49b-v1.5	1287	±23	601	Nvidia	Nvidia Open
131	107◄─►159	gpt-oss-120b	1287	±8	5,582	OpenAI	Apache 2.0
132	108◄─►159	gpt-4-0125-preview	1287	±8	14,022	OpenAI	Proprietary
133	100◄─►173	gpt-4.1-nano-2025-04-14	1287	±17	1,063	OpenAI	Proprietary
134	99◄─►175	qwen3-32b	1286	±21	706	Alibaba	Apache 2.0
135	97◄─►178	hunyuan-turbos-20250226	1286	±26	450	Tencent	Proprietary
136	108◄─►162	qwq-32b	1285	±9	4,583	Alibaba	Apache 2.0
137	110◄─►160	llama-3.3-70b-instruct	1285	±6	9,924	Meta	Llama-3.3
138	104◄─►174	nova-2-lite	1284	±15	1,592	Amazon	Proprietary
139	111◄─►162	gpt-4o-mini-2024-07-18	1283	±6	11,321	OpenAI	Proprietary
140	111◄─►162	claude-3-opus-20240229	1283	±6	29,438	Anthropic	Proprietary
141	106◄─►175	gpt-5-nano-high	1282	±16	1,352	OpenAI	Proprietary
142	112◄─►167	o1-mini	1280	±7	8,621	OpenAI	Proprietary
143	111◄─►172	gemma-3n-e4b-it	1280	±9	4,096	Google	Gemma
144	111◄─►173	glm-4-plus	1279	±10	3,860	Zhipu AI	Proprietary
145	106◄─►178	ling-flash-2.0	1279	±17	1,177	Ant Group	MIT
146	111◄─►175	qwen-max-0919	1278	±12	2,407	Alibaba	Qwen
147	114◄─►174	mistral-small-3.1-24b-instruct-2503	1277	±8	6,000	Mistral	Apache 2.0
148	110◄─►178	step-1o-turbo-202506	1277	±15	1,578	StepFun	Proprietary
149	108◄─►180	nvidia-nemotron-3-nano-30b-a3b-bf16	1275	±20	917	Nvidia	NVIDIA Open Model
150	121◄─►175	gemini-1.5-flash-002	1273	±8	5,702	Google	Proprietary
151	127◄─►175	gemma-2-27b-it	1271	±6	12,303	Google	Gemma license
152	112◄─►180	ring-flash-2.0	1271	±16	1,269	Ant Group	MIT
153	124◄─►178	qwen3-30b-a3b	1270	±9	4,714	Alibaba	Apache 2.0
154	126◄─►178	mistral-large-2411	1270	±8	5,136	Mistral	MRL
155	121◄─►178	athene-70b-0725	1270	±10	3,243	NexusFlow	CC-BY-NC-4.0
156	115◄─►180	jamba-1.5-large	1269	±15	1,424	AI21 Labs	Jamba Open
157	112◄─►182	llama-3.1-nemotron-70b-instruct	1268	±19	961	Nvidia	Llama 3.1
158	121◄─►181	gemma-2-9b-it-simpo	1267	±14	1,684	Princeton	MIT
159	132◄─►178	gpt-4-0613	1267	±8	13,921	OpenAI	Proprietary
160	136◄─►179	llama-3.1-70b-instruct	1263	±7	8,724	Meta	Llama 3.1 Community
161	136◄─►181	deepseek-v2.5	1263	±10	3,668	DeepSeek	DeepSeek
162	137◄─►180	grok-2-mini-2024-08-13	1262	±7	8,614	xAI	Proprietary
163	136◄─►181	gpt-4-0314	1262	±10	8,085	OpenAI	Proprietary
164	121◄─►187	olmo-3-32b-think	1262	±19	997	Allen AI	Apache 2.0
165	110◄─►191	mercury	1260	±32	363	Inception AI	Proprietary
166	117◄─►187	llama-3.1-tulu-3-70b	1260	±22	552	Ai2	Llama 3.1
167	135◄─►186	gpt-oss-20b	1259	±15	1,788	OpenAI	Apache 2.0
168	121◄─►187	hunyuan-standard-2025-02-10	1258	±22	676	Tencent	Proprietary
169	136◄─►187	command-r-plus-08-2024	1257	±15	1,451	Cohere	CC-BY-NC-4.0
170	132◄─►187	ibm-granite-h-small	1256	±20	969	IBM	Apache 2.0
171	148◄─►184	gemini-1.5-flash-001	1255	±8	9,790	Google	Proprietary
172	132◄─►188	hunyuan-large-vision	1255	±20	919	Tencent	Proprietary
173	142◄─►187	qwen2.5-plus-1127	1254	±13	1,873	Alibaba	Proprietary
174	148◄─►187	nemotron-4-340b-instruct	1253	±11	3,259	Nvidia	NVIDIA Open Model
175	132◄─►191	olmo-2-0325-32b-instruct	1252	±23	607	Allen AI	Apache-2.0
176	136◄─►192	llama-3.1-nemotron-51b-instruct	1250	±24	552	Nvidia	Llama 3.1
177	156◄─►187	llama-3-70b-instruct	1249	±7	23,287	Meta	Llama 3 Community
178	139◄─►191	gemma-3-4b-it	1249	±21	764	Google	Gemma
179	155◄─►187	athene-v2-chat	1248	±9	4,387	NexusFlow	NexusFlow
180	160◄─►187	gemma-2-9b-it	1246	±7	9,160	Google	Gemma license
181	148◄─►191	reka-core-20240904	1246	±17	1,098	Reka AI	Proprietary
182	163◄─►187	qwen2.5-72b-instruct	1244	±8	6,225	Alibaba	Qwen
183	164◄─►188	amazon-nova-pro-v1.0	1239	±9	4,526	Amazon	Proprietary
184	165◄─►188	claude-3-sonnet-20240229	1238	±8	16,006	Anthropic	Proprietary
185	165◄─►191	command-r-plus	1237	±8	11,298	Cohere	CC-BY-NC-4.0
186	164◄─►196	glm-4-0520	1233	±14	1,604	Zhipu AI	Proprietary
187	166◄─►200	reka-flash-20240904	1227	±17	1,115	Reka AI	Proprietary
188	177◄─►198	mistral-small-24b-instruct-2501	1224	±11	2,684	Mistral	Apache 2.0
189	180◄─►199	qwen2-72b-instruct	1221	±9	5,819	Alibaba	Qianwen LICENSE
190	180◄─►199	c4ai-aya-expanse-32b	1221	±9	4,355	Cohere	CC-BY-NC-4.0
191	185◄─►199	claude-3-haiku-20240307	1219	±7	17,182	Anthropic	Proprietary
192	186◄─►203	gemini-1.5-flash-8b-001	1217	±8	5,718	Google	Proprietary
193	180◄─►209	command-r-08-2024	1215	±14	1,592	Cohere	CC-BY-NC-4.0
194	186◄─►204	mistral-large-2402	1212	±9	9,194	Mistral	Proprietary
195	186◄─►211	deepseek-coder-v2	1211	±12	2,519	DeepSeek AI	DeepSeek License
196	186◄─►215	jamba-1.5-mini	1209	±15	1,443	AI21 Labs	Jamba Open
197	187◄─►211	amazon-nova-lite-v1.0	1206	±10	3,430	Amazon	Proprietary
198	192◄─►215	mixtral-8x22b-instruct-v0.1	1201	±9	7,639	Mistral	Apache 2.0
199	192◄─►215	phi-4	1201	±9	4,489	Microsoft	MIT
200	191◄─►219	reka-flash-21b-20240226-online	1197	±14	2,129	Reka AI	Proprietary
201	194◄─►219	gpt-3.5-turbo-0125	1194	±8	9,676	OpenAI	Proprietary
202	194◄─►219	command-r	1194	±9	7,993	Cohere	CC-BY-NC-4.0
203	194◄─►219	amazon-nova-micro-v1.0	1193	±10	3,354	Amazon	Proprietary
204	194◄─►221	qwen1.5-110b-chat	1191	±11	3,911	Alibaba	Qianwen LICENSE
205	192◄─►231	ministral-8b-2410	1189	±20	774	Mistral	MRL
206	188◄─►231	zephyr-orpo-141b-A35b-v0.1	1189	±23	618	HuggingFace	Apache 2.0
207	195◄─►222	mistral-medium	1189	±11	5,408	Mistral	Proprietary
208	197◄─►221	llama-3-8b-instruct	1186	±8	15,452	Meta	Llama 3 Community
209	197◄─►224	qwen1.5-72b-chat	1186	±10	5,827	Alibaba	Qianwen LICENSE
210	193◄─►231	qwen2.5-coder-32b-instruct	1186	±19	928	Alibaba	Apache 2.0
211	195◄─►229	gemini-pro-dev-api	1185	±14	2,884	Google	Proprietary
212	187◄─►239	hunyuan-standard-256k	1184	±29	379	Tencent	Proprietary
213	197◄─►231	c4ai-aya-expanse-8b	1181	±14	1,789	Cohere	CC-BY-NC-4.0
214	194◄─►239	llama-3.1-tulu-3-8b	1179	±23	563	Ai2	Llama 3.1
215	197◄─►240	gemini-pro	1175	±21	1,035	Google	Proprietary
216	200◄─►238	wizardlm-70b	1175	±18	1,539	Microsoft	Llama 2 Community
217	204◄─►231	llama-3.1-8b-instruct	1173	±8	7,708	Meta	Llama 3.1 Community
218	200◄─►242	tulu-2-dpo-70b	1171	±20	989	AllenAI/UW	AI2 ImpACT Low-risk
219	206◄─►231	gemma-2-2b-it	1171	±8	7,531	Google	Gemma license
220	200◄─►240	openchat-3.5	1171	±17	1,340	OpenChat	Apache-2.0
221	204◄─►238	dbrx-instruct-preview	1169	±11	4,629	Databricks	DBRX LICENSE
222	208◄─►238	mixtral-8x7b-instruct-v0.1	1166	±8	11,019	Mistral	Apache 2.0
223	200◄─►245	granite-3.1-8b-instruct	1165	±25	537	IBM	Apache 2.0
224	207◄─►240	vicuna-33b	1165	±12	3,642	LMSYS	Non-commercial
225	208◄─►242	reka-flash-21b-20240226	1162	±12	3,482	Reka AI	Proprietary
226	208◄─►245	gpt-3.5-turbo-1106	1160	±15	2,647	OpenAI	Proprietary
227	208◄─►245	yi-34b-chat	1159	±13	2,341	01 AI	Yi License
228	215◄─►245	yi-1.5-34b-chat	1152	±11	3,901	01 AI	Apache-2.0
229	209◄─►253	openhermes-2.5-mistral-7b	1149	±21	799	NousResearch	Apache-2.0
230	215◄─►247	gemma-1.1-7b-it	1149	±11	3,440	Google	Gemma license
231	208◄─►255	granite-3.1-2b-instruct	1148	±24	569	IBM	Apache 2.0
232	218◄─►249	snowflake-arctic-instruct	1145	±12	4,671	Snowflake	Apache 2.0
233	215◄─►255	llama-3.2-3b-instruct	1141	±18	1,149	Meta	Llama 3.2
234	215◄─►258	granite-3.0-8b-instruct	1141	±21	937	IBM	Apache 2.0
235	209◄─►261	guanaco-33b	1140	±30	443	UW	Non-commercial
236	223◄─►253	qwen1.5-32b-chat	1140	±12	3,072	Alibaba	Qianwen LICENSE
237	220◄─►255	openchat-3.5-0106	1140	±15	1,868	OpenChat	Apache-2.0
238	215◄─►257	wizardlm-13b	1140	±18	1,220	Microsoft	Llama 2 Community
239	215◄─►258	deepseek-llm-67b-chat	1140	±21	802	DeepSeek AI	DeepSeek License
240	207◄─►267	falcon-180b-chat	1139	±38	229	TII	Falcon-180B TII License
241	225◄─►255	phi-3-medium-4k-instruct	1136	±10	3,905	Microsoft	MIT
242	225◄─►258	starling-lm-7b-alpha	1133	±15	1,623	UC Berkeley	CC-BY-NC-4.0
243	215◄─►268	mpt-30b-chat	1130	±29	435	MosaicML	CC-BY-NC-SA-4.0
244	229◄─►261	qwen1.5-14b-chat	1125	±14	2,455	Alibaba	Qianwen LICENSE
245	225◄─►270	solar-10.7b-instruct-v1.0	1123	±24	654	Upstage AI	CC-BY-NC-4.0
246	229◄─►264	internlm2_5-20b-chat	1123	±16	1,429	InternLM	Other
247	223◄─►275	dolphin-2.2.1-mistral-7b	1118	±33	282	Cognitive Computations	Apache-2.0
248	231◄─►269	zephyr-7b-beta	1115	±16	1,869	HuggingFace	MIT
249	231◄─►270	starling-lm-7b-beta	1114	±15	2,206	Nexusflow	Apache-2.0
250	233◄─►268	phi-3-small-8k-instruct	1114	±12	2,639	Microsoft	MIT
251	230◄─►273	nous-hermes-2-mixtral-8x7b-dpo	1113	±24	593	NousResearch	Apache-2.0
252	237◄─►267	llama-2-70b-chat	1112	±10	6,077	Meta	Llama 2 Community
253	230◄─►274	llama2-70b-steerlm-chat	1110	±25	591	Nvidia	Llama 2 Community
254	237◄─►270	vicuna-13b	1110	±13	3,242	LMSYS	Llama 2 Community
255	238◄─►270	mistral-7b-instruct-v0.2	1109	±12	2,923	Mistral	Apache-2.0
256	233◄─►275	granite-3.0-2b-instruct	1105	±21	941	IBM	Apache 2.0
257	231◄─►277	qwq-32b-preview	1104	±27	543	Alibaba	Apache 2.0
258	241◄─►273	llama-2-13b-chat	1103	±12	3,094	Meta	Llama 2 Community
259	231◄─►277	zephyr-7b-alpha	1099	±32	329	HuggingFace	MIT
260	241◄─►277	vicuna-7b	1096	±18	1,286	LMSYS	Llama 2 Community
261	241◄─►277	palm-2	1095	±18	1,482	Google	Proprietary
262	244◄─►277	phi-3-mini-4k-instruct-june-2024	1091	±14	1,978	Microsoft	MIT
263	244◄─►277	gemma-7b-it	1088	±18	1,294	Google	Gemma license
264	243◄─►277	stripedhyena-nous-7b	1087	±21	806	Together AI	Apache 2.0
265	248◄─►277	phi-3-mini-128k-instruct	1085	±14	2,934	Microsoft	MIT
266	243◄─►278	qwen1.5-7b-chat	1085	±23	709	Alibaba	Qianwen LICENSE
267	246◄─►277	gemma-1.1-2b-it	1085	±17	1,503	Google	Gemma license
268	244◄─►278	qwen-14b-chat	1084	±21	848	Alibaba	Qianwen LICENSE
269	249◄─►278	llama-3.2-1b-instruct	1080	±19	1,155	Meta	Llama 3.2
270	253◄─►278	codellama-34b-instruct	1080	±17	1,376	Meta	Llama 2 Community
271	253◄─►278	mistral-7b-instruct	1078	±17	1,497	Mistral	Apache 2.0
272	243◄─►281	smollm2-1.7b-instruct	1077	±33	362	HuggingFace	Apache 2.0
273	253◄─►280	alpaca-13b	1070	±22	936	Stanford	Non-commercial
274	258◄─►279	phi-3-mini-4k-instruct	1069	±12	3,012	Microsoft	MIT
275	258◄─►279	llama-2-7b-chat	1068	±14	2,220	Meta	Llama 2 Community
276	255◄─►281	gemma-2b-it	1066	±23	677	Google	Gemma license
277	256◄─►284	gpt4all-13b-snoozy	1048	±38	253	Nomic AI	Non-commercial
278	267◄─►282	qwen1.5-4b-chat	1046	±18	1,147	Alibaba	Qianwen LICENSE
279	272◄─►284	mpt-7b-chat	1034	±24	718	MosaicML	CC-BY-NC-SA-4.0
280	274◄─►284	koala-13b	1029	±20	1,135	UC Berkeley	Non-commercial
281	275◄─►285	olmo-7b-instruct	1025	±21	878	Allen AI	Apache-2.0
282	277◄─►285	chatglm3-6b	1016	±24	754	Tsinghua	Apache-2.0
283	278◄─►287	chatglm2-6b	994	±28	483	Tsinghua	Apache-2.0
284	278◄─►286	RWKV-4-Raven-14B	989	±22	835	RWKV	Apache 2.0
285	281◄─►287	oasst-pythia-12b	986	±21	1,068	OpenAssistant	Apache 2.0
286	283◄─►290	fastchat-t5-3b	957	±25	720	LMSYS	Apache 2.0
287	284◄─►290	llama-13b	935	±32	402	Meta	Non-commercial
288	286◄─►290	dolly-v2-12b	935	±28	558	Databricks	MIT
289	286◄─►290	chatglm-6b	912	±25	774	Tsinghua	Non-commercial
290	286◄─►290	stablelm-tuned-alpha-7b	905	±29	514	Stability AI	CC-BY-NC-SA-4.0

Text Arena

Default Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

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

Battle Count for Each Combination of Models (without Ties)

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