Text Arena

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

Last Updated

Dec 23, 2025

Total Votes

628,366

Total Models

285

/

Style Control

	Rank Spread
1	1◄─►8	gemini-3-pro	1477	±11	3,677	Google	Proprietary
2	1◄─►9	gemini-3-flash	1477	±19	958	Google	Proprietary
3	1◄─►8	grok-4.1-thinking	1477	±10	3,952	xAI	Proprietary
4	1◄─►8	grok-4.1	1473	±10	4,178	xAI	Proprietary
5	1◄─►9	claude-opus-4-5-20251101	1472	±12	2,811	Anthropic	Proprietary
6	1◄─►13	claude-opus-4-5-20251101-thinking-32k	1466	±12	2,566	Anthropic	Proprietary
7	1◄─►21	gemini-3-flash (thinking-minimal)	1462	±19	997	Google	Proprietary
8	4◄─►21	claude-sonnet-4-5-20250929	1451	±9	5,223	Anthropic	Proprietary
9	6◄─►21	claude-opus-4-1-20250805-thinking-16k	1449	±7	8,671	Anthropic	Proprietary
10	6◄─►21	chatgpt-4o-latest-20250326	1449	±7	10,706	OpenAI	Proprietary
11	6◄─►23	claude-sonnet-4-5-20250929-thinking-32k	1446	±8	6,034	Anthropic	Proprietary
12	6◄─►28	gpt-5.1-high	1445	±11	3,288	OpenAI	Proprietary
13	7◄─►27	qwen3-max-preview	1443	±9	5,136	Alibaba	Proprietary
14	7◄─►26	claude-opus-4-1-20250805	1442	±7	10,782	Anthropic	Proprietary
15	7◄─►29	gpt-5-chat	1441	±8	5,611	OpenAI	Proprietary
16	1◄─►57	gpt-5.2	1440	±29	449	OpenAI	Proprietary
17	7◄─►34	gpt-5.1	1440	±11	3,663	OpenAI	Proprietary
18	7◄─►31	gemini-2.5-pro	1437	±6	13,776	Google	Proprietary
19	7◄─►47	gpt-5.2-high	1436	±17	1,250	OpenAI	Proprietary
20	7◄─►42	qwen3-vl-235b-a22b-instruct	1436	±14	1,838	Alibaba	Apache 2.0
21	12◄─►39	qwen3-235b-a22b-instruct-2507	1430	±7	9,961	Alibaba	Apache 2.0
22	7◄─►59	ernie-5.0-preview-1203	1430	±24	618	Baidu	Proprietary
23	13◄─►45	o3-2025-04-16	1427	±7	9,613	OpenAI	Proprietary
24	11◄─►57	gpt-4.5-preview-2025-02-27	1425	±15	1,401	OpenAI	Proprietary
25	12◄─►57	grok-4-1-fast-reasoning	1423	±12	2,565	xAI	Proprietary
26	16◄─►57	kimi-k2-thinking-turbo	1421	±10	3,707	Moonshot	Modified MIT
27	13◄─►59	deepseek-v3.2-thinking	1420	±14	1,890	DeepSeek AI	MIT
28	15◄─►59	qwen3-max-2025-09-23	1420	±14	1,762	Alibaba	Proprietary
29	16◄─►61	mistral-large-3	1418	±14	1,976	Mistral	Apache 2.0
30	11◄─►70	deepseek-v3.1-terminus-thinking	1418	±22	696	DeepSeek AI	MIT
31	17◄─►61	deepseek-v3.2	1417	±13	2,155	DeepSeek AI	MIT
32	18◄─►57	gpt-5-high	1417	±9	5,537	OpenAI	Proprietary
33	19◄─►57	gpt-4.1-2025-04-14	1416	±7	8,337	OpenAI	Proprietary
34	17◄─►65	ernie-5.0-preview-1103	1415	±16	1,441	Baidu	Proprietary
35	18◄─►64	deepseek-v3.2-exp	1414	±13	2,245	DeepSeek AI	MIT
36	18◄─►64	deepseek-v3.1	1414	±12	2,516	DeepSeek	MIT
37	18◄─►65	deepseek-v3.1-thinking	1414	±13	1,935	DeepSeek	MIT
38	19◄─►60	kimi-k2-0711-preview	1414	±9	4,622	Moonshot	Modified MIT
39	20◄─►60	claude-opus-4-20250514-thinking-16k	1413	±8	6,103	Anthropic	Proprietary
40	18◄─►66	longcat-flash-chat	1412	±13	2,162	Meituan	MIT
41	21◄─►60	mistral-medium-2508	1412	±7	8,822	Mistral	Proprietary
42	21◄─►61	qwen3-235b-a22b-no-thinking	1411	±8	6,392	Alibaba	Apache 2.0
43	22◄─►65	glm-4.5	1409	±10	4,266	Z.ai	MIT
44	19◄─►70	kimi-k2-0905-preview	1409	±13	2,045	Moonshot	Modified MIT
45	22◄─►67	qwen3-next-80b-a3b-instruct	1409	±10	4,251	Alibaba	Apache 2.0
46	12◄─►83	hunyuan-vision-1.5-thinking	1408	±27	461	Tencent	Proprietary
47	22◄─►67	claude-haiku-4-5-20251001	1407	±9	5,678	Anthropic	Proprietary
48	22◄─►66	claude-opus-4-20250514	1407	±8	7,183	Anthropic	Proprietary
49	22◄─►69	glm-4.6	1406	±9	5,346	Z.ai	MIT
50	20◄─►76	hunyuan-turbos-20250416	1404	±16	1,421	Tencent	Proprietary
51	22◄─►74	deepseek-v3.2-exp-thinking	1404	±14	1,785	DeepSeek AI	MIT
52	20◄─►76	grok-4-fast-chat	1404	±17	1,212	xAI	Proprietary
53	17◄─►90	mimo-v2-flash (non-thinking)	1403	±28	467	Xiaomi	MIT
54	22◄─►74	deepseek-r1-0528	1402	±11	2,896	DeepSeek	MIT
55	22◄─►77	qwen3-235b-a22b-thinking-2507	1401	±15	1,578	Alibaba	Apache 2.0
56	28◄─►71	gemini-2.5-flash-preview-09-2025	1400	±8	6,218	Google	Proprietary
57	28◄─►76	grok-4-fast-reasoning	1397	±10	3,632	xAI	Proprietary
58	31◄─►77	qwen3-30b-a3b-instruct-2507	1396	±10	4,149	Alibaba	Apache 2.0
59	34◄─►78	grok-3-preview-02-24	1394	±10	4,020	xAI	Proprietary
60	22◄─►90	deepseek-v3.1-terminus	1394	±22	738	DeepSeek AI	MIT
61	42◄─►76	gemini-2.5-flash	1393	±6	13,427	Google	Proprietary
62	37◄─►80	qwen3-coder-480b-a35b-instruct	1393	±10	4,004	Alibaba	Apache 2.0
63	44◄─►78	grok-4-0709	1392	±8	7,309	xAI	Proprietary
64	46◄─►83	claude-sonnet-4-20250514	1390	±8	6,671	Anthropic	Proprietary
65	46◄─►82	deepseek-v3-0324	1390	±8	6,935	DeepSeek	MIT
66	37◄─►90	deepseek-r1	1389	±14	1,807	DeepSeek	MIT
67	37◄─►90	qwen3-vl-235b-a22b-thinking	1388	±15	1,560	Alibaba	Apache 2.0
68	47◄─►85	mistral-medium-2505	1387	±9	5,126	Mistral	Proprietary
69	49◄─►85	claude-sonnet-4-20250514-thinking-32k	1386	±8	5,878	Anthropic	Proprietary
70	22◄─►112	gemma-3-12b-it	1384	±30	367	Google	Gemma
71	50◄─►90	gpt-4.1-mini-2025-04-14	1383	±8	6,091	OpenAI	Proprietary
72	52◄─►90	o4-mini-2025-04-16	1382	±8	7,160	OpenAI	Proprietary
73	50◄─►90	gpt-5-mini-high	1382	±9	4,824	OpenAI	Proprietary
74	52◄─►95	mai-1-preview	1379	±10	3,393	Microsoft AI	Proprietary
75	58◄─►93	gemma-3-27b-it	1378	±8	6,712	Google	Gemma
76	60◄─►97	claude-3-7-sonnet-20250219	1375	±8	5,863	Anthropic	Proprietary
77	61◄─►97	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1375	±8	6,401	Google	Proprietary
78	61◄─►106	o1-2024-12-17	1371	±12	2,737	OpenAI	Proprietary
79	64◄─►104	claude-3-7-sonnet-20250219-thinking-32k	1370	±9	5,678	Anthropic	Proprietary
80	39◄─►123	hunyuan-turbos-20250226	1369	±32	263	Tencent	Proprietary
81	66◄─►107	qwen3-235b-a22b	1368	±10	3,993	Alibaba	Apache 2.0
82	66◄─►106	glm-4.5-air	1368	±8	5,497	Z.ai	MIT
83	66◄─►107	qwen2.5-max	1367	±10	3,741	Alibaba	Proprietary
84	50◄─►120	amazon-nova-experimental-chat-10-09	1367	±24	582	Amazon	Proprietary
85	66◄─►113	mistral-small-2506	1365	±11	2,940	Mistral	Apache 2.0
86	66◄─►113	qwen3-next-80b-a3b-thinking	1364	±12	2,483	Alibaba	Apache 2.0
87	73◄─►110	gemini-2.5-flash-lite-preview-06-17-thinking	1363	±9	5,462	Google	Proprietary
88	56◄─►122	amazon-nova-experimental-chat-11-10	1362	±24	613	Amazon	Proprietary
89	60◄─►121	hunyuan-t1-20250711	1362	±21	759	Tencent	Proprietary
90	75◄─►111	claude-3-5-sonnet-20241022	1361	±6	11,360	Anthropic	Proprietary
91	74◄─►118	gemini-2.0-flash-lite-preview-02-05	1358	±12	2,432	Google	Proprietary
92	77◄─►120	o1-preview	1355	±10	3,780	OpenAI	Proprietary
93	75◄─►120	amazon-nova-experimental-chat-10-20	1355	±13	2,161	Amazon	Proprietary
94	73◄─►122	step-3	1355	±17	1,156	StepFun	Apache 2.0
95	73◄─►127	intellect-3	1353	±19	1,012	Prime Intellect	MIT
96	78◄─►120	minimax-m1	1352	±8	6,145	MiniMax	Apache 2.0
97	82◄─►120	command-a-03-2025	1351	±7	8,851	Cohere	CC-BY-NC-4.0
98	77◄─►122	deepseek-v3	1350	±12	2,243	DeepSeek	DeepSeek
99	77◄─►124	o3-mini-high	1349	±14	1,824	OpenAI	Proprietary
100	77◄─►127	minimax-m2	1349	±17	1,337	MiniMax	Apache 2.0
101	77◄─►127	nova-2-lite	1348	±14	1,886	Amazon	Proprietary
102	62◄─►155	hunyuan-turbo-0110	1348	±34	256	Tencent	Proprietary
103	83◄─►122	gemini-2.0-flash-001	1346	±8	5,352	Google	Proprietary
104	84◄─►122	gpt-oss-120b	1346	±9	5,385	OpenAI	Apache 2.0
105	74◄─►147	glm-4-plus-0111	1345	±24	591	Zhipu	Proprietary
106	64◄─►159	llama-3.1-nemotron-ultra-253b-v1	1344	±35	259	Nvidia	Nvidia Open Model
107	77◄─►150	qwen-plus-0125	1342	±24	570	Alibaba	Proprietary
108	87◄─►129	grok-3-mini-beta	1341	±10	3,592	xAI	Proprietary
109	82◄─►142	ling-flash-2.0	1341	±16	1,350	Ant Group	MIT
110	80◄─►148	glm-4.5v	1340	±20	913	Z.ai	MIT
111	87◄─►139	grok-3-mini-high	1339	±11	2,776	xAI	Proprietary
112	77◄─►156	qwen3-32b	1338	±27	437	Alibaba	Apache 2.0
113	88◄─►140	qwq-32b	1336	±10	3,530	Alibaba	Apache 2.0
114	87◄─►148	gpt-5-nano-high	1336	±16	1,518	OpenAI	Proprietary
115	93◄─►142	gemini-1.5-pro-002	1333	±8	6,382	Google	Proprietary
116	78◄─►169	gemma-3-4b-it	1330	±30	391	Google	Gemma
117	87◄─►157	nvidia-nemotron-3-nano-30b-a3b-bf16	1329	±19	1,007	Nvidia	NVIDIA Open Model
118	94◄─►149	qwen3-30b-a3b	1329	±10	4,058	Alibaba	Apache 2.0
119	101◄─►147	o3-mini	1328	±7	7,746	OpenAI	Proprietary
120	101◄─►149	claude-3-5-sonnet-20240620	1327	±8	9,721	Anthropic	Proprietary
121	104◄─►151	gpt-4o-2024-05-13	1324	±7	13,317	OpenAI	Proprietary
122	82◄─►173	mercury	1324	±32	365	Inception AI	Proprietary
123	87◄─►169	nvidia-llama-3.3-nemotron-super-49b-v1.5	1324	±23	615	Nvidia	Nvidia Open
124	88◄─►169	gpt-4.1-nano-2025-04-14	1324	±22	661	OpenAI	Proprietary
125	104◄─►155	llama-4-scout-17b-16e-instruct	1323	±9	4,983	Meta	Llama
126	100◄─►161	gpt-oss-20b	1322	±14	1,838	OpenAI	Apache 2.0
127	105◄─►155	llama-4-maverick-17b-128e-instruct	1322	±8	6,233	Meta	Llama 4
128	99◄─►167	ring-flash-2.0	1320	±16	1,343	Ant Group	MIT
129	105◄─►155	claude-3-5-haiku-20241022	1320	±7	9,226	Anthropic	Proprietary
130	105◄─►160	yi-lightning	1319	±11	3,423	01 AI	Proprietary
131	105◄─►161	glm-4-plus	1319	±11	3,273	Zhipu AI	Proprietary
132	85◄─►179	llama-3.3-nemotron-49b-super-v1	1319	±35	243	Nvidia	Nvidia
133	105◄─►161	gemma-3n-e4b-it	1319	±11	3,359	Google	Gemma
134	106◄─►159	llama-3.1-405b-instruct-fp8	1318	±8	6,669	Meta	Llama 3.1 Community
135	105◄─►161	gemini-advanced-0514	1318	±10	6,134	Google	Proprietary
136	107◄─►159	o1-mini	1318	±8	6,094	OpenAI	Proprietary
137	106◄─►160	llama-3.1-405b-instruct-bf16	1318	±9	4,523	Meta	Llama 3.1 Community
138	109◄─►160	grok-2-2024-08-13	1316	±8	7,494	xAI	Proprietary
139	105◄─►169	step-1o-turbo-202506	1315	±16	1,427	StepFun	Proprietary
140	109◄─►164	gemini-1.5-pro-001	1314	±9	9,300	Google	Proprietary
141	105◄─►172	qwen2.5-plus-1127	1313	±17	1,080	Alibaba	Proprietary
142	116◄─►167	claude-3-opus-20240229	1311	±7	21,739	Anthropic	Proprietary
143	115◄─►168	gpt-4o-mini-2024-07-18	1311	±8	7,786	OpenAI	Proprietary
144	101◄─►179	step-2-16k-exp-202412	1310	±25	506	StepFun	Proprietary
145	111◄─►169	athene-v2-chat	1309	±11	2,735	NexusFlow	NexusFlow
146	117◄─►169	llama-3.3-70b-instruct	1307	±7	6,704	Meta	Llama-3.3
147	113◄─►173	qwen-max-0919	1307	±13	2,199	Alibaba	Qwen
148	105◄─►179	deepseek-v2.5-1210	1306	±22	715	DeepSeek	DeepSeek
149	117◄─►170	gpt-4o-2024-08-06	1306	±9	5,098	OpenAI	Proprietary
150	109◄─►178	olmo-3-32b-think	1306	±18	1,131	Allen AI	Apache 2.0
151	123◄─►173	grok-2-mini-2024-08-13	1302	±8	6,129	xAI	Proprietary
152	121◄─►178	deepseek-v2.5	1301	±11	2,831	DeepSeek	DeepSeek
153	117◄─►178	athene-70b-0725	1301	±13	2,095	NexusFlow	CC-BY-NC-4.0
154	105◄─►187	hunyuan-standard-2025-02-10	1301	±29	376	Tencent	Proprietary
155	126◄─►174	qwen2.5-72b-instruct	1300	±9	4,656	Alibaba	Qwen
156	129◄─►178	gemini-1.5-flash-002	1299	±10	4,257	Google	Proprietary
157	133◄─►178	mistral-small-3.1-24b-instruct-2503	1298	±9	5,551	Mistral	Apache 2.0
158	123◄─►179	magistral-medium-2506	1297	±14	2,229	Mistral	Proprietary
159	109◄─►190	llama-3.1-nemotron-51b-instruct	1296	±27	421	Nvidia	Llama 3.1
160	133◄─►179	mistral-large-2411	1296	±11	3,033	Mistral	MRL
161	134◄─►178	gpt-4-turbo-2024-04-09	1296	±8	10,829	OpenAI	Proprietary
162	117◄─►185	llama-3.1-nemotron-70b-instruct	1295	±19	905	Nvidia	Llama 3.1
163	137◄─►179	mistral-large-2407	1293	±9	5,169	Mistral	Mistral Research
164	109◄─►197	hunyuan-large-2025-02-10	1291	±31	358	Tencent	Proprietary
165	143◄─►180	llama-3.1-70b-instruct	1290	±8	6,387	Meta	Llama 3.1 Community
166	134◄─►188	gemma-2-9b-it-simpo	1288	±17	1,121	Princeton	MIT
167	144◄─►181	gpt-4-0125-preview	1287	±9	9,719	OpenAI	Proprietary
168	144◄─►182	gemini-1.5-flash-001	1287	±9	7,268	Google	Proprietary
169	133◄─►194	qwen2.5-coder-32b-instruct	1285	±22	630	Alibaba	Apache 2.0
170	136◄─►193	reka-core-20240904	1284	±20	838	Reka AI	Proprietary
171	148◄─►185	gpt-4-1106-preview	1283	±9	9,598	OpenAI	Proprietary
172	134◄─►196	hunyuan-large-vision	1283	±22	790	Tencent	Proprietary
173	149◄─►185	gemma-2-27b-it	1283	±7	8,735	Google	Gemma license
174	149◄─►190	amazon-nova-pro-v1.0	1279	±11	2,596	Amazon	Proprietary
175	122◄─►205	llama-3.1-tulu-3-70b	1278	±33	289	Ai2	Llama 3.1
176	145◄─►197	ibm-granite-h-small	1276	±20	1,041	IBM	Apache 2.0
177	149◄─►197	command-r-plus-08-2024	1273	±17	1,132	Cohere	CC-BY-NC-4.0
178	149◄─►198	reka-flash-20240904	1271	±19	903	Reka AI	Proprietary
179	161◄─►197	amazon-nova-lite-v1.0	1271	±13	2,105	Amazon	Proprietary
180	162◄─►197	c4ai-aya-expanse-32b	1270	±11	3,116	Cohere	CC-BY-NC-4.0
181	155◄─►201	jamba-1.5-large	1268	±19	981	AI21 Labs	Jamba Open
182	164◄─►197	claude-3-sonnet-20240229	1267	±9	11,888	Anthropic	Proprietary
183	167◄─►197	gemma-2-9b-it	1265	±8	6,183	Google	Gemma license
184	167◄─►198	command-r-plus	1263	±9	8,520	Cohere	CC-BY-NC-4.0
185	164◄─►200	nemotron-4-340b-instruct	1263	±13	2,167	Nvidia	NVIDIA Open Model
186	163◄─►204	mistral-small-24b-instruct-2501	1263	±16	1,457	Mistral	Apache 2.0
187	169◄─►204	phi-4	1259	±12	2,453	Microsoft	MIT
188	171◄─►204	gemini-1.5-flash-8b-001	1257	±10	4,297	Google	Proprietary
189	168◄─►207	deepseek-coder-v2	1257	±14	1,799	DeepSeek AI	DeepSeek License
190	173◄─►204	claude-3-haiku-20240307	1254	±8	13,280	Anthropic	Proprietary
191	173◄─►204	llama-3-70b-instruct	1254	±8	16,686	Meta	Llama 3 Community
192	172◄─►207	gpt-4-0314	1252	±11	5,139	OpenAI	Proprietary
193	171◄─►211	glm-4-0520	1247	±17	1,192	Zhipu AI	Proprietary
194	164◄─►219	llama-3.1-tulu-3-8b	1246	±32	285	Ai2	Llama 3.1
195	184◄─►211	gpt-4-0613	1240	±9	8,691	OpenAI	Proprietary
196	174◄─►219	ministral-8b-2410	1238	±24	572	Mistral	MRL
197	169◄─►221	olmo-2-0325-32b-instruct	1237	±32	335	Allen AI	Apache-2.0
198	185◄─►214	amazon-nova-micro-v1.0	1235	±13	2,065	Amazon	Proprietary
199	183◄─►217	gemini-pro-dev-api	1234	±17	1,673	Google	Proprietary
200	191◄─►214	qwen2-72b-instruct	1233	±11	4,351	Alibaba	Qianwen LICENSE
201	183◄─►218	command-r-08-2024	1233	±18	1,153	Cohere	CC-BY-NC-4.0
202	171◄─►223	granite-3.1-8b-instruct	1232	±33	317	IBM	Apache 2.0
203	190◄─►219	reka-flash-21b-20240226-online	1231	±16	1,681	Reka AI	Proprietary
204	185◄─►220	c4ai-aya-expanse-8b	1230	±18	1,096	Cohere	CC-BY-NC-4.0
205	193◄─►216	command-r	1229	±10	5,992	Cohere	CC-BY-NC-4.0
206	193◄─►217	mistral-large-2402	1227	±10	6,483	Mistral	Proprietary
207	191◄─►221	jamba-1.5-mini	1226	±19	1,006	AI21 Labs	Jamba Open
208	193◄─►220	qwen1.5-110b-chat	1225	±12	3,124	Alibaba	Qianwen LICENSE
209	181◄─►230	hunyuan-standard-256k	1224	±32	328	Tencent	Proprietary
210	193◄─►221	reka-flash-21b-20240226	1219	±13	2,708	Reka AI	Proprietary
211	185◄─►235	granite-3.1-2b-instruct	1218	±30	382	IBM	Apache 2.0
212	195◄─►221	mixtral-8x22b-instruct-v0.1	1218	±10	5,573	Mistral	Apache 2.0
213	195◄─►223	mistral-medium	1213	±13	3,228	Mistral	Proprietary
214	195◄─►223	qwen1.5-72b-chat	1212	±12	3,853	Alibaba	Qianwen LICENSE
215	197◄─►222	llama-3-8b-instruct	1211	±9	10,793	Meta	Llama 3 Community
216	197◄─►222	llama-3.1-8b-instruct	1210	±9	5,724	Meta	Llama 3.1 Community
217	198◄─►223	gpt-3.5-turbo-0125	1208	±10	6,915	OpenAI	Proprietary
218	206◄─►235	yi-1.5-34b-chat	1198	±12	2,762	01 AI	Apache-2.0
219	200◄─►249	zephyr-orpo-141b-A35b-v0.1	1189	±28	444	HuggingFace	Apache 2.0
220	210◄─►243	qwen1.5-32b-chat	1188	±14	2,312	Alibaba	Qianwen LICENSE
221	216◄─►244	phi-3-medium-4k-instruct	1184	±12	2,851	Microsoft	MIT
222	216◄─►243	mixtral-8x7b-instruct-v0.1	1184	±10	7,081	Mistral	Apache 2.0
223	216◄─►243	gemma-2-2b-it	1183	±9	5,204	Google	Gemma license
224	204◄─►253	gemini-pro	1183	±30	430	Google	Proprietary
225	216◄─►247	dbrx-instruct-preview	1182	±13	3,379	Databricks	DBRX LICENSE
226	201◄─►256	llama2-70b-steerlm-chat	1179	±36	282	Nvidia	Llama 2 Community
227	216◄─►250	openchat-3.5-0106	1178	±18	1,177	OpenChat	Apache-2.0
228	217◄─►249	gemma-1.1-7b-it	1178	±13	2,718	Google	Gemma license
229	212◄─►253	wizardlm-70b	1177	±24	683	Microsoft	Llama 2 Community
230	217◄─►249	qwen1.5-14b-chat	1177	±16	1,871	Alibaba	Qianwen LICENSE
231	217◄─►251	yi-34b-chat	1175	±17	1,434	01 AI	Yi License
232	217◄─►251	starling-lm-7b-beta	1173	±16	1,655	Nexusflow	Apache-2.0
233	216◄─►255	tulu-2-dpo-70b	1171	±26	540	AllenAI/UW	AI2 ImpACT Low-risk
234	219◄─►254	internlm2_5-20b-chat	1169	±17	1,291	InternLM	Other
235	216◄─►256	deepseek-llm-67b-chat	1168	±28	441	DeepSeek AI	DeepSeek License
236	219◄─►253	llama-2-70b-chat	1165	±12	3,546	Meta	Llama 2 Community
237	219◄─►255	starling-lm-7b-alpha	1164	±21	844	UC Berkeley	CC-BY-NC-4.0
238	219◄─►255	phi-3-small-8k-instruct	1164	±14	2,181	Microsoft	MIT
239	219◄─►256	gpt-3.5-turbo-1106	1161	±19	1,382	OpenAI	Proprietary
240	219◄─►259	granite-3.0-8b-instruct	1158	±23	813	IBM	Apache 2.0
241	222◄─►256	vicuna-33b	1157	±16	1,912	LMSYS	Non-commercial
242	217◄─►267	nous-hermes-2-mixtral-8x7b-dpo	1156	±35	282	NousResearch	Apache-2.0
243	219◄─►263	qwen1.5-7b-chat	1154	±28	448	Alibaba	Qianwen LICENSE
244	219◄─►260	openchat-3.5	1154	±24	616	OpenChat	Apache-2.0
245	223◄─►260	llama-3.2-3b-instruct	1150	±20	1,011	Meta	Llama 3.2
246	227◄─►259	snowflake-arctic-instruct	1147	±13	3,271	Snowflake	Apache 2.0
247	224◄─►267	granite-3.0-2b-instruct	1144	±22	874	IBM	Apache 2.0
248	230◄─►265	llama-2-13b-chat	1139	±16	1,713	Meta	Llama 2 Community
249	223◄─►272	openhermes-2.5-mistral-7b	1139	±30	381	NousResearch	Apache-2.0
250	234◄─►268	mistral-7b-instruct-v0.2	1136	±16	1,747	Mistral	Apache-2.0
251	228◄─►272	codellama-34b-instruct	1134	±25	639	Meta	Llama 2 Community
252	223◄─►273	solar-10.7b-instruct-v1.0	1134	±34	312	Upstage AI	CC-BY-NC-4.0
253	233◄─►272	gemma-7b-it	1131	±22	821	Google	Gemma license
254	224◄─►274	mpt-30b-chat	1129	±38	207	MosaicML	CC-BY-NC-SA-4.0
255	230◄─►273	qwen-14b-chat	1126	±29	427	Alibaba	Qianwen LICENSE
256	237◄─►272	vicuna-13b	1126	±17	1,640	LMSYS	Llama 2 Community
257	243◄─►272	phi-3-mini-4k-instruct	1117	±14	2,483	Microsoft	MIT
258	241◄─►274	wizardlm-13b	1114	±25	634	Microsoft	Llama 2 Community
259	245◄─►274	llama-2-7b-chat	1109	±18	1,256	Meta	Llama 2 Community
260	246◄─►274	phi-3-mini-4k-instruct-june-2024	1109	±17	1,427	Microsoft	MIT
261	241◄─►276	gemma-2b-it	1108	±28	449	Google	Gemma license
262	245◄─►274	gemma-1.1-2b-it	1108	±19	1,136	Google	Gemma license
263	247◄─►274	phi-3-mini-128k-instruct	1107	±16	2,096	Microsoft	MIT
264	241◄─►276	qwq-32b-preview	1104	±33	375	Alibaba	Apache 2.0
265	245◄─►276	palm-2	1103	±25	755	Google	Proprietary
266	249◄─►276	zephyr-7b-beta	1100	±21	997	HuggingFace	MIT
267	250◄─►276	qwen1.5-4b-chat	1094	±24	740	Alibaba	Qianwen LICENSE
268	250◄─►276	vicuna-7b	1092	±27	555	LMSYS	Llama 2 Community
269	250◄─►276	olmo-7b-instruct	1089	±27	547	Allen AI	Apache-2.0
270	250◄─►276	stripedhyena-nous-7b	1089	±30	455	Together AI	Apache 2.0
271	246◄─►280	guanaco-33b	1087	±39	260	UW	Non-commercial
272	255◄─►278	mistral-7b-instruct	1079	±24	747	Mistral	Apache 2.0
273	247◄─►280	smollm2-1.7b-instruct	1077	±45	253	HuggingFace	Apache 2.0
274	257◄─►278	llama-3.2-1b-instruct	1074	±21	1,044	Meta	Llama 3.2
275	263◄─►281	koala-13b	1057	±30	503	UC Berkeley	Non-commercial
276	263◄─►281	chatglm3-6b	1052	±32	379	Tsinghua	Apache-2.0
277	271◄─►283	mpt-7b-chat	1018	±37	308	MosaicML	CC-BY-NC-SA-4.0
278	273◄─►283	RWKV-4-Raven-14B	1017	±34	361	RWKV	Apache 2.0
279	271◄─►283	chatglm2-6b	1014	±42	234	Tsinghua	Apache-2.0
280	273◄─►283	fastchat-t5-3b	1009	±39	289	LMSYS	Apache 2.0
281	275◄─►283	alpaca-13b	994	±34	393	Stanford	Non-commercial
282	277◄─►285	oasst-pythia-12b	971	±31	456	OpenAssistant	Apache 2.0
283	277◄─►285	chatglm-6b	959	±39	300	Tsinghua	Non-commercial
284	282◄─►285	stablelm-tuned-alpha-7b	915	±42	238	Stability AI	CC-BY-NC-SA-4.0
285	282◄─►285	dolly-v2-12b	911	±45	233	Databricks	MIT

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)

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

Confidence Intervals on Model Strength (via Bootstrapping)