Text Arena

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

Last Updated

Dec 30, 2025

Total Votes

706,358

Total Models

292

/

Style Control

	Rank Spread
1	1◄─►2	gemini-3-pro	1489	±12	2,958	Google	Proprietary
2	1◄─►11	gemini-3-flash	1466	±20	1,033	Google	Proprietary
3	2◄─►12	claude-opus-4-5-20251101	1458	±14	2,105	Anthropic	Proprietary
4	2◄─►14	claude-opus-4-5-20251101-thinking-32k	1452	±14	1,974	Anthropic	Proprietary
5	2◄─►12	gemini-2.5-pro	1451	±7	10,717	Google	Proprietary
6	2◄─►16	claude-opus-4-1-20250805-thinking-16k	1442	±8	6,436	Anthropic	Proprietary
7	2◄─►18	claude-sonnet-4-5-20250929-thinking-32k	1440	±10	4,401	Anthropic	Proprietary
8	2◄─►18	claude-sonnet-4-5-20250929	1439	±10	3,908	Anthropic	Proprietary
9	2◄─►27	gemini-3-flash (thinking-minimal)	1437	±23	741	Google	Proprietary
10	2◄─►18	grok-4.1-thinking	1437	±12	3,066	xAI	Proprietary
11	2◄─►19	gpt-5.1-high	1436	±13	2,600	OpenAI	Proprietary
12	5◄─►18	claude-opus-4-1-20250805	1435	±7	8,058	Anthropic	Proprietary
13	3◄─►19	gpt-4.5-preview-2025-02-27	1434	±12	2,642	OpenAI	Proprietary
14	6◄─►27	grok-4.1	1425	±11	3,123	xAI	Proprietary
15	7◄─►27	claude-opus-4-20250514-thinking-16k	1422	±9	4,629	Anthropic	Proprietary
16	5◄─►46	ernie-5.0-preview-1203	1420	±22	723	Baidu	Proprietary
17	11◄─►28	chatgpt-4o-latest-20250326	1418	±7	9,332	OpenAI	Proprietary
18	13◄─►39	claude-opus-4-20250514	1412	±8	5,650	Anthropic	Proprietary
19	13◄─►47	gpt-5.1	1409	±12	2,809	OpenAI	Proprietary
20	13◄─►52	deepseek-v3.2-thinking	1406	±16	1,491	DeepSeek AI	MIT
21	6◄─►72	gpt-5.2	1405	±31	352	OpenAI	Proprietary
22	7◄─►67	deepseek-v3.1-terminus	1405	±27	452	DeepSeek AI	MIT
23	13◄─►52	deepseek-v3.1-thinking	1404	±15	1,698	DeepSeek	MIT
24	13◄─►58	ernie-5.0-preview-1103	1404	±17	1,266	Baidu	Proprietary
25	13◄─►52	grok-4-1-fast-reasoning	1404	±14	2,040	xAI	Proprietary
26	13◄─►58	deepseek-v3.2-exp	1401	±15	1,523	DeepSeek AI	MIT
27	17◄─►52	glm-4.6	1399	±10	3,813	Z.ai	MIT
28	17◄─►57	kimi-k2-thinking-turbo	1399	±12	2,856	Moonshot	Modified MIT
29	17◄─►49	gpt-4.1-2025-04-14	1399	±8	6,832	OpenAI	Proprietary
30	13◄─►68	glm-4.7	1399	±22	737	Z.ai	MIT
31	17◄─►52	grok-3-preview-02-24	1399	±9	4,948	xAI	Proprietary
32	17◄─►49	gemini-2.5-flash	1398	±7	10,463	Google	Proprietary
33	17◄─►58	qwen3-max-preview	1396	±10	3,720	Alibaba	Proprietary
34	17◄─►64	deepseek-v3.2	1396	±15	1,712	DeepSeek AI	MIT
35	16◄─►67	qwen3-max-2025-09-23	1395	±17	1,146	Alibaba	Proprietary
36	18◄─►58	grok-4-0709	1395	±8	5,567	xAI	Proprietary
37	17◄─►68	deepseek-v3.2-exp-thinking	1394	±17	1,192	DeepSeek AI	MIT
38	17◄─►66	deepseek-v3.1	1393	±13	2,042	DeepSeek	MIT
39	18◄─►60	claude-sonnet-4-20250514-thinking-32k	1392	±9	4,480	Anthropic	Proprietary
40	19◄─►64	deepseek-v3-0324	1389	±8	6,236	DeepSeek	MIT
41	18◄─►66	gpt-5-chat	1389	±10	3,976	OpenAI	Proprietary
42	18◄─►68	deepseek-r1-0528	1389	±12	2,601	DeepSeek	MIT
43	20◄─►65	claude-3-7-sonnet-20250219-thinking-32k	1388	±8	5,395	Anthropic	Proprietary
44	17◄─►76	gpt-5.2-high	1386	±22	802	OpenAI	Proprietary
45	22◄─►68	o3-2025-04-16	1384	±7	7,913	OpenAI	Proprietary
46	18◄─►76	grok-4-fast-chat	1382	±19	984	xAI	Proprietary
47	22◄─►72	gemini-2.5-flash-preview-09-2025	1381	±10	4,346	Google	Proprietary
48	22◄─►73	gpt-5-high	1381	±10	4,330	OpenAI	Proprietary
49	27◄─►72	claude-sonnet-4-20250514	1381	±9	5,233	Anthropic	Proprietary
50	27◄─►72	mistral-medium-2508	1381	±8	6,757	Mistral	Proprietary
51	27◄─►73	o1-2024-12-17	1380	±9	4,683	OpenAI	Proprietary
52	27◄─►72	qwen3-235b-a22b-instruct-2507	1380	±7	7,407	Alibaba	Apache 2.0
53	20◄─►76	kimi-k2-0905-preview	1380	±15	1,473	Moonshot	Modified MIT
54	17◄─►87	deepseek-v3.1-terminus-thinking	1378	±28	431	DeepSeek AI	MIT
55	18◄─►83	hunyuan-t1-20250711	1378	±24	619	Tencent	Proprietary
56	27◄─►76	grok-4-fast-reasoning	1377	±12	2,397	xAI	Proprietary
57	32◄─►75	claude-haiku-4-5-20251001	1376	±10	4,120	Anthropic	Proprietary
58	32◄─►76	glm-4.5	1375	±11	3,152	Z.ai	MIT
59	33◄─►75	claude-3-7-sonnet-20250219	1374	±8	6,207	Anthropic	Proprietary
60	33◄─►76	deepseek-r1	1373	±10	3,339	DeepSeek	MIT
61	36◄─►77	gemini-2.5-flash-lite-preview-06-17-thinking	1371	±9	4,297	Google	Proprietary
62	35◄─►78	kimi-k2-0711-preview	1371	±10	3,650	Moonshot	Modified MIT
63	28◄─►86	qwen3-235b-a22b-thinking-2507	1370	±18	1,152	Alibaba	Apache 2.0
64	44◄─►77	claude-3-5-sonnet-20241022	1368	±6	12,002	Anthropic	Proprietary
65	44◄─►80	qwen3-235b-a22b-no-thinking	1367	±9	4,760	Alibaba	Apache 2.0
66	18◄─►108	hunyuan-vision-1.5-thinking	1365	±37	251	Tencent	Proprietary
67	33◄─►88	qwen3-vl-235b-a22b-instruct	1365	±17	1,231	Alibaba	Apache 2.0
68	44◄─►82	o1-preview	1365	±10	4,565	OpenAI	Proprietary
69	38◄─►88	mistral-large-3	1364	±15	1,640	Mistral	Apache 2.0
70	44◄─►86	qwen3-coder-480b-a35b-instruct	1364	±10	3,280	Alibaba	Apache 2.0
71	40◄─►88	hunyuan-turbos-20250416	1363	±15	1,599	Tencent	Proprietary
72	51◄─►87	mistral-medium-2505	1360	±9	4,355	Mistral	Proprietary
73	49◄─►91	mai-1-preview	1359	±13	2,209	Microsoft AI	Proprietary
74	53◄─►87	gemini-1.5-pro-002	1358	±7	8,148	Google	Proprietary
75	33◄─►103	mimo-v2-flash (non-thinking)	1358	±25	589	Xiaomi	MIT
76	51◄─►88	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1357	±9	4,470	Google	Proprietary
77	61◄─►91	qwen2.5-max	1353	±8	5,151	Alibaba	Proprietary
78	62◄─►96	deepseek-v3	1348	±10	3,655	DeepSeek	DeepSeek
79	63◄─►94	gemma-3-27b-it	1348	±7	6,617	Google	Gemma
80	65◄─►96	gemini-2.0-flash-001	1346	±8	6,483	Google	Proprietary
81	65◄─►97	gpt-4.1-mini-2025-04-14	1345	±9	5,303	OpenAI	Proprietary
82	65◄─►98	gemini-2.0-flash-lite-preview-02-05	1345	±9	4,174	Google	Proprietary
83	59◄─►113	qwen3-vl-235b-a22b-thinking	1344	±18	978	Alibaba	Apache 2.0
84	67◄─►104	gemini-advanced-0514	1342	±10	7,089	Google	Proprietary
85	74◄─►104	o4-mini-2025-04-16	1339	±8	6,012	OpenAI	Proprietary
86	74◄─►113	grok-3-mini-beta	1336	±11	2,954	xAI	Proprietary
87	76◄─►107	gpt-4o-2024-05-13	1336	±7	16,709	OpenAI	Proprietary
88	63◄─►122	step-2-16k-exp-202412	1335	±21	758	StepFun	Proprietary
89	76◄─►110	command-a-03-2025	1335	±7	7,818	Cohere	CC-BY-NC-4.0
90	62◄─►134	llama-3.1-nemotron-ultra-253b-v1	1333	±27	455	Nvidia	Nvidia Open Model
91	74◄─►121	longcat-flash-chat	1332	±16	1,354	Meituan	MIT
92	64◄─►127	gemma-3-12b-it	1331	±23	615	Google	Gemma
93	76◄─►121	grok-3-mini-high	1331	±13	2,134	xAI	Proprietary
94	77◄─►121	gpt-5-mini-high	1329	±11	3,480	OpenAI	Proprietary
95	77◄─►121	qwen3-235b-a22b	1329	±10	3,736	Alibaba	Apache 2.0
96	80◄─►121	glm-4.5-air	1327	±10	4,031	Z.ai	MIT
97	82◄─►121	gpt-4o-2024-08-06	1324	±8	6,818	OpenAI	Proprietary
98	81◄─►122	qwen3-30b-a3b-instruct-2507	1324	±11	3,021	Alibaba	Apache 2.0
99	70◄─►143	minimax-m2.1-preview	1323	±26	528	MiniMax	MIT
100	81◄─►123	mistral-small-2506	1322	±12	2,336	Mistral	Apache 2.0
101	84◄─►122	minimax-m1	1322	±9	4,752	MiniMax	Apache 2.0
102	84◄─►122	gpt-4-turbo-2024-04-09	1322	±8	14,494	OpenAI	Proprietary
103	85◄─►122	gemini-1.5-pro-001	1321	±8	11,903	Google	Proprietary
104	81◄─►132	qwen3-next-80b-a3b-thinking	1321	±14	1,752	Alibaba	Apache 2.0
105	79◄─►138	glm-4-plus-0111	1318	±19	935	Zhipu	Proprietary
106	86◄─►134	qwen3-next-80b-a3b-instruct	1317	±11	2,917	Alibaba	Apache 2.0
107	89◄─►124	grok-2-2024-08-13	1316	±7	9,381	xAI	Proprietary
108	81◄─►143	qwen-plus-0125	1315	±18	942	Alibaba	Proprietary
109	89◄─►138	o3-mini-high	1310	±11	3,082	OpenAI	Proprietary
110	89◄─►153	deepseek-v2.5-1210	1308	±17	1,100	DeepSeek	DeepSeek
111	84◄─►158	glm-4.5v	1308	±23	619	Z.ai	MIT
112	95◄─►139	llama-4-maverick-17b-128e-instruct	1307	±8	5,358	Meta	Llama 4
113	81◄─►165	nvidia-llama-3.3-nemotron-super-49b-v1.5	1306	±28	410	Nvidia	Nvidia Open
114	89◄─►154	gpt-4.1-nano-2025-04-14	1306	±18	1,013	OpenAI	Proprietary
115	87◄─►160	qwen3-32b	1304	±23	621	Alibaba	Apache 2.0
116	89◄─►159	step-3	1304	±21	792	StepFun	Apache 2.0
117	100◄─►144	llama-3.1-405b-instruct-fp8	1304	±7	9,074	Meta	Llama 3.1 Community
118	87◄─►161	intellect-3	1304	±22	755	Prime Intellect	MIT
119	102◄─►145	o3-mini	1302	±7	8,371	OpenAI	Proprietary
120	101◄─►147	claude-3-5-sonnet-20240620	1302	±7	12,521	Anthropic	Proprietary
121	87◄─►168	hunyuan-turbos-20250226	1301	±26	429	Tencent	Proprietary
122	89◄─►167	hunyuan-large-2025-02-10	1301	±24	571	Tencent	Proprietary
123	103◄─►148	llama-3.1-405b-instruct-bf16	1301	±7	6,604	Meta	Llama 3.1 Community
124	89◄─►169	hunyuan-turbo-0110	1300	±25	455	Tencent	Proprietary
125	104◄─►148	claude-3-5-haiku-20241022	1300	±6	10,106	Anthropic	Proprietary
126	103◄─►154	gemini-1.5-flash-002	1298	±9	5,076	Google	Proprietary
127	102◄─►157	gemma-3n-e4b-it	1298	±11	3,063	Google	Gemma
128	103◄─►157	yi-lightning	1297	±10	3,831	01 AI	Proprietary
129	86◄─►176	amazon-nova-experimental-chat-10-09	1296	±33	306	Amazon	Proprietary
130	89◄─►174	llama-3.3-nemotron-49b-super-v1	1295	±27	435	Nvidia	Nvidia
131	106◄─►158	qwq-32b	1295	±10	3,811	Alibaba	Apache 2.0
132	106◄─►157	gpt-4o-mini-2024-07-18	1294	±7	10,585	OpenAI	Proprietary
133	109◄─►158	gemma-2-27b-it	1291	±7	11,547	Google	Gemma license
134	106◄─►162	llama-4-scout-17b-16e-instruct	1290	±10	3,906	Meta	Llama
135	108◄─►165	glm-4-plus	1289	±10	3,834	Zhipu AI	Proprietary
136	102◄─►174	minimax-m2	1288	±21	862	MiniMax	Apache 2.0
137	104◄─►174	step-1o-turbo-202506	1288	±18	1,081	StepFun	Proprietary
138	116◄─►161	claude-3-opus-20240229	1287	±6	28,675	Anthropic	Proprietary
139	113◄─►166	mistral-large-2407	1287	±8	6,754	Mistral	Mistral Research
140	106◄─►174	magistral-medium-2506	1286	±16	1,414	Mistral	Proprietary
141	116◄─►165	llama-3.3-70b-instruct	1286	±7	8,294	Meta	Llama-3.3
142	116◄─►166	gpt-4-1106-preview	1286	±8	15,722	OpenAI	Proprietary
143	103◄─►177	hunyuan-large-vision	1285	±23	659	Tencent	Proprietary
144	114◄─►169	qwen3-30b-a3b	1285	±10	3,532	Alibaba	Apache 2.0
145	103◄─►180	amazon-nova-experimental-chat-11-10	1285	±23	654	Amazon	Proprietary
146	112◄─►169	qwen-max-0919	1284	±12	2,371	Alibaba	Qwen
147	109◄─►174	gemma-2-9b-it-simpo	1283	±14	1,672	Princeton	MIT
148	116◄─►169	gpt-oss-120b	1282	±10	3,955	OpenAI	Apache 2.0
149	111◄─►175	amazon-nova-experimental-chat-10-20	1281	±16	1,486	Amazon	Proprietary
150	119◄─►169	o1-mini	1280	±7	7,930	OpenAI	Proprietary
151	119◄─►172	gpt-4-0125-preview	1280	±8	14,105	OpenAI	Proprietary
152	113◄─►182	llama-3.1-nemotron-70b-instruct	1277	±19	1,003	Nvidia	Llama 3.1
153	109◄─►184	gemma-3-4b-it	1276	±22	680	Google	Gemma
154	126◄─►174	mistral-large-2411	1275	±9	4,503	Mistral	MRL
155	109◄─►185	hunyuan-standard-2025-02-10	1274	±24	593	Tencent	Proprietary
156	117◄─►182	nova-2-lite	1274	±17	1,398	Amazon	Proprietary
157	119◄─►181	qwen2.5-plus-1127	1274	±14	1,599	Alibaba	Proprietary
158	127◄─►177	mistral-small-3.1-24b-instruct-2503	1272	±9	4,291	Mistral	Apache 2.0
159	116◄─►185	ling-flash-2.0	1272	±21	832	Ant Group	MIT
160	130◄─►175	grok-2-mini-2024-08-13	1272	±7	7,963	xAI	Proprietary
161	129◄─►182	athene-70b-0725	1269	±11	3,128	NexusFlow	CC-BY-NC-4.0
162	125◄─►187	reka-core-20240904	1266	±18	1,046	Reka AI	Proprietary
163	137◄─►184	deepseek-v2.5	1265	±10	3,483	DeepSeek	DeepSeek
164	142◄─►184	gpt-4-0613	1264	±8	14,055	OpenAI	Proprietary
165	133◄─►187	command-r-plus-08-2024	1263	±15	1,479	Cohere	CC-BY-NC-4.0
166	143◄─►184	gemini-1.5-flash-001	1263	±8	9,125	Google	Proprietary
167	122◄─►193	llama-3.1-nemotron-51b-instruct	1260	±25	486	Nvidia	Llama 3.1
168	136◄─►190	jamba-1.5-large	1260	±16	1,377	AI21 Labs	Jamba Open
169	129◄─►193	olmo-3-32b-think	1259	±22	805	Allen AI	Apache 2.0
170	149◄─►185	llama-3.1-70b-instruct	1258	±8	8,365	Meta	Llama 3.1 Community
171	135◄─►192	ring-flash-2.0	1257	±20	888	Ant Group	MIT
172	151◄─►185	gemma-2-9b-it	1257	±7	8,426	Google	Gemma license
173	154◄─►187	llama-3-70b-instruct	1254	±7	23,005	Meta	Llama 3 Community
174	154◄─►188	qwen2.5-72b-instruct	1253	±8	5,742	Alibaba	Qwen
175	151◄─►190	gpt-4-0314	1253	±10	8,323	OpenAI	Proprietary
176	142◄─►194	gpt-5-nano-high	1252	±20	901	OpenAI	Proprietary
177	154◄─►190	athene-v2-chat	1252	±10	3,744	NexusFlow	NexusFlow
178	141◄─►198	llama-3.1-tulu-3-70b	1248	±25	445	Ai2	Llama 3.1
179	143◄─►198	ibm-granite-h-small	1247	±23	710	IBM	Apache 2.0
180	163◄─►193	claude-3-sonnet-20240229	1245	±8	15,719	Anthropic	Proprietary
181	156◄─►198	reka-flash-20240904	1242	±17	1,043	Reka AI	Proprietary
182	159◄─►195	glm-4-0520	1241	±15	1,553	Zhipu AI	Proprietary
183	130◄─►214	mercury	1240	±40	266	Inception AI	Proprietary
184	155◄─►203	nvidia-nemotron-3-nano-30b-a3b-bf16	1240	±21	919	Nvidia	NVIDIA Open Model
185	159◄─►200	gpt-oss-20b	1239	±18	1,292	OpenAI	Apache 2.0
186	167◄─►195	nemotron-4-340b-instruct	1238	±11	3,183	Nvidia	NVIDIA Open Model
187	170◄─►195	gemini-1.5-flash-8b-001	1238	±9	5,089	Google	Proprietary
188	171◄─►195	command-r-plus	1236	±8	11,116	Cohere	CC-BY-NC-4.0
189	171◄─►195	amazon-nova-pro-v1.0	1236	±9	3,999	Amazon	Proprietary
190	175◄─►203	c4ai-aya-expanse-32b	1227	±10	3,896	Cohere	CC-BY-NC-4.0
191	174◄─►206	mistral-small-24b-instruct-2501	1227	±12	2,445	Mistral	Apache 2.0
192	167◄─►214	olmo-2-0325-32b-instruct	1224	±24	578	Allen AI	Apache-2.0
193	178◄─►206	qwen2-72b-instruct	1223	±9	5,560	Alibaba	Qianwen LICENSE
194	179◄─►206	amazon-nova-lite-v1.0	1220	±10	3,092	Amazon	Proprietary
195	174◄─►215	ministral-8b-2410	1219	±22	685	Mistral	MRL
196	187◄─►207	claude-3-haiku-20240307	1215	±7	16,882	Anthropic	Proprietary
197	188◄─►214	mistral-large-2402	1211	±9	9,160	Mistral	Proprietary
198	184◄─►219	command-r-08-2024	1210	±15	1,432	Cohere	CC-BY-NC-4.0
199	184◄─►219	jamba-1.5-mini	1210	±16	1,404	AI21 Labs	Jamba Open
200	188◄─►214	phi-4	1210	±9	4,115	Microsoft	MIT
201	187◄─►225	qwen2.5-coder-32b-instruct	1203	±19	851	Alibaba	Apache 2.0
202	190◄─►222	deepseek-coder-v2	1203	±13	2,287	DeepSeek AI	DeepSeek License
203	190◄─►222	gemini-pro-dev-api	1202	±14	3,070	Google	Proprietary
204	190◄─►225	wizardlm-70b	1198	±17	1,787	Microsoft	Llama 2 Community
205	193◄─►223	amazon-nova-micro-v1.0	1198	±11	3,117	Amazon	Proprietary
206	194◄─►222	llama-3-8b-instruct	1196	±8	15,560	Meta	Llama 3 Community
207	194◄─►223	command-r	1196	±10	7,917	Cohere	CC-BY-NC-4.0
208	184◄─►232	hunyuan-standard-256k	1195	±29	363	Tencent	Proprietary
209	188◄─►229	llama-3.1-tulu-3-8b	1194	±25	479	Ai2	Llama 3.1
210	194◄─►225	mistral-medium	1194	±11	5,613	Mistral	Proprietary
211	194◄─►225	qwen1.5-110b-chat	1193	±11	3,728	Alibaba	Qianwen LICENSE
212	194◄─►228	c4ai-aya-expanse-8b	1190	±15	1,549	Cohere	CC-BY-NC-4.0
213	198◄─►225	mixtral-8x22b-instruct-v0.1	1190	±9	7,564	Mistral	Apache 2.0
214	199◄─►227	qwen1.5-72b-chat	1187	±10	5,955	Alibaba	Qianwen LICENSE
215	199◄─►226	gpt-3.5-turbo-0125	1187	±9	9,820	OpenAI	Proprietary
216	194◄─►232	openchat-3.5	1184	±18	1,467	OpenChat	Apache-2.0
217	201◄─►228	gemma-2-2b-it	1183	±8	7,165	Google	Gemma license
218	194◄─►239	gemini-pro	1182	±21	954	Google	Proprietary
219	199◄─►232	reka-flash-21b-20240226-online	1181	±14	2,133	Reka AI	Proprietary
220	206◄─►229	llama-3.1-8b-instruct	1178	±8	7,431	Meta	Llama 3.1 Community
221	204◄─►235	reka-flash-21b-20240226	1176	±12	3,529	Reka AI	Proprietary
222	206◄─►238	vicuna-33b	1173	±12	4,045	LMSYS	Non-commercial
223	199◄─►253	granite-3.1-8b-instruct	1170	±26	460	IBM	Apache 2.0
224	201◄─►253	zephyr-orpo-141b-A35b-v0.1	1167	±23	643	HuggingFace	Apache 2.0
225	213◄─►246	dbrx-instruct-preview	1164	±12	4,858	Databricks	DBRX LICENSE
226	217◄─►249	mixtral-8x7b-instruct-v0.1	1159	±8	11,287	Mistral	Apache 2.0
227	215◄─►249	yi-1.5-34b-chat	1159	±11	3,653	01 AI	Apache-2.0
228	211◄─►255	openhermes-2.5-mistral-7b	1157	±22	814	NousResearch	Apache-2.0
229	217◄─►253	yi-34b-chat	1155	±14	2,405	01 AI	Yi License
230	201◄─►262	falcon-180b-chat	1153	±37	270	TII	Falcon-180B TII License
231	220◄─►255	gpt-3.5-turbo-1106	1151	±15	2,859	OpenAI	Proprietary
232	223◄─►253	phi-3-medium-4k-instruct	1150	±11	3,757	Microsoft	MIT
233	212◄─►259	granite-3.1-2b-instruct	1149	±29	447	IBM	Apache 2.0
234	223◄─►255	gemma-1.1-7b-it	1147	±11	3,463	Google	Gemma license
235	222◄─►256	openchat-3.5-0106	1147	±15	1,875	OpenChat	Apache-2.0
236	220◄─►256	tulu-2-dpo-70b	1147	±19	1,132	AllenAI/UW	AI2 ImpACT Low-risk
237	221◄─►257	llama-3.2-3b-instruct	1144	±20	1,079	Meta	Llama 3.2
238	223◄─►256	snowflake-arctic-instruct	1143	±12	4,848	Snowflake	Apache 2.0
239	223◄─►258	wizardlm-13b	1141	±18	1,383	Microsoft	Llama 2 Community
240	220◄─►262	solar-10.7b-instruct-v1.0	1140	±24	707	Upstage AI	CC-BY-NC-4.0
241	224◄─►257	qwen1.5-14b-chat	1138	±14	2,405	Alibaba	Qianwen LICENSE
242	223◄─►262	granite-3.0-8b-instruct	1137	±21	903	IBM	Apache 2.0
243	223◄─►263	nous-hermes-2-mixtral-8x7b-dpo	1136	±23	618	NousResearch	Apache-2.0
244	224◄─►259	starling-lm-7b-alpha	1136	±16	1,709	UC Berkeley	CC-BY-NC-4.0
245	224◄─►260	zephyr-7b-beta	1136	±16	2,007	HuggingFace	MIT
246	217◄─►275	dolphin-2.2.1-mistral-7b	1135	±34	291	Cognitive Computations	Apache-2.0
247	221◄─►269	guanaco-33b	1134	±27	517	UW	Non-commercial
248	226◄─►259	phi-3-small-8k-instruct	1134	±13	2,421	Microsoft	MIT
249	221◄─►271	mpt-30b-chat	1133	±29	456	MosaicML	CC-BY-NC-SA-4.0
250	226◄─►259	qwen1.5-32b-chat	1133	±12	3,059	Alibaba	Qianwen LICENSE
251	223◄─►265	deepseek-llm-67b-chat	1132	±22	796	DeepSeek AI	DeepSeek License
252	226◄─►262	internlm2_5-20b-chat	1131	±16	1,448	InternLM	Other
253	230◄─►263	vicuna-13b	1125	±13	3,384	LMSYS	Llama 2 Community
254	226◄─►277	llama2-70b-steerlm-chat	1120	±25	611	Nvidia	Llama 2 Community
255	238◄─►272	llama-2-70b-chat	1113	±10	6,433	Meta	Llama 2 Community
256	236◄─►277	starling-lm-7b-beta	1110	±15	2,402	Nexusflow	Apache-2.0
257	230◄─►279	qwq-32b-preview	1108	±29	459	Alibaba	Apache 2.0
258	244◄─►277	mistral-7b-instruct-v0.2	1106	±12	2,981	Mistral	Apache-2.0
259	233◄─►280	zephyr-7b-alpha	1103	±30	400	HuggingFace	MIT
260	239◄─►279	qwen-14b-chat	1101	±21	908	Alibaba	Qianwen LICENSE
261	244◄─►279	gemma-7b-it	1099	±18	1,364	Google	Gemma license
262	243◄─►279	granite-3.0-2b-instruct	1099	±21	921	IBM	Apache 2.0
263	251◄─►279	phi-3-mini-4k-instruct-june-2024	1095	±15	1,982	Microsoft	MIT
264	251◄─►279	mistral-7b-instruct	1093	±17	1,704	Mistral	Apache 2.0
265	252◄─►279	llama-2-13b-chat	1093	±12	3,328	Meta	Llama 2 Community
266	250◄─►280	stripedhyena-nous-7b	1091	±21	873	Together AI	Apache 2.0
267	251◄─►279	gemma-1.1-2b-it	1090	±17	1,509	Google	Gemma license
268	250◄─►280	alpaca-13b	1090	±22	969	Stanford	Non-commercial
269	251◄─►280	vicuna-7b	1089	±18	1,333	LMSYS	Llama 2 Community
270	254◄─►280	phi-3-mini-128k-instruct	1087	±14	3,004	Microsoft	MIT
271	253◄─►280	palm-2	1087	±17	1,598	Google	Proprietary
272	254◄─►280	codellama-34b-instruct	1086	±17	1,522	Meta	Llama 2 Community
273	252◄─►282	llama-3.2-1b-instruct	1085	±20	1,108	Meta	Llama 3.2
274	254◄─►283	qwen1.5-7b-chat	1080	±23	705	Alibaba	Qianwen LICENSE
275	248◄─►283	smollm2-1.7b-instruct	1079	±35	348	HuggingFace	Apache 2.0
276	255◄─►283	gemma-2b-it	1075	±23	699	Google	Gemma license
277	258◄─►283	llama-2-7b-chat	1074	±13	2,367	Meta	Llama 2 Community
278	258◄─►283	phi-3-mini-4k-instruct	1071	±13	2,886	Microsoft	MIT
279	255◄─►287	gpt4all-13b-snoozy	1062	±37	256	Nomic AI	Non-commercial
280	266◄─►287	mpt-7b-chat	1049	±24	692	MosaicML	CC-BY-NC-SA-4.0
281	273◄─►285	qwen1.5-4b-chat	1048	±19	1,090	Alibaba	Qianwen LICENSE
282	273◄─►287	koala-13b	1044	±21	1,207	UC Berkeley	Non-commercial
283	274◄─►287	chatglm3-6b	1040	±23	819	Tsinghua	Apache-2.0
284	279◄─►289	oasst-pythia-12b	1010	±20	1,102	OpenAssistant	Apache 2.0
285	280◄─►289	olmo-7b-instruct	1006	±20	1,028	Allen AI	Apache-2.0
286	279◄─►289	chatglm2-6b	1005	±26	570	Tsinghua	Apache-2.0
287	280◄─►289	RWKV-4-Raven-14B	1004	±23	889	RWKV	Apache 2.0
288	284◄─►291	fastchat-t5-3b	989	±24	753	LMSYS	Apache 2.0
289	284◄─►292	dolly-v2-12b	967	±28	571	Databricks	MIT
290	288◄─►292	chatglm-6b	952	±25	775	Tsinghua	Non-commercial
291	288◄─►292	llama-13b	931	±34	433	Meta	Non-commercial
292	289◄─►292	stablelm-tuned-alpha-7b	930	±28	543	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

Confidence Intervals on Model Strength (via Bootstrapping)

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