Text Arena

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

Feb 9, 2026

914,516 votes

299 models

/

Style Control

	Rank Spread
1	12	claude-opus-4-6-thinking Anthropic · Proprietary	1553±22	745
2	14	claude-opus-4-6 Anthropic · Proprietary	1530±19	983
3	25	claude-opus-4-5-20251101-thinking-32k Anthropic · Proprietary	1509±9	5,336
4	211	kimi-k2.5-instant Moonshot · Modified MIT	1501±21	803
5	38	claude-opus-4-5-20251101 Anthropic · Proprietary	1496±8	6,657
6	411	claude-sonnet-4-5-20250929-thinking-32k Anthropic · Proprietary	1487±7	9,737
7	412	gemini-3-pro Google · Proprietary	1483±8	7,339
8	413	kimi-k2.5-thinking Moonshot · Modified MIT	1483±14	1,699
9	512	claude-opus-4-1-20250805-thinking-16k Anthropic · Proprietary	1480±7	9,882
10	513	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1479±7	9,096
11	716	claude-opus-4-1-20250805 Anthropic · Proprietary	1472±6	14,970
12	528	longcat-flash-chat Meituan · MIT	1468±13	2,260
13	939	ernie-5.0-0110 Baidu · Proprietary	1460±13	2,216
14	1133	gemini-3-flash Google · Proprietary	1459±9	5,369
15	1136	qwen3-max-preview Alibaba · Proprietary	1457±8	5,356
16	1233	gemini-2.5-pro Google · Proprietary	1457±5	18,355
17	1142	glm-4.7 Z.ai · MIT	1456±12	2,434
18	1239	gpt-5.1-high OpenAI · Proprietary	1455±8	6,169
19	1239	grok-4.1-thinking xAI · Proprietary	1454±8	7,055
20	1242	glm-4.6 Z.ai · MIT	1451±7	7,518
21	1247	gemini-3-flash (thinking-minimal) Google · Proprietary	1451±10	3,570
22	1245	kimi-k2-thinking-turbo Moonshot · Modified MIT	1450±8	6,924
23	1244	claude-haiku-4-5-20251001 Anthropic · Proprietary	1450±7	9,416
24	1246	grok-4.1 xAI · Proprietary	1450±8	7,867
25	1248	deepseek-v3.2 DeepSeek · MIT	1448±9	5,508
26	1251	deepseek-v3.2-thinking DeepSeek · MIT	1446±10	4,150
27	1351	mistral-large-3 Mistral · Apache 2.0	1445±9	4,914
28	1254	gpt-5.2 OpenAI · Proprietary	1444±12	2,598
29	1354	gpt-5.2-high OpenAI · Proprietary	1444±11	3,230
30	1651	qwen3-235b-a22b-instruct-2507 Alibaba · Apache 2.0	1443±6	13,706
31	1355	qwen3-max-2025-09-23 Alibaba · Proprietary	1442±13	2,040
32	1553	claude-opus-4-20250514-thinking-16k Anthropic · Proprietary	1442±8	6,753
33	1554	qwen3-next-80b-a3b-instruct Alibaba · Apache 2.0	1441±9	4,810
34	1358	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1439±13	2,370
35	1656	mimo-v2-flash (non-thinking) Xiaomi · MIT	1438±10	3,439
36	1360	deepseek-v3.2-exp-thinking DeepSeek · MIT	1438±13	1,907
37	1956	gpt-5-high OpenAI · Proprietary	1437±8	6,454
38	1660	deepseek-v3.2-exp DeepSeek · MIT	1436±12	2,506
39	2156	gpt-5.1 OpenAI · Proprietary	1435±8	6,938
40	1269	amazon-nova-experimental-chat-12-10 Amazon · Proprietary	1434±21	715
41	2459	grok-3-preview-02-24 xAI · Proprietary	1433±8	5,499
42	2359	glm-4.5 Z.ai · MIT	1433±9	4,809
43	2260	amazon-nova-experimental-chat-11-10 Amazon · Proprietary	1433±10	3,363
44	2658	mistral-medium-2508 Mistral · Proprietary	1432±6	12,876
45	2167	qwen3-vl-235b-a22b-thinking Alibaba · Apache 2.0	1429±14	1,633
46	1969	grok-4-fast-chat xAI · Proprietary	1428±16	1,255
47	2666	deepseek-r1-0528 DeepSeek · MIT	1427±11	2,794
48	2569	ernie-5.0-preview-1203 Baidu · Proprietary	1426±13	1,988
49	1579	deepseek-v3.1-terminus-thinking DeepSeek · MIT	1426±23	648
50	2968	minimax-m2.1-preview MiniMax · MIT	1424±11	3,161
51	3463	gemini-2.5-flash Google · Proprietary	1424±5	17,674
52	2670	qwen3-235b-a22b-thinking-2507 Alibaba · Apache 2.0	1424±15	1,628
53	3369	grok-4-fast-reasoning xAI · Proprietary	1420±9	3,961
54	3075	deepseek-v3.1-thinking DeepSeek · MIT	1420±13	1,905
55	1985	hunyuan-vision-1.5-thinking Tencent · Proprietary	1418±27	439
56	3770	qwen3-30b-a3b-instruct-2507 Alibaba · Apache 2.0	1418±9	4,694
57	2980	ernie-5.0-preview-1022 Baidu · Proprietary	1416±19	910
58	4470	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1415±5	15,704
59	3979	deepseek-v3.1 DeepSeek · MIT	1414±12	2,651
60	4179	amazon-nova-experimental-chat-10-20 Amazon · Proprietary	1412±12	2,316
61	4477	claude-sonnet-4-20250514-thinking-32k Anthropic · Proprietary	1412±8	6,515
62	4479	qwen3-coder-480b-a35b-instruct Alibaba · Apache 2.0	1411±9	4,985
63	4579	grok-4-0709 xAI · Proprietary	1409±7	8,259
64	4579	grok-4-1-fast-reasoning xAI · Proprietary	1408±8	5,821
65	4779	o3-2025-04-16 OpenAI · Proprietary	1408±6	11,938
66	4679	gpt-5-mini-high OpenAI · Proprietary	1407±8	5,518
67	3792	deepseek-v3.1-terminus DeepSeek · MIT	1406±21	793
68	5581	claude-opus-4-20250514 Anthropic · Proprietary	1401±7	8,019
69	5582	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1401±8	6,877
70	4889	kimi-k2-0905-preview Moonshot · Modified MIT	1401±12	2,262
71	5583	gpt-5-chat OpenAI · Proprietary	1400±8	5,999
72	5686	qwen3-235b-a22b-no-thinking Alibaba · Apache 2.0	1398±8	7,127
73	5293	gpt-4.5-preview-2025-02-27 OpenAI · Proprietary	1397±13	1,939
74	5593	mai-1-preview Microsoft AI · Proprietary	1396±11	2,804
75	5789	glm-4.5-air Z.ai · MIT	1395±8	6,139
76	5798	qwen3-next-80b-a3b-thinking Alibaba · Apache 2.0	1392±11	2,706
77	56100	ling-flash-2.0 Ant Group · MIT	1391±15	1,532
78	45116	glm-4.6v Z.ai · MIT	1391±25	538
79	6694	gpt-4.1-2025-04-14 OpenAI · Proprietary	1390±7	9,435
80	55115	hunyuan-t1-20250711 Tencent · Proprietary	1387±20	808
81	65107	nova-2-lite Amazon · Proprietary	1386±12	2,553
82	67101	qwen3-235b-a22b Alibaba · Apache 2.0	1385±9	4,418
83	68100	mistral-medium-2505 Mistral · Proprietary	1384±8	6,006
84	69110	nvidia-nemotron-3-nano-30b-a3b-bf16 Nvidia · NVIDIA Open Model	1381±11	3,288
85	73108	claude-sonnet-4-20250514 Anthropic · Proprietary	1380±7	7,516
86	73109	gpt-oss-120b OpenAI · Apache 2.0	1379±8	6,517
87	70115	o3-mini-high OpenAI · Proprietary	1379±12	2,595
88	73111	kimi-k2-0711-preview Moonshot · Modified MIT	1378±8	5,353
89	74116	grok-3-mini-high xAI · Proprietary	1375±10	3,358
90	71117	glm-4.7-flash Z.ai · MIT	1374±15	1,609
91	77116	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1374±8	6,107
92	71117	minimax-m2 MiniMax · Apache 2.0	1374±15	1,532
93	78116	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1372±7	9,756
94	76117	deepseek-r1 DeepSeek · MIT	1372±12	2,318
95	71120	intellect-3 Prime Intellect · MIT	1370±19	978
96	81117	o4-mini-2025-04-16 OpenAI · Proprietary	1368±7	8,830
97	81117	deepseek-v3-0324 DeepSeek · MIT	1368±7	8,488
98	81117	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1368±7	7,064
99	78117	o1-2024-12-17 OpenAI · Proprietary	1367±9	3,974
100	80117	o1-preview OpenAI · Proprietary	1367±9	5,123
101	69127	amazon-nova-experimental-chat-10-09 Amazon · Proprietary	1367±24	555
102	77120	ring-flash-2.0 Ant Group · MIT	1366±15	1,549
103	82119	grok-3-mini-beta xAI · Proprietary	1365±9	4,356
104	77121	step-3 StepFun · Apache 2.0	1365±17	1,246
105	84120	claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary	1363±8	6,291
106	86118	o3-mini OpenAI · Proprietary	1363±6	9,596
107	85120	o1-mini OpenAI · Proprietary	1363±7	8,482
108	81121	hunyuan-turbos-20250416 Tencent · Proprietary	1362±14	1,803
109	83120	mistral-small-2506 Mistral · Apache 2.0	1362±10	3,415
110	86120	minimax-m1 MiniMax · Apache 2.0	1360±8	6,634
111	86120	qwen2.5-max Alibaba · Proprietary	1360±8	5,183
112	77131	qwen3-32b Alibaba · Apache 2.0	1358±25	513
113	81134	nvidia-llama-3.3-nemotron-super-49b-v1.5 Nvidia · Nvidia Open	1354±22	670
114	92128	olmo-3.1-32b-instruct Allen AI · Apache 2.0	1352±13	2,321
115	88128	gpt-5-nano-high OpenAI · Proprietary	1352±15	1,696
116	86132	glm-4.5v Z.ai · MIT	1351±19	996
117	100126	gemini-2.0-flash-001 Google · Proprietary	1350±7	7,126
118	81145	hunyuan-turbos-20250226 Tencent · Proprietary	1343±32	275
119	111128	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1342±5	15,077
120	102139	step-1o-turbo-202506 StepFun · Proprietary	1341±15	1,566
121	111132	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1339±7	7,270
122	111134	qwen3-30b-a3b Alibaba · Apache 2.0	1339±9	4,625
123	111139	qwq-32b Alibaba · Apache 2.0	1335±9	4,108
124	116140	command-a-03-2025 Cohere · CC-BY-NC-4.0	1331±6	10,344
125	111147	qwen-plus-0125 Alibaba · Proprietary	1328±18	893
126	101156	mercury Inception AI · Proprietary	1327±29	398
127	116144	deepseek-v3 DeepSeek · DeepSeek	1325±10	3,281
128	121144	gemma-3-27b-it Google · Gemma	1323±7	8,206
129	119145	gemini-2.0-flash-lite-preview-02-05 Google · Proprietary	1322±10	3,475
130	113151	olmo-3-32b-think Allen AI · Apache 2.0	1322±19	1,056
131	117147	magistral-medium-2506 Mistral · Proprietary	1321±12	2,298
132	109164	hunyuan-turbo-0110 Tencent · Proprietary	1320±30	299
133	116157	step-2-16k-exp-202412 StepFun · Proprietary	1317±20	738
134	121152	qwen2.5-plus-1127 Alibaba · Proprietary	1315±14	1,554
135	124151	yi-lightning 01 AI · Proprietary	1313±10	4,316
136	124151	athene-v2-chat NexusFlow · NexusFlow	1313±9	4,019
137	112167	llama-3.1-nemotron-ultra-253b-v1 Nvidia · Nvidia Open Model	1312±30	367
138	124151	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1310±8	6,237
139	121161	deepseek-v2.5-1210 DeepSeek · DeepSeek	1310±17	1,079
140	121164	hunyuan-large-vision Tencent · Proprietary	1309±19	993
141	124159	gpt-oss-20b OpenAI · Apache 2.0	1307±13	2,179
142	119167	hunyuan-large-2025-02-10 Tencent · Proprietary	1307±25	519
143	126154	claude-3-5-sonnet-20240620 Anthropic · Proprietary	1307±7	13,609
144	123165	gpt-4.1-nano-2025-04-14 OpenAI · Proprietary	1306±19	807
145	128157	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1303±7	7,132
146	128161	deepseek-v2.5 DeepSeek · DeepSeek	1302±9	4,252
147	130163	gpt-4o-2024-05-13 OpenAI · Proprietary	1298±6	19,526
148	121180	llama-3.3-nemotron-49b-super-v1 Nvidia · Nvidia	1295±32	285
149	134164	gemini-1.5-pro-002 Google · Proprietary	1295±7	9,174
150	135165	qwen2.5-72b-instruct Alibaba · Qwen	1293±8	6,687
151	136167	llama-3.1-405b-instruct-bf16 Meta · Llama 3.1 Community	1292±7	6,251
152	130173	olmo-3.1-32b-think Allen AI · Apache 2.0	1291±15	1,604
153	135167	glm-4-plus Zhipu AI · Proprietary	1291±9	4,450
154	137167	gpt-4o-mini-2024-07-18 OpenAI · Proprietary	1290±6	10,944
155	136170	qwen-max-0919 Alibaba · Qwen	1288±11	2,756
156	139168	grok-2-2024-08-13 xAI · Proprietary	1288±7	10,367
157	130176	glm-4-plus-0111 Zhipu · Proprietary	1287±18	894
158	142168	claude-3-5-haiku-20241022 Anthropic · Proprietary	1286±6	11,363
159	139170	llama-4-scout-17b-16e-instruct Meta · Llama	1286±9	5,347
160	143170	llama-3.1-405b-instruct-fp8 Meta · Llama 3.1 Community	1284±7	9,714
161	142172	gpt-4o-2024-08-06 OpenAI · Proprietary	1284±8	7,319
162	130183	gemma-3-12b-it Google · Gemma	1282±23	543
163	148176	mistral-large-2407 Mistral · Mistral Research	1277±8	7,590
164	140183	qwen2.5-coder-32b-instruct Alibaba · Apache 2.0	1276±18	873
165	148177	mistral-large-2411 Mistral · MRL	1276±9	4,214
166	146184	llama-3.1-nemotron-70b-instruct Nvidia · Llama 3.1	1272±15	1,312
167	153181	gemma-3n-e4b-it Google · Gemma	1271±10	3,607
168	155181	amazon-nova-pro-v1.0 Amazon · Proprietary	1270±9	3,854
169	140187	hunyuan-standard-2025-02-10 Tencent · Proprietary	1270±24	549
170	158179	llama-3.3-70b-instruct Meta · Llama-3.3	1270±6	8,845
171	158180	grok-2-mini-2024-08-13 xAI · Proprietary	1269±7	8,653
172	159181	gpt-4-turbo-2024-04-09 OpenAI · Proprietary	1269±7	17,110
173	155184	athene-70b-0725 NexusFlow · CC-BY-NC-4.0	1267±11	3,122
174	160182	gemini-1.5-pro-001 Google · Proprietary	1267±8	12,749
175	160182	claude-3-opus-20240229 Anthropic · Proprietary	1265±6	33,751
176	160186	gemini-1.5-flash-002 Google · Proprietary	1262±8	5,893
177	162186	llama-3.1-70b-instruct Meta · Llama 3.1 Community	1260±7	9,390
178	163187	gemini-advanced-0514 Google · Proprietary	1255±9	8,138
179	166187	gpt-4-1106-preview OpenAI · Proprietary	1254±7	15,608
180	164193	deepseek-coder-v2 DeepSeek · DeepSeek License	1251±12	2,671
181	173192	gpt-4-0125-preview OpenAI · Proprietary	1250±8	15,292
182	163194	ibm-granite-h-small IBM · Apache 2.0	1249±17	1,272
183	171194	mistral-small-24b-instruct-2501 Mistral · Apache 2.0	1246±12	2,083
184	177195	amazon-nova-lite-v1.0 Amazon · Proprietary	1239±10	3,060
185	180196	gemini-1.5-flash-001 Google · Proprietary	1236±8	10,680
186	169203	llama-3.1-tulu-3-70b Ai2 · Llama 3.1	1236±24	450
187	181197	phi-4 Microsoft · MIT	1232±10	3,304
188	175204	hunyuan-standard-256k Tencent · Proprietary	1231±25	497
189	175204	gemma-3-4b-it Google · Gemma	1231±24	606
190	180201	reka-core-20240904 Reka AI · Proprietary	1230±16	1,216
191	180201	glm-4-0520 Zhipu AI · Proprietary	1228±14	1,718
192	180202	jamba-1.5-large AI21 Labs · Jamba Open	1228±15	1,440
193	180210	llama-3.1-nemotron-51b-instruct Nvidia · Llama 3.1	1223±22	665
194	184201	claude-3-sonnet-20240229 Anthropic · Proprietary	1223±7	18,888
195	185204	amazon-nova-micro-v1.0 Amazon · Proprietary	1218±10	2,980
196	186203	gemini-1.5-flash-8b-001 Google · Proprietary	1218±8	6,067
197	187209	gemma-2-27b-it Google · Gemma license	1211±6	12,090
198	182216	olmo-2-0325-32b-instruct Allen AI · Apache-2.0	1211±28	427
199	187211	nemotron-4-340b-instruct Nvidia · NVIDIA Open Model	1210±11	3,254
200	187211	gpt-4-0314 OpenAI · Proprietary	1209±9	8,308
201	190211	llama-3-70b-instruct Meta · Llama 3 Community	1206±7	28,131
202	187215	ministral-8b-2410 Mistral · MRL	1202±19	838
203	196214	claude-3-haiku-20240307 Anthropic · Proprietary	1199±7	20,901
204	196215	c4ai-aya-expanse-32b Cohere · CC-BY-NC-4.0	1197±9	4,686
205	196215	qwen2-72b-instruct Alibaba · Qianwen LICENSE	1196±9	6,249
206	197215	llama-3.1-8b-instruct Meta · Llama 3.1 Community	1195±7	8,584
207	196221	gemma-2-9b-it-simpo Princeton · MIT	1191±15	1,471
208	196223	reka-flash-20240904 Reka AI · Proprietary	1190±15	1,207
209	201220	gpt-4-0613 OpenAI · Proprietary	1188±8	13,720
210	198225	command-r-plus-08-2024 Cohere · CC-BY-NC-4.0	1187±14	1,675
211	191229	granite-3.1-8b-instruct IBM · Apache 2.0	1187±26	478
212	201225	qwen1.5-110b-chat Alibaba · Qianwen LICENSE	1184±10	4,763
213	193230	llama-3.1-tulu-3-8b Ai2 · Llama 3.1	1184±25	476
214	202223	mistral-large-2402 Mistral · Proprietary	1183±9	10,419
215	201229	jamba-1.5-mini AI21 Labs · Jamba Open	1179±15	1,352
216	207227	gemma-2-9b-it Google · Gemma license	1174±7	8,923
217	207229	command-r-plus Cohere · CC-BY-NC-4.0	1172±8	13,944
218	206230	command-r-08-2024 Cohere · CC-BY-NC-4.0	1170±13	1,783
219	207230	yi-1.5-34b-chat 01 AI · Apache-2.0	1170±11	3,842
220	211230	mixtral-8x22b-instruct-v0.1 Mistral · Apache 2.0	1166±9	8,781
221	209230	qwen1.5-72b-chat Alibaba · Qianwen LICENSE	1166±10	6,366
222	208231	reka-flash-21b-20240226-online Reka AI · Proprietary	1165±13	2,879
223	213231	mistral-medium Mistral · Proprietary	1162±11	5,149
224	209233	c4ai-aya-expanse-8b Cohere · CC-BY-NC-4.0	1161±15	1,567
225	213233	internlm2_5-20b-chat InternLM · Other	1159±14	1,684
226	207241	qwq-32b-preview Alibaba · Apache 2.0	1156±24	567
227	214234	qwen1.5-32b-chat Alibaba · Qianwen LICENSE	1155±11	3,931
228	214234	reka-flash-21b-20240226 Reka AI · Proprietary	1154±11	4,750
229	217234	llama-3-8b-instruct Meta · Llama 3 Community	1152±8	18,377
230	211245	granite-3.1-2b-instruct IBM · Apache 2.0	1150±25	508
231	222242	starling-lm-7b-beta Nexusflow · Apache-2.0	1143±13	2,948
232	224245	qwen1.5-14b-chat Alibaba · Qianwen LICENSE	1138±13	3,208
233	226243	gpt-3.5-turbo-0125 OpenAI · Proprietary	1137±8	11,127
234	229245	dbrx-instruct-preview Databricks · DBRX LICENSE	1132±11	5,501
235	229246	phi-3-medium-4k-instruct Microsoft · MIT	1131±10	3,973
236	224251	zephyr-orpo-141b-A35b-v0.1 HuggingFace · Apache 2.0	1130±21	832
237	229247	command-r Cohere · CC-BY-NC-4.0	1128±9	9,648
238	229247	mixtral-8x7b-instruct-v0.1 Mistral · Apache 2.0	1127±8	11,789
239	229258	tulu-2-dpo-70b AllenAI/UW · AI2 ImpACT Low-risk	1117±21	805
240	229257	gpt-3.5-turbo-1106 OpenAI · Proprietary	1116±16	2,122
241	232257	openchat-3.5-0106 OpenChat · Apache-2.0	1113±14	2,003
242	235253	gemma-2-2b-it Google · Gemma license	1113±8	7,299
243	230259	granite-3.0-8b-instruct IBM · Apache 2.0	1113±18	1,109
244	232257	yi-34b-chat 01 AI · Yi License	1112±13	2,346
245	229267	gemini-pro Google · Proprietary	1108±24	678
246	231266	qwen1.5-7b-chat Alibaba · Qianwen LICENSE	1108±21	771
247	238264	gemini-pro-dev-api Google · Proprietary	1104±14	2,681
248	238264	phi-3-small-8k-instruct Microsoft · MIT	1102±12	3,218
249	238268	llama-3.2-3b-instruct Meta · Llama 3.2	1098±16	1,351
250	238268	starling-lm-7b-alpha UC Berkeley · CC-BY-NC-4.0	1098±16	1,397
251	236270	deepseek-llm-67b-chat DeepSeek · DeepSeek License	1096±24	649
252	239268	phi-3-mini-4k-instruct-june-2024 Microsoft · MIT	1093±14	1,841
253	240268	phi-3-mini-4k-instruct Microsoft · MIT	1093±12	3,450
254	239270	granite-3.0-2b-instruct IBM · Apache 2.0	1091±17	1,134
255	240268	snowflake-arctic-instruct Snowflake · Apache 2.0	1090±11	5,737
256	244270	gemma-1.1-7b-it Google · Gemma license	1084±10	4,332
257	245270	mistral-7b-instruct-v0.2 Mistral · Apache-2.0	1082±12	3,113
258	240273	wizardlm-70b Microsoft · Llama 2 Community	1082±20	988
259	240274	nous-hermes-2-mixtral-8x7b-dpo NousResearch · Apache-2.0	1080±24	575
260	247270	llama-2-70b-chat Meta · Llama 2 Community	1079±10	5,715
261	245271	vicuna-33b LMSYS · Non-commercial	1079±13	2,866
262	245275	openchat-3.5 OpenChat · Apache-2.0	1075±20	971
263	243278	qwen-14b-chat Alibaba · Qianwen LICENSE	1072±24	599
264	248275	llama-3.2-1b-instruct Meta · Llama 3.2	1071±16	1,346
265	245278	solar-10.7b-instruct-v1.0 Upstage AI · CC-BY-NC-4.0	1067±27	482
266	247278	openhermes-2.5-mistral-7b NousResearch · Apache-2.0	1065±24	589
267	254277	llama-2-13b-chat Meta · Llama 2 Community	1063±13	2,624
268	245287	zephyr-7b-alpha HuggingFace · MIT	1053±41	201
269	249285	smollm2-1.7b-instruct HuggingFace · Apache 2.0	1050±33	352
270	260283	gemma-7b-it Google · Gemma license	1049±17	1,381
271	259283	codellama-34b-instruct Meta · Llama 2 Community	1046±21	853
272	260283	zephyr-7b-beta HuggingFace · MIT	1045±18	1,249
273	262283	vicuna-13b LMSYS · Llama 2 Community	1041±14	2,389
274	264283	phi-3-mini-128k-instruct Microsoft · MIT	1040±13	3,889
275	254287	mpt-30b-chat MosaicML · CC-BY-NC-SA-4.0	1040±36	258
276	261287	wizardlm-13b Microsoft · Llama 2 Community	1035±22	735
277	265284	gemma-1.1-2b-it Google · Gemma license	1035±14	1,963
278	264287	llama2-70b-steerlm-chat Nvidia · Llama 2 Community	1025±29	467
279	268287	mistral-7b-instruct Mistral · Apache 2.0	1019±20	1,032
280	268287	olmo-7b-instruct Allen AI · Apache-2.0	1016±22	772
281	268288	vicuna-7b LMSYS · Llama 2 Community	1010±23	726
282	268288	gemma-2b-it Google · Gemma license	1010±22	741
283	275288	llama-2-7b-chat Meta · Llama 2 Community	1002±14	1,956
284	273288	stripedhyena-nous-7b Together AI · Apache 2.0	1001±23	704
285	274288	qwen1.5-4b-chat Alibaba · Qianwen LICENSE	999±17	1,282
286	268289	guanaco-33b UW · Non-commercial	996±36	263
287	275288	palm-2 Google · Proprietary	995±21	917
288	281293	chatglm3-6b Tsinghua · Apache-2.0	965±27	535
289	287294	koala-13b UC Berkeley · Non-commercial	945±25	747
290	288295	RWKV-4-Raven-14B RWKV · Apache 2.0	928±28	505
291	288295	chatglm-6b Tsinghua · Non-commercial	920±27	551
292	288295	mpt-7b-chat MosaicML · CC-BY-NC-SA-4.0	914±32	397
293	288295	chatglm2-6b Tsinghua · Apache-2.0	902±36	293
294	289295	oasst-pythia-12b OpenAssistant · Apache 2.0	901±26	714
295	290295	stablelm-tuned-alpha-7b Stability AI · CC-BY-NC-SA-4.0	886±34	363
296	296298	alpaca-13b Stanford · Non-commercial	799±28	626
297	296298	dolly-v2-12b Databricks · MIT	777±34	396
298	296298	fastchat-t5-3b LMSYS · Apache 2.0	764±31	428
299	299299	llama-13b Meta · Non-commercial	683±41	304

Text Arena

Remove Style Control Leaderboard Plots

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)

Battle Count for Each Combination of Models (without Ties)