Text Arena

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

Feb 10, 2026

916,962 votes

300 models

/

Style Control

	Rank Spread
1	12	claude-opus-4-6-thinking Anthropic · Proprietary	1568±21	805
2	18	claude-opus-4-6 Anthropic · Proprietary	1538±19	1,039
3	24	claude-opus-4-5-20251101-thinking-32k Anthropic · Proprietary	1537±9	5,410
4	218	kimi-k2.5-instant Moonshot · Modified MIT	1524±20	865
5	313	claude-sonnet-4-5-20250929-thinking-32k Anthropic · Proprietary	1519±7	9,796
6	313	gemini-3-pro Google · Proprietary	1518±8	7,405
7	313	claude-opus-4-5-20251101 Anthropic · Proprietary	1518±8	6,730
8	416	claude-opus-4-1-20250805-thinking-16k Anthropic · Proprietary	1512±7	9,882
9	321	kimi-k2.5-thinking Moonshot · Modified MIT	1511±14	1,765
10	418	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1509±7	9,158
11	420	grok-4.1-thinking xAI · Proprietary	1506±8	7,124
12	421	gemini-3-flash Google · Proprietary	1506±9	5,446
13	421	gemini-3-flash (thinking-minimal) Google · Proprietary	1505±10	3,630
14	721	claude-opus-4-1-20250805 Anthropic · Proprietary	1503±6	15,030
15	824	claude-opus-4-20250514-thinking-16k Anthropic · Proprietary	1497±8	6,751
16	824	grok-4.1 xAI · Proprietary	1496±8	7,929
17	729	gpt-5.2 OpenAI · Proprietary	1494±12	2,649
18	730	ernie-5.0-0110 Baidu · Proprietary	1493±12	2,286
19	1026	gpt-5.1-high OpenAI · Proprietary	1493±8	6,238
20	1030	gpt-5.2-high OpenAI · Proprietary	1491±11	3,293
21	1141	glm-4.7 Z.ai · MIT	1486±12	2,434
22	1537	kimi-k2-thinking-turbo Moonshot · Modified MIT	1484±8	6,986
23	1541	qwen3-max-preview Alibaba · Proprietary	1482±8	5,356
24	1846	claude-haiku-4-5-20251001 Anthropic · Proprietary	1477±7	9,485
25	1550	qwen3-max-2025-09-23 Alibaba · Proprietary	1477±13	2,040
26	1755	longcat-flash-chat Meituan · MIT	1475±13	2,260
27	1950	gpt-5.1 OpenAI · Proprietary	1474±8	6,997
28	1758	deepseek-v3.2-exp-thinking DeepSeek · MIT	1473±13	1,907
29	1860	ernie-5.0-preview-1203 Baidu · Proprietary	1471±13	1,989
30	2150	qwen3-235b-a22b-instruct-2507 Alibaba · Apache 2.0	1471±6	13,774
31	2153	claude-sonnet-4-20250514-thinking-32k Anthropic · Proprietary	1471±8	6,515
32	2158	deepseek-v3.2-thinking DeepSeek · MIT	1469±9	4,201
33	2251	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1469±5	15,760
34	2157	deepseek-v3.2 DeepSeek · MIT	1469±9	5,572
35	2157	mistral-large-3 Mistral · Apache 2.0	1469±9	4,987
36	2165	kimi-k2-0905-preview Moonshot · Modified MIT	1468±13	2,261
37	2258	gpt-5-high OpenAI · Proprietary	1468±8	6,454
38	2457	gemini-2.5-pro Google · Proprietary	1467±5	18,415
39	2166	deepseek-v3.2-exp DeepSeek · MIT	1467±12	2,506
40	2268	deepseek-r1-0528 DeepSeek · MIT	1464±11	2,794
41	2271	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1464±13	2,370
42	2466	gpt-5-chat OpenAI · Proprietary	1463±8	6,000
43	2565	claude-opus-4-20250514 Anthropic · Proprietary	1463±7	8,018
44	2568	glm-4.6 Z.ai · MIT	1460±7	7,517
45	1884	deepseek-v3.1-terminus-thinking DeepSeek · MIT	1460±23	648
46	2571	kimi-k2-0711-preview Moonshot · Modified MIT	1459±8	5,354
47	2474	gpt-4.5-preview-2025-02-27 OpenAI · Proprietary	1458±13	1,939
48	2474	deepseek-v3.1-thinking DeepSeek · MIT	1458±13	1,905
49	2970	o3-2025-04-16 OpenAI · Proprietary	1457±6	11,937
50	2479	grok-4-fast-chat xAI · Proprietary	1457±16	1,255
51	2578	qwen3-vl-235b-a22b-thinking Alibaba · Apache 2.0	1456±14	1,633
52	2873	grok-4-1-fast-reasoning xAI · Proprietary	1456±8	5,876
53	3171	gpt-4.1-2025-04-14 OpenAI · Proprietary	1455±7	9,435
54	2973	glm-4.5 Z.ai · MIT	1455±9	4,809
55	3074	qwen3-coder-480b-a35b-instruct Alibaba · Apache 2.0	1454±9	4,984
56	3372	mistral-medium-2508 Mistral · Proprietary	1454±6	12,941
57	3774	claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary	1451±8	6,290
58	4079	claude-sonnet-4-20250514 Anthropic · Proprietary	1448±7	7,516
59	3884	mimo-v2-flash (non-thinking) Xiaomi · MIT	1447±10	3,513
60	3886	deepseek-v3.1 DeepSeek · MIT	1446±12	2,650
61	4284	qwen3-next-80b-a3b-instruct Alibaba · Apache 2.0	1446±9	4,809
62	4484	qwen3-235b-a22b-no-thinking Alibaba · Apache 2.0	1445±8	7,127
63	3890	deepseek-r1 DeepSeek · MIT	1444±12	2,318
64	4485	grok-3-preview-02-24 xAI · Proprietary	1444±8	5,498
65	3896	qwen3-235b-a22b-thinking-2507 Alibaba · Apache 2.0	1441±15	1,628
66	31106	amazon-nova-experimental-chat-12-10 Amazon · Proprietary	1441±21	715
67	3899	step-3.5-flash StepFun · Apache 2.0	1440±17	1,237
68	4593	minimax-m2.1-preview MiniMax · MIT	1440±11	3,222
69	4891	qwen3-30b-a3b-instruct-2507 Alibaba · Apache 2.0	1440±9	4,694
70	4995	grok-4-fast-reasoning xAI · Proprietary	1438±9	3,961
71	37106	deepseek-v3.1-terminus DeepSeek · MIT	1438±21	793
72	30108	hunyuan-vision-1.5-thinking Tencent · Proprietary	1436±27	439
73	42106	ernie-5.0-preview-1022 Baidu · Proprietary	1436±19	909
74	5595	grok-4-0709 xAI · Proprietary	1435±7	8,259
75	51102	o3-mini-high OpenAI · Proprietary	1434±11	2,595
76	5896	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1433±5	15,077
77	5599	qwen3-235b-a22b Alibaba · Apache 2.0	1433±9	4,418
78	5897	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1433±7	7,064
79	55102	o1-2024-12-17 OpenAI · Proprietary	1432±9	3,974
80	5899	o4-mini-2025-04-16 OpenAI · Proprietary	1431±7	8,830
81	58102	mistral-medium-2505 Mistral · Proprietary	1431±8	6,006
82	56106	mai-1-preview Microsoft AI · Proprietary	1430±11	2,804
83	58105	gpt-5-mini-high OpenAI · Proprietary	1429±9	5,518
84	62103	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1428±7	7,270
85	63106	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1427±8	6,877
86	64105	deepseek-v3-0324 DeepSeek · MIT	1427±7	8,488
87	64106	glm-4.5-air Z.ai · MIT	1426±8	6,139
88	67106	gemini-2.5-flash Google · Proprietary	1424±5	17,735
89	64107	amazon-nova-experimental-chat-11-10 Amazon · Proprietary	1422±10	3,413
90	64108	qwen3-next-80b-a3b-thinking Alibaba · Apache 2.0	1421±11	2,706
91	72108	minimax-m1 MiniMax · Apache 2.0	1417±8	6,634
92	55131	glm-4.6v Z.ai · MIT	1417±25	539
93	66113	glm-4.7-flash Z.ai · MIT	1416±14	1,687
94	71109	o1-preview OpenAI · Proprietary	1416±9	5,123
95	78108	o3-mini OpenAI · Proprietary	1415±6	9,595
96	69119	ling-flash-2.0 Ant Group · MIT	1413±15	1,532
97	79114	mistral-small-2506 Mistral · Apache 2.0	1411±10	3,415
98	75118	amazon-nova-experimental-chat-10-20 Amazon · Proprietary	1411±12	2,316
99	67131	intellect-3 Prime Intellect · MIT	1410±19	978
100	65136	qwen3-32b Alibaba · Apache 2.0	1407±24	513
101	75134	step-3 StepFun · Apache 2.0	1407±17	1,246
102	75135	glm-4.5v Z.ai · MIT	1405±18	996
103	89125	qwen2.5-max Alibaba · Proprietary	1403±8	5,183
104	72138	nvidia-llama-3.3-nemotron-super-49b-v1.5 Nvidia · Nvidia Open	1402±22	670
105	81138	hunyuan-t1-20250711 Tencent · Proprietary	1400±20	808
106	66151	hunyuan-turbos-20250226 Tencent · Proprietary	1399±31	275
107	94131	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1398±7	9,797
108	94134	claude-3-5-sonnet-20240620 Anthropic · Proprietary	1397±7	13,609
109	93137	hunyuan-turbos-20250416 Tencent · Proprietary	1395±14	1,803
110	94136	nova-2-lite Amazon · Proprietary	1395±12	2,554
111	79158	llama-3.1-nemotron-ultra-253b-v1 Nvidia · Nvidia Open Model	1391±30	367
112	94143	ring-flash-2.0 Ant Group · MIT	1390±15	1,549
113	98136	gpt-oss-120b OpenAI · Apache 2.0	1390±8	6,516
114	88153	amazon-nova-experimental-chat-10-09 Amazon · Proprietary	1389±24	555
115	98136	command-a-03-2025 Cohere · CC-BY-NC-4.0	1389±6	10,343
116	96139	grok-3-mini-high xAI · Proprietary	1389±10	3,358
117	98139	qwen3-30b-a3b Alibaba · Apache 2.0	1388±9	4,624
118	99138	o1-mini OpenAI · Proprietary	1387±7	8,482
119	98142	deepseek-v3 DeepSeek · DeepSeek	1387±10	3,281
120	96145	magistral-medium-2506 Mistral · Proprietary	1387±12	2,299
121	96145	olmo-3.1-32b-instruct Allen AI · Apache 2.0	1386±12	2,389
122	99142	grok-3-mini-beta xAI · Proprietary	1386±9	4,356
123	99143	qwq-32b Alibaba · Apache 2.0	1385±9	4,108
124	99143	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1384±8	6,107
125	96151	minimax-m2 MiniMax · Apache 2.0	1384±15	1,532
126	104141	claude-3-5-haiku-20241022 Anthropic · Proprietary	1383±6	11,364
127	98152	gpt-5-nano-high OpenAI · Proprietary	1382±15	1,696
128	98157	qwen-plus-0125 Alibaba · Proprietary	1379±18	893
129	102163	deepseek-v2.5-1210 DeepSeek · DeepSeek	1374±17	1,079
130	109152	llama-3.1-405b-instruct-bf16 Meta · Llama 3.1 Community	1374±7	6,251
131	99165	gpt-4.1-nano-2025-04-14 OpenAI · Proprietary	1373±19	807
132	113154	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1372±7	7,132
133	95178	hunyuan-turbo-0110 Tencent · Proprietary	1372±30	299
134	102171	step-2-16k-exp-202412 StepFun · Proprietary	1371±20	738
135	97178	mercury Inception AI · Proprietary	1370±29	398
136	115161	athene-v2-chat NexusFlow · NexusFlow	1369±9	4,019
137	115161	yi-lightning 01 AI · Proprietary	1368±10	4,316
138	121157	gpt-4o-2024-05-13 OpenAI · Proprietary	1368±6	19,526
139	116161	deepseek-v2.5 DeepSeek · DeepSeek	1368±9	4,252
140	110165	gpt-oss-20b OpenAI · Apache 2.0	1368±13	2,179
141	123161	llama-3.1-405b-instruct-fp8 Meta · Llama 3.1 Community	1366±7	9,714
142	101178	hunyuan-large-2025-02-10 Tencent · Proprietary	1366±25	519
143	105173	olmo-3-32b-think Allen AI · Apache 2.0	1366±19	1,056
144	121167	nvidia-nemotron-3-nano-30b-a3b-bf16 Nvidia · NVIDIA Open Model	1364±11	3,287
145	123163	gemini-2.0-flash-001 Google · Proprietary	1364±7	7,126
146	99184	llama-3.3-nemotron-49b-super-v1 Nvidia · Nvidia	1361±32	285
147	123167	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1361±8	6,237
148	123169	llama-4-scout-17b-16e-instruct Meta · Llama	1361±8	5,346
149	125170	gpt-4o-2024-08-06 OpenAI · Proprietary	1360±8	7,319
150	127170	gemma-3-27b-it Google · Gemma	1359±7	8,206
151	128171	grok-2-2024-08-13 xAI · Proprietary	1358±7	10,367
152	118179	hunyuan-large-vision Tencent · Proprietary	1358±19	993
153	123177	qwen2.5-plus-1127 Alibaba · Proprietary	1357±14	1,554
154	129172	gemini-1.5-pro-002 Google · Proprietary	1356±7	9,174
155	129173	qwen2.5-72b-instruct Alibaba · Qwen	1355±8	6,687
156	123180	step-1o-turbo-202506 StepFun · Proprietary	1354±15	1,566
157	132176	mistral-large-2407 Mistral · Mistral Research	1352±8	7,590
158	136173	claude-3-opus-20240229 Anthropic · Proprietary	1352±6	33,751
159	129178	qwen-max-0919 Alibaba · Qwen	1352±11	2,756
160	131177	glm-4-plus Zhipu AI · Proprietary	1351±9	4,450
161	132180	athene-70b-0725 NexusFlow · CC-BY-NC-4.0	1350±11	3,122
162	138177	gpt-4o-mini-2024-07-18 OpenAI · Proprietary	1349±6	10,944
163	140180	gemini-1.5-pro-001 Google · Proprietary	1346±7	12,749
164	142180	gpt-4-turbo-2024-04-09 OpenAI · Proprietary	1346±7	17,110
165	145180	llama-3.3-70b-instruct Meta · Llama-3.3	1345±6	8,845
166	140181	mistral-large-2411 Mistral · MRL	1345±9	4,214
167	143182	gemini-2.0-flash-lite-preview-02-05 Google · Proprietary	1343±10	3,475
168	136185	olmo-3.1-32b-think Allen AI · Apache 2.0	1342±15	1,604
169	147182	amazon-nova-pro-v1.0 Amazon · Proprietary	1342±9	3,854
170	132190	qwen2.5-coder-32b-instruct Alibaba · Apache 2.0	1341±19	873
171	142185	deepseek-coder-v2 DeepSeek · DeepSeek License	1341±12	2,671
172	151183	gpt-4-1106-preview OpenAI · Proprietary	1338±7	15,608
173	151185	gemini-advanced-0514 Google · Proprietary	1337±9	8,138
174	155185	grok-2-mini-2024-08-13 xAI · Proprietary	1335±7	8,653
175	160186	llama-3.1-70b-instruct Meta · Llama 3.1 Community	1332±7	9,390
176	138200	hunyuan-standard-2025-02-10 Tencent · Proprietary	1331±24	549
177	148197	glm-4-plus-0111 Zhipu · Proprietary	1330±18	894
178	165190	gpt-4-0125-preview OpenAI · Proprietary	1330±8	15,292
179	152197	llama-3.1-nemotron-70b-instruct Nvidia · Llama 3.1	1328±15	1,312
180	151199	ibm-granite-h-small IBM · Apache 2.0	1328±17	1,272
181	166194	gpt-4-0314 OpenAI · Proprietary	1326±9	8,308
182	159208	gemma-3-12b-it Google · Gemma	1317±23	543
183	175200	claude-3-sonnet-20240229 Anthropic · Proprietary	1316±7	18,888
184	175200	gemini-1.5-flash-002 Google · Proprietary	1315±8	5,893
185	170206	reka-core-20240904 Reka AI · Proprietary	1314±15	1,216
186	175206	mistral-small-24b-instruct-2501 Mistral · Apache 2.0	1311±12	2,083
187	177204	gpt-4-0613 OpenAI · Proprietary	1311±8	13,720
188	174208	jamba-1.5-large AI21 Labs · Jamba Open	1311±15	1,440
189	177206	gemma-3n-e4b-it Google · Gemma	1310±10	3,607
190	168211	llama-3.1-nemotron-51b-instruct Nvidia · Llama 3.1	1310±22	665
191	178204	gemini-1.5-flash-001 Google · Proprietary	1309±8	10,680
192	177208	glm-4-0520 Zhipu AI · Proprietary	1307±14	1,718
193	169215	llama-3.1-tulu-3-70b Ai2 · Llama 3.1	1306±24	450
194	177208	nemotron-4-340b-instruct Nvidia · NVIDIA Open Model	1306±11	3,254
195	178208	phi-4 Microsoft · MIT	1306±10	3,304
196	178208	amazon-nova-lite-v1.0 Amazon · Proprietary	1305±10	3,060
197	181206	gemma-2-27b-it Google · Gemma license	1304±6	12,090
198	180208	llama-3-70b-instruct Meta · Llama 3 Community	1304±7	28,131
199	175222	hunyuan-standard-256k Tencent · Proprietary	1300±25	497
200	184210	claude-3-haiku-20240307 Anthropic · Proprietary	1299±7	20,901
201	184214	qwen2-72b-instruct Alibaba · Qianwen LICENSE	1295±9	6,249
202	186214	mistral-large-2402 Mistral · Proprietary	1293±8	10,419
203	186215	c4ai-aya-expanse-32b Cohere · CC-BY-NC-4.0	1291±9	4,686
204	184224	reka-flash-20240904 Reka AI · Proprietary	1289±15	1,207
205	190222	amazon-nova-micro-v1.0 Amazon · Proprietary	1287±10	2,980
206	180232	granite-3.1-8b-instruct IBM · Apache 2.0	1286±26	478
207	197230	command-r-08-2024 Cohere · CC-BY-NC-4.0	1279±13	1,783
208	184236	olmo-2-0325-32b-instruct Allen AI · Apache-2.0	1279±27	427
209	197230	command-r-plus-08-2024 Cohere · CC-BY-NC-4.0	1278±14	1,675
210	199229	qwen1.5-110b-chat Alibaba · Qianwen LICENSE	1278±10	4,763
211	199231	reka-flash-21b-20240226-online Reka AI · Proprietary	1275±13	2,879
212	201230	mixtral-8x22b-instruct-v0.1 Mistral · Apache 2.0	1274±9	8,781
213	190237	gemma-3-4b-it Google · Gemma	1274±24	606
214	197236	ministral-8b-2410 Mistral · MRL	1273±19	838
215	203231	qwen1.5-72b-chat Alibaba · Qianwen LICENSE	1272±10	6,366
216	203230	gpt-3.5-turbo-0125 OpenAI · Proprietary	1272±8	11,127
217	203230	gemini-1.5-flash-8b-001 Google · Proprietary	1272±8	6,067
218	199235	gemma-2-9b-it-simpo Princeton · MIT	1271±15	1,471
219	203231	gemma-2-9b-it Google · Gemma license	1270±7	8,923
220	203231	command-r-plus Cohere · CC-BY-NC-4.0	1270±8	13,944
221	203239	jamba-1.5-mini AI21 Labs · Jamba Open	1264±15	1,352
222	205236	reka-flash-21b-20240226 Reka AI · Proprietary	1264±11	4,750
223	206239	mistral-medium Mistral · Proprietary	1259±10	5,149
224	206239	qwen1.5-32b-chat Alibaba · Qianwen LICENSE	1259±11	3,931
225	205241	gpt-3.5-turbo-1106 OpenAI · Proprietary	1259±16	2,122
226	207237	llama-3.1-8b-instruct Meta · Llama 3.1 Community	1259±7	8,584
227	206242	c4ai-aya-expanse-8b Cohere · CC-BY-NC-4.0	1254±14	1,567
228	203247	llama-3.1-tulu-3-8b Ai2 · Llama 3.1	1252±25	476
229	217241	llama-3-8b-instruct Meta · Llama 3 Community	1251±8	18,377
230	217244	dbrx-instruct-preview Databricks · DBRX LICENSE	1248±11	5,501
231	206249	granite-3.1-2b-instruct IBM · Apache 2.0	1246±25	508
232	216246	internlm2_5-20b-chat InternLM · Other	1246±14	1,684
233	206249	gemini-pro Google · Proprietary	1246±24	678
234	217244	yi-1.5-34b-chat 01 AI · Apache-2.0	1246±10	3,842
235	212249	zephyr-orpo-141b-A35b-v0.1 HuggingFace · Apache 2.0	1242±21	832
236	223246	command-r Cohere · CC-BY-NC-4.0	1240±9	9,648
237	218250	granite-3.0-8b-instruct IBM · Apache 2.0	1237±18	1,109
238	221249	gemini-pro-dev-api Google · Proprietary	1237±14	2,681
239	223249	qwen1.5-14b-chat Alibaba · Qianwen LICENSE	1237±13	3,208
240	226246	mixtral-8x7b-instruct-v0.1 Mistral · Apache 2.0	1236±8	11,789
241	226250	starling-lm-7b-beta Nexusflow · Apache-2.0	1233±13	2,948
242	229251	phi-3-medium-4k-instruct Microsoft · MIT	1228±10	3,973
243	228254	openchat-3.5-0106 OpenChat · Apache-2.0	1227±14	2,003
244	231254	snowflake-arctic-instruct Snowflake · Apache 2.0	1221±11	5,737
245	235258	gemma-1.1-7b-it Google · Gemma license	1216±10	4,332
246	229267	deepseek-llm-67b-chat DeepSeek · DeepSeek License	1215±24	649
247	231267	tulu-2-dpo-70b AllenAI/UW · AI2 ImpACT Low-risk	1212±21	805
248	234268	qwen1.5-7b-chat Alibaba · Qianwen LICENSE	1207±21	771
249	235268	granite-3.0-2b-instruct IBM · Apache 2.0	1207±18	1,134
250	240268	starling-lm-7b-alpha UC Berkeley · CC-BY-NC-4.0	1205±16	1,397
251	243268	yi-34b-chat 01 AI · Yi License	1203±13	2,346
252	243267	phi-3-small-8k-instruct Microsoft · MIT	1202±12	3,218
253	242271	openchat-3.5 OpenChat · Apache-2.0	1199±20	971
254	243276	qwen-14b-chat Alibaba · Qianwen LICENSE	1194±24	599
255	245271	phi-3-mini-4k-instruct-june-2024 Microsoft · MIT	1194±14	1,841
256	246269	gemma-2-2b-it Google · Gemma license	1193±8	7,299
257	246271	vicuna-33b LMSYS · Non-commercial	1191±13	2,866
258	245276	wizardlm-70b Microsoft · Llama 2 Community	1190±20	988
259	246273	phi-3-mini-4k-instruct Microsoft · MIT	1185±12	3,450
260	245281	openhermes-2.5-mistral-7b NousResearch · Apache-2.0	1184±23	589
261	246274	mistral-7b-instruct-v0.2 Mistral · Apache-2.0	1183±12	3,113
262	245282	solar-10.7b-instruct-v1.0 Upstage AI · CC-BY-NC-4.0	1181±27	482
263	253278	llama-2-70b-chat Meta · Llama 2 Community	1176±10	5,715
264	249281	llama-3.2-3b-instruct Meta · Llama 3.2	1174±16	1,351
265	246283	nous-hermes-2-mixtral-8x7b-dpo NousResearch · Apache-2.0	1173±24	575
266	246283	qwq-32b-preview Alibaba · Apache 2.0	1173±24	567
267	254282	gemma-1.1-2b-it Google · Gemma license	1170±14	1,963
268	254283	gemma-7b-it Google · Gemma license	1166±17	1,381
269	246286	mpt-30b-chat MosaicML · CC-BY-NC-SA-4.0	1165±35	258
270	246287	zephyr-7b-alpha HuggingFace · MIT	1164±40	201
271	257285	vicuna-13b LMSYS · Llama 2 Community	1160±14	2,389
272	258284	llama-2-13b-chat Meta · Llama 2 Community	1160±13	2,624
273	246287	smollm2-1.7b-instruct HuggingFace · Apache 2.0	1159±33	352
274	257286	codellama-34b-instruct Meta · Llama 2 Community	1156±20	853
275	262286	phi-3-mini-128k-instruct Microsoft · MIT	1152±13	3,889
276	259286	palm-2 Google · Proprietary	1150±21	917
277	261286	zephyr-7b-beta HuggingFace · MIT	1150±18	1,249
278	259286	wizardlm-13b Microsoft · Llama 2 Community	1149±22	735
279	262286	llama-3.2-1b-instruct Meta · Llama 3.2	1147±16	1,346
280	261287	llama2-70b-steerlm-chat Nvidia · Llama 2 Community	1142±28	467
281	262287	mistral-7b-instruct Mistral · Apache 2.0	1141±20	1,032
282	264289	gemma-2b-it Google · Gemma license	1135±22	741
283	266289	vicuna-7b LMSYS · Llama 2 Community	1129±23	726
284	271289	qwen1.5-4b-chat Alibaba · Qianwen LICENSE	1128±17	1,282
285	270289	stripedhyena-nous-7b Together AI · Apache 2.0	1124±22	704
286	269292	guanaco-33b UW · Non-commercial	1111±36	263
287	278292	olmo-7b-instruct Allen AI · Apache-2.0	1104±22	772
288	282291	llama-2-7b-chat Meta · Llama 2 Community	1100±14	1,956
289	282294	chatglm3-6b Tsinghua · Apache-2.0	1087±26	535
290	286296	mpt-7b-chat MosaicML · CC-BY-NC-SA-4.0	1063±32	397
291	286295	koala-13b UC Berkeley · Non-commercial	1063±24	747
292	287296	RWKV-4-Raven-14B RWKV · Apache 2.0	1056±27	505
293	289297	oasst-pythia-12b OpenAssistant · Apache 2.0	1047±25	714
294	290297	chatglm-6b Tsinghua · Non-commercial	1032±27	551
295	289298	chatglm2-6b Tsinghua · Apache-2.0	1028±35	293
296	291298	stablelm-tuned-alpha-7b Stability AI · CC-BY-NC-SA-4.0	1002±33	363
297	293298	alpaca-13b Stanford · Non-commercial	996±27	626
298	295299	dolly-v2-12b Databricks · MIT	959±34	396
299	298300	fastchat-t5-3b LMSYS · Apache 2.0	905±31	428
300	299300	llama-13b Meta · Non-commercial	880±40	304

Text Arena

Default Leaderboard Plots

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)

Battle Count for Each Combination of Models (without Ties)