Text Arena

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

Feb 10, 2026

758,776 votes

303 models

/

Style Control

	Rank Spread
1	13	gemini-3-pro Google · Proprietary	1489±9	5,024
2	16	claude-opus-4-6-thinking Anthropic · Proprietary	1483±26	523
3	114	claude-opus-4-6 Anthropic · Proprietary	1468±24	608
4	210	claude-opus-4-5-20251101-thinking-32k Anthropic · Proprietary	1460±10	3,848
5	212	claude-opus-4-5-20251101 Anthropic · Proprietary	1456±10	4,531
6	213	gemini-3-flash Google · Proprietary	1455±11	3,838
7	314	gemini-2.5-pro Google · Proprietary	1450±6	12,712
8	315	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1448±8	5,940
9	318	claude-opus-4-1-20250805-thinking-16k Anthropic · Proprietary	1445±8	6,650
10	322	gemini-3-flash (thinking-minimal) Google · Proprietary	1442±13	2,401
11	421	claude-sonnet-4-5-20250929-thinking-32k Anthropic · Proprietary	1441±8	6,158
12	522	claude-opus-4-1-20250805 Anthropic · Proprietary	1439±7	9,954
13	424	gpt-4.5-preview-2025-02-27 OpenAI · Proprietary	1438±12	2,618
14	624	grok-4.1-thinking xAI · Proprietary	1435±9	4,907
15	825	gpt-5.1-high OpenAI · Proprietary	1434±10	4,370
16	927	claude-opus-4-20250514-thinking-16k Anthropic · Proprietary	1428±9	4,754
17	927	grok-4.1 xAI · Proprietary	1428±9	5,217
18	1330	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1422±6	11,289
19	1043	ernie-5.0-preview-1203 Baidu · Proprietary	1420±16	1,475
20	1335	claude-opus-4-20250514 Anthropic · Proprietary	1419±8	5,791
21	1146	ernie-5.0-0110 Baidu · Proprietary	1418±14	1,763
22	1052	kimi-k2.5-thinking Moonshot · Modified MIT	1416±17	1,198
23	1648	gpt-5.1 OpenAI · Proprietary	1411±10	4,675
24	967	deepseek-v3.1-terminus DeepSeek · MIT	1411±27	458
25	1064	ernie-5.0-preview-1022 Baidu · Proprietary	1411±23	662
26	1553	deepseek-v3.1-thinking DeepSeek · MIT	1410±14	1,720
27	1853	grok-4-1-fast-reasoning xAI · Proprietary	1407±10	3,961
28	1860	glm-4.7 Z.ai · MIT	1404±14	1,799
29	1864	deepseek-v3.2-exp DeepSeek · MIT	1403±15	1,500
30	2053	gpt-4.1-2025-04-14 OpenAI · Proprietary	1402±8	6,856
31	1955	glm-4.6 Z.ai · MIT	1402±9	4,765
32	1955	grok-3-preview-02-24 xAI · Proprietary	1402±9	4,971
33	2062	deepseek-v3.2 DeepSeek · MIT	1400±11	3,661
34	1966	gpt-5.2 OpenAI · Proprietary	1400±14	1,839
35	1677	kimi-k2.5-instant Moonshot · Modified MIT	1399±24	601
36	2155	gemini-2.5-flash Google · Proprietary	1398±6	12,446
37	2064	grok-4-0709 xAI · Proprietary	1397±8	5,555
38	2066	qwen3-max-preview Alibaba · Proprietary	1396±10	3,713
39	2166	claude-sonnet-4-20250514-thinking-32k Anthropic · Proprietary	1395±9	4,583
40	2071	deepseek-v3.1 DeepSeek · MIT	1395±13	2,085
41	1975	deepseek-v3.2-exp-thinking DeepSeek · MIT	1395±18	1,154
42	2266	claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary	1395±8	5,472
43	1974	qwen3-max-2025-09-23 Alibaba · Proprietary	1395±17	1,157
44	2267	gpt-5-chat OpenAI · Proprietary	1394±10	4,010
45	2072	gpt-5.2-high OpenAI · Proprietary	1393±13	2,276
46	2369	kimi-k2-thinking-turbo Moonshot · Modified MIT	1392±9	4,665
47	2468	deepseek-v3-0324 DeepSeek · MIT	1391±8	6,338
48	2374	deepseek-v3.2-thinking DeepSeek · MIT	1389±11	3,251
49	2376	deepseek-r1-0528 DeepSeek · MIT	1389±12	2,660
50	2776	claude-sonnet-4-20250514 Anthropic · Proprietary	1385±9	5,327
51	3074	qwen3-235b-a22b-instruct-2507 Alibaba · Apache 2.0	1384±7	9,254
52	3076	o3-2025-04-16 OpenAI · Proprietary	1384±7	8,013
53	3077	o1-2024-12-17 OpenAI · Proprietary	1383±9	4,646
54	2090	hunyuan-t1-20250711 Tencent · Proprietary	1382±23	642
55	2385	grok-4-fast-chat xAI · Proprietary	1382±19	995
56	3079	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1382±9	4,287
57	3277	mistral-medium-2508 Mistral · Proprietary	1382±7	8,683
58	3179	claude-haiku-4-5-20251001 Anthropic · Proprietary	1381±8	5,910
59	2096	deepseek-v3.1-terminus-thinking DeepSeek · MIT	1381±27	446
60	3083	grok-4-fast-reasoning xAI · Proprietary	1380±12	2,371
61	3281	gpt-5-high OpenAI · Proprietary	1379±10	4,329
62	2785	kimi-k2-0905-preview Moonshot · Modified MIT	1379±15	1,495
63	3981	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1377±8	6,259
64	3583	deepseek-r1 DeepSeek · MIT	1377±10	3,295
65	3583	glm-4.5 Z.ai · MIT	1376±11	3,224
66	4186	mistral-large-3 Mistral · Apache 2.0	1373±11	3,448
67	4385	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1373±9	4,431
68	3196	qwen3-235b-a22b-thinking-2507 Alibaba · Apache 2.0	1372±18	1,151
69	4586	qwen3-235b-a22b-no-thinking Alibaba · Apache 2.0	1372±9	4,897
70	4883	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1371±6	11,986
71	4589	kimi-k2-0711-preview Moonshot · Modified MIT	1370±10	3,713
72	21115	hunyuan-vision-1.5-thinking Tencent · Proprietary	1369±36	258
73	4396	hunyuan-turbos-20250416 Tencent · Proprietary	1367±15	1,578
74	4992	o1-preview OpenAI · Proprietary	1367±10	4,506
75	4497	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1365±17	1,373
76	5596	mistral-medium-2505 Mistral · Proprietary	1364±9	4,429
77	5596	qwen3-coder-480b-a35b-instruct Alibaba · Apache 2.0	1364±10	3,480
78	5296	mimo-v2-flash (non-thinking) Xiaomi · MIT	1364±12	2,494
79	5796	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1362±8	6,262
80	5996	gemini-1.5-pro-002 Google · Proprietary	1361±7	8,065
81	5798	mai-1-preview Microsoft AI · Proprietary	1359±13	2,244
82	6697	qwen2.5-max Alibaba · Proprietary	1355±8	5,132
83	42128	glm-4.6v Z.ai · MIT	1354±29	393
84	68102	deepseek-v3 DeepSeek · DeepSeek	1351±10	3,624
85	71102	gemma-3-27b-it Google · Gemma	1350±8	6,591
86	71102	gemini-2.0-flash-001 Google · Proprietary	1349±8	6,494
87	70102	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1349±9	5,436
88	68111	minimax-m2.1-preview MiniMax · MIT	1349±12	2,439
89	59128	step-3.5-flash StepFun · Apache 2.0	1347±21	776
90	71109	gemini-2.0-flash-lite-preview-02-05 Google · Proprietary	1347±9	4,100
91	63124	qwen3-vl-235b-a22b-thinking Alibaba · Apache 2.0	1346±18	1,007
92	71112	gemini-advanced-0514 Google · Proprietary	1345±10	7,026
93	79113	o4-mini-2025-04-16 OpenAI · Proprietary	1341±8	6,078
94	63131	amazon-nova-experimental-chat-12-10 Amazon · Proprietary	1341±24	582
95	82115	gpt-4o-2024-05-13 OpenAI · Proprietary	1339±7	16,599
96	69131	step-2-16k-exp-202412 StepFun · Proprietary	1339±21	748
97	82122	command-a-03-2025 Cohere · CC-BY-NC-4.0	1336±7	7,865
98	81128	grok-3-mini-beta xAI · Proprietary	1336±11	2,997
99	70136	gemma-3-12b-it Google · Gemma	1335±23	600
100	68144	llama-3.1-nemotron-ultra-253b-v1 Nvidia · Nvidia Open Model	1334±27	444
101	82130	grok-3-mini-high xAI · Proprietary	1333±13	2,203
102	82133	longcat-flash-chat Meituan · MIT	1330±16	1,383
103	86130	glm-4.5-air Z.ai · MIT	1330±10	4,039
104	87130	gpt-4o-2024-08-06 OpenAI · Proprietary	1328±8	6,756
105	86130	qwen3-235b-a22b Alibaba · Apache 2.0	1328±10	3,785
106	86131	gpt-5-mini-high OpenAI · Proprietary	1328±10	3,511
107	86137	qwen3-next-80b-a3b-thinking Alibaba · Apache 2.0	1325±14	1,798
108	88133	qwen3-30b-a3b-instruct-2507 Alibaba · Apache 2.0	1325±11	3,062
109	90131	gemini-1.5-pro-001 Google · Proprietary	1325±8	11,800
110	92131	gpt-4-turbo-2024-04-09 OpenAI · Proprietary	1324±8	14,398
111	89139	mistral-small-2506 Mistral · Apache 2.0	1323±12	2,361
112	92133	minimax-m1 MiniMax · Apache 2.0	1323±9	4,880
113	86150	glm-4-plus-0111 Zhipu · Proprietary	1320±19	920
114	94135	grok-2-2024-08-13 xAI · Proprietary	1319±7	9,339
115	87149	qwen-plus-0125 Alibaba · Proprietary	1319±18	933
116	92144	qwen3-next-80b-a3b-instruct Alibaba · Apache 2.0	1318±11	2,934
117	86163	glm-4.5v Z.ai · MIT	1317±23	631
118	97148	o3-mini-high OpenAI · Proprietary	1314±11	3,067
119	93161	deepseek-v2.5-1210 DeepSeek · DeepSeek	1312±17	1,088
120	90167	intellect-3 Prime Intellect · MIT	1311±22	762
121	101149	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1310±8	5,437
122	86174	nvidia-llama-3.3-nemotron-super-49b-v1.5 Nvidia · Nvidia Open	1310±28	407
123	94167	gpt-4.1-nano-2025-04-14 OpenAI · Proprietary	1308±18	1,008
124	92172	qwen3-32b Alibaba · Apache 2.0	1308±22	622
125	94172	step-3 StepFun · Apache 2.0	1307±21	796
126	109156	llama-3.1-405b-instruct-fp8 Meta · Llama 3.1 Community	1306±8	8,950
127	92173	hunyuan-large-2025-02-10 Tencent · Proprietary	1306±24	568
128	109157	claude-3-5-sonnet-20240620 Anthropic · Proprietary	1305±7	12,430
129	112156	claude-3-5-haiku-20241022 Anthropic · Proprietary	1305±6	10,166
130	92176	hunyuan-turbos-20250226 Tencent · Proprietary	1305±26	425
131	92175	hunyuan-turbo-0110 Tencent · Proprietary	1305±25	452
132	106164	amazon-nova-experimental-chat-11-10 Amazon · Proprietary	1304±13	2,361
133	113158	o3-mini OpenAI · Proprietary	1303±7	8,459
134	113160	llama-3.1-405b-instruct-bf16 Meta · Llama 3.1 Community	1303±8	6,518
135	97173	glm-4.7-flash Z.ai · MIT	1302±18	1,069
136	110166	gemma-3n-e4b-it Google · Gemma	1301±11	3,066
137	113164	gemini-1.5-flash-002 Google · Proprietary	1301±9	5,018
138	93180	llama-3.3-nemotron-49b-super-v1 Nvidia · Nvidia	1301±27	430
139	113167	yi-lightning 01 AI · Proprietary	1300±10	3,782
140	113169	qwq-32b Alibaba · Apache 2.0	1298±10	3,841
141	115166	gpt-4o-mini-2024-07-18 OpenAI · Proprietary	1297±7	10,501
142	106176	step-1o-turbo-202506 StepFun · Proprietary	1297±18	1,116
143	94191	amazon-nova-experimental-chat-10-09 Amazon · Proprietary	1295±32	320
144	118170	gemma-2-27b-it Google · Gemma license	1294±7	11,430
145	115173	llama-4-scout-17b-16e-instruct Meta · Llama	1293±10	4,002
146	116173	glm-4-plus Zhipu AI · Proprietary	1292±10	3,803
147	111184	minimax-m2 MiniMax · Apache 2.0	1290±21	806
148	123173	claude-3-opus-20240229 Anthropic · Proprietary	1289±6	28,394
149	121174	mistral-large-2407 Mistral · Mistral Research	1289±8	6,693
150	119175	qwen3-30b-a3b Alibaba · Apache 2.0	1289±10	3,608
151	123174	llama-3.3-70b-instruct Meta · Llama-3.3	1289±7	8,258
152	112188	hunyuan-large-vision Tencent · Proprietary	1288±23	674
153	123175	gpt-4-1106-preview OpenAI · Proprietary	1288±8	15,576
154	115182	olmo-3.1-32b-instruct Allen AI · Apache 2.0	1287±16	1,573
155	119178	qwen-max-0919 Alibaba · Qwen	1287±12	2,358
156	119182	gemma-2-9b-it-simpo Princeton · MIT	1286±15	1,671
157	125178	gpt-oss-120b OpenAI · Apache 2.0	1285±10	3,963
158	119184	amazon-nova-experimental-chat-10-20 Amazon · Proprietary	1284±16	1,488
159	128178	o1-mini OpenAI · Proprietary	1283±7	7,861
160	130180	gpt-4-0125-preview OpenAI · Proprietary	1282±8	13,941
161	122188	magistral-medium-2506 Mistral · Proprietary	1281±16	1,466
162	119193	llama-3.1-nemotron-70b-instruct Nvidia · Llama 3.1	1280±19	1,000
163	115195	hunyuan-standard-2025-02-10 Tencent · Proprietary	1279±24	590
164	135184	mistral-large-2411 Mistral · MRL	1278±9	4,441
165	119195	gemma-3-4b-it Google · Gemma	1278±22	667
166	126193	nova-2-lite Amazon · Proprietary	1277±15	1,616
167	128192	qwen2.5-plus-1127 Alibaba · Proprietary	1277±14	1,589
168	135185	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1277±9	4,360
169	142186	grok-2-mini-2024-08-13 xAI · Proprietary	1274±8	7,925
170	125196	ling-flash-2.0 Ant Group · MIT	1274±20	831
171	137193	athene-70b-0725 NexusFlow · CC-BY-NC-4.0	1273±11	3,098
172	134197	reka-core-20240904 Reka AI · Proprietary	1270±18	1,037
173	150194	deepseek-v2.5 DeepSeek · DeepSeek	1267±11	3,451
174	133201	olmo-3-32b-think Allen AI · Apache 2.0	1267±21	800
175	153193	gpt-4-0613 OpenAI · Proprietary	1267±8	13,932
176	155194	gemini-1.5-flash-001 Google · Proprietary	1265±8	9,032
177	145198	command-r-plus-08-2024 Cohere · CC-BY-NC-4.0	1265±15	1,474
178	133204	llama-3.1-nemotron-51b-instruct Nvidia · Llama 3.1	1263±26	482
179	148201	jamba-1.5-large AI21 Labs · Jamba Open	1263±16	1,379
180	161196	gemma-2-9b-it Google · Gemma license	1260±7	8,342
181	160196	llama-3.1-70b-instruct Meta · Llama 3.1 Community	1260±8	8,250
182	150204	ring-flash-2.0 Ant Group · MIT	1258±20	890
183	164200	qwen2.5-72b-instruct Alibaba · Qwen	1256±8	5,680
184	162201	athene-v2-chat NexusFlow · NexusFlow	1256±10	3,716
185	164200	llama-3-70b-instruct Meta · Llama 3 Community	1256±7	22,749
186	162201	gpt-4-0314 OpenAI · Proprietary	1256±10	8,230
187	155205	gpt-5-nano-high OpenAI · Proprietary	1254±20	933
188	164204	nvidia-nemotron-3-nano-30b-a3b-bf16 Nvidia · NVIDIA Open Model	1250±13	2,250
189	153210	llama-3.1-tulu-3-70b Ai2 · Llama 3.1	1250±25	441
190	174204	claude-3-sonnet-20240229 Anthropic · Proprietary	1247±8	15,593
191	157212	ibm-granite-h-small IBM · Apache 2.0	1246±23	708
192	165208	olmo-3.1-32b-think Allen AI · Apache 2.0	1245±18	1,265
193	166208	reka-flash-20240904 Reka AI · Proprietary	1245±17	1,037
194	170208	glm-4-0520 Zhipu AI · Proprietary	1243±15	1,547
195	179206	gemini-1.5-flash-8b-001 Google · Proprietary	1240±9	5,029
196	177208	nemotron-4-340b-instruct Nvidia · NVIDIA Open Model	1240±12	3,153
197	179206	amazon-nova-pro-v1.0 Amazon · Proprietary	1239±9	3,946
198	181206	command-r-plus Cohere · CC-BY-NC-4.0	1238±9	11,009
199	172214	gpt-oss-20b OpenAI · Apache 2.0	1238±18	1,297
200	185214	c4ai-aya-expanse-32b Cohere · CC-BY-NC-4.0	1230±10	3,850
201	157234	mercury Inception AI · Proprietary	1229±41	261
202	185216	mistral-small-24b-instruct-2501 Mistral · Apache 2.0	1229±12	2,417
203	178226	olmo-2-0325-32b-instruct Allen AI · Apache-2.0	1226±25	568
204	189217	qwen2-72b-instruct Alibaba · Qianwen LICENSE	1225±9	5,505
205	190217	amazon-nova-lite-v1.0 Amazon · Proprietary	1223±10	3,037
206	185225	ministral-8b-2410 Mistral · MRL	1223±22	678
207	198218	claude-3-haiku-20240307 Anthropic · Proprietary	1217±7	16,721
208	193229	jamba-1.5-mini AI21 Labs · Jamba Open	1213±16	1,399
209	199225	phi-4 Microsoft · MIT	1213±10	4,068
210	199225	mistral-large-2402 Mistral · Proprietary	1213±9	9,058
211	197230	command-r-08-2024 Cohere · CC-BY-NC-4.0	1211±16	1,421
212	193233	qwen2.5-coder-32b-instruct Alibaba · Apache 2.0	1209±19	835
213	201232	deepseek-coder-v2 DeepSeek · DeepSeek License	1205±13	2,271
214	201233	gemini-pro-dev-api Google · Proprietary	1204±14	3,045
215	204233	amazon-nova-micro-v1.0 Amazon · Proprietary	1200±11	3,060
216	202236	wizardlm-70b Microsoft · Llama 2 Community	1200±17	1,779
217	198239	llama-3.1-tulu-3-8b Ai2 · Llama 3.1	1199±25	471
218	205233	llama-3-8b-instruct Meta · Llama 3 Community	1198±8	15,364
219	205235	command-r Cohere · CC-BY-NC-4.0	1197±10	7,837
220	197244	hunyuan-standard-256k Tencent · Proprietary	1197±29	357
221	205236	mistral-medium Mistral · Proprietary	1195±11	5,549
222	205236	qwen1.5-110b-chat Alibaba · Qianwen LICENSE	1195±12	3,678
223	207236	mixtral-8x22b-instruct-v0.1 Mistral · Apache 2.0	1192±9	7,448
224	205238	c4ai-aya-expanse-8b Cohere · CC-BY-NC-4.0	1192±15	1,530
225	209237	qwen1.5-72b-chat Alibaba · Qianwen LICENSE	1190±10	5,889
226	209236	gpt-3.5-turbo-0125 OpenAI · Proprietary	1190±9	9,693
227	205244	openchat-3.5 OpenChat · Apache-2.0	1186±18	1,454
228	211238	gemma-2-2b-it Google · Gemma license	1185±8	7,095
229	205247	gemini-pro Google · Proprietary	1185±21	953
230	210244	reka-flash-21b-20240226-online Reka AI · Proprietary	1183±14	2,118
231	217240	llama-3.1-8b-instruct Meta · Llama 3.1 Community	1180±8	7,346
232	216247	reka-flash-21b-20240226 Reka AI · Proprietary	1176±12	3,490
233	218251	vicuna-33b LMSYS · Non-commercial	1174±12	4,010
234	209263	granite-3.1-8b-instruct IBM · Apache 2.0	1172±27	450
235	211262	zephyr-orpo-141b-A35b-v0.1 HuggingFace · Apache 2.0	1170±23	635
236	226259	dbrx-instruct-preview Databricks · DBRX LICENSE	1165±12	4,808
237	227260	yi-1.5-34b-chat 01 AI · Apache-2.0	1162±11	3,602
238	228260	mixtral-8x7b-instruct-v0.1 Mistral · Apache 2.0	1161±9	11,172
239	223266	openhermes-2.5-mistral-7b NousResearch · Apache-2.0	1159±22	811
240	228264	yi-34b-chat 01 AI · Yi License	1156±14	2,378
241	212273	falcon-180b-chat TII · Falcon-180B TII License	1154±37	270
242	228266	gpt-3.5-turbo-1106 OpenAI · Proprietary	1154±15	2,828
243	233264	phi-3-medium-4k-instruct Microsoft · MIT	1152±11	3,736
244	224271	granite-3.1-2b-instruct IBM · Apache 2.0	1150±29	443
245	234266	gemma-1.1-7b-it Google · Gemma license	1149±12	3,408
246	233266	openchat-3.5-0106 OpenChat · Apache-2.0	1148±15	1,859
247	231267	tulu-2-dpo-70b AllenAI/UW · AI2 ImpACT Low-risk	1148±19	1,125
248	231267	llama-3.2-3b-instruct Meta · Llama 3.2	1146±20	1,070
249	234267	snowflake-arctic-instruct Snowflake · Apache 2.0	1144±12	4,777
250	234267	wizardlm-13b Microsoft · Llama 2 Community	1142±18	1,375
251	233273	solar-10.7b-instruct-v1.0 Upstage AI · CC-BY-NC-4.0	1140±24	698
252	235268	qwen1.5-14b-chat Alibaba · Qianwen LICENSE	1139±14	2,392
253	234271	zephyr-7b-beta HuggingFace · MIT	1138±16	1,993
254	234271	starling-lm-7b-alpha UC Berkeley · CC-BY-NC-4.0	1138±16	1,701
255	234273	granite-3.0-8b-instruct IBM · Apache 2.0	1137±21	895
256	234275	nous-hermes-2-mixtral-8x7b-dpo NousResearch · Apache-2.0	1137±23	616
257	231279	guanaco-33b UW · Non-commercial	1137±28	515
258	228285	dolphin-2.2.1-mistral-7b Cognitive Computations · Apache-2.0	1136±34	291
259	234274	deepseek-llm-67b-chat DeepSeek · DeepSeek License	1136±22	789
260	237271	phi-3-small-8k-instruct Microsoft · MIT	1135±13	2,400
261	237273	internlm2_5-20b-chat InternLM · Other	1134±16	1,432
262	233285	mpt-30b-chat MosaicML · CC-BY-NC-SA-4.0	1134±29	452
263	239271	qwen1.5-32b-chat Alibaba · Qianwen LICENSE	1133±12	3,024
264	241274	vicuna-13b LMSYS · Llama 2 Community	1127±13	3,346
265	238288	llama2-70b-steerlm-chat Nvidia · Llama 2 Community	1121±25	603
266	250285	llama-2-70b-chat Meta · Llama 2 Community	1114±10	6,377
267	241290	qwq-32b-preview Alibaba · Apache 2.0	1110±29	454
268	249288	starling-lm-7b-beta Nexusflow · Apache-2.0	1110±15	2,378
269	255288	mistral-7b-instruct-v0.2 Mistral · Apache-2.0	1106±13	2,952
270	250290	qwen-14b-chat Alibaba · Qianwen LICENSE	1103±21	898
271	245291	zephyr-7b-alpha HuggingFace · MIT	1103±30	399
272	255290	gemma-7b-it Google · Gemma license	1102±18	1,345
273	250290	granite-3.0-2b-instruct IBM · Apache 2.0	1101±22	916
274	262290	phi-3-mini-4k-instruct-june-2024 Microsoft · MIT	1098±15	1,955
275	263290	llama-2-13b-chat Meta · Llama 2 Community	1094±13	3,296
276	262291	gemma-1.1-2b-it Google · Gemma license	1093±17	1,486
277	262291	mistral-7b-instruct Mistral · Apache 2.0	1092±17	1,689
278	261291	alpaca-13b Stanford · Non-commercial	1092±22	954
279	263291	vicuna-7b LMSYS · Llama 2 Community	1091±18	1,323
280	262291	stripedhyena-nous-7b Together AI · Apache 2.0	1091±21	869
281	263291	codellama-34b-instruct Meta · Llama 2 Community	1088±17	1,507
282	263291	palm-2 Google · Proprietary	1088±18	1,576
283	266291	phi-3-mini-128k-instruct Microsoft · MIT	1087±14	2,949
284	263294	llama-3.2-1b-instruct Meta · Llama 3.2	1084±21	1,091
285	263294	qwen1.5-7b-chat Alibaba · Qianwen LICENSE	1083±23	701
286	259294	smollm2-1.7b-instruct HuggingFace · Apache 2.0	1081±35	341
287	266294	gemma-2b-it Google · Gemma license	1078±23	696
288	269294	phi-3-mini-4k-instruct Microsoft · MIT	1076±13	2,812
289	269294	llama-2-7b-chat Meta · Llama 2 Community	1074±14	2,341
290	266297	gpt4all-13b-snoozy Nomic AI · Non-commercial	1064±38	250
291	275296	mpt-7b-chat MosaicML · CC-BY-NC-SA-4.0	1053±24	683
292	284296	qwen1.5-4b-chat Alibaba · Qianwen LICENSE	1050±19	1,082
293	284297	koala-13b UC Berkeley · Non-commercial	1047±21	1,199
294	284298	chatglm3-6b Tsinghua · Apache-2.0	1041±23	816
295	290300	oasst-pythia-12b OpenAssistant · Apache 2.0	1013±21	1,094
296	294300	olmo-7b-instruct Allen AI · Apache-2.0	1005±20	1,020
297	290300	chatglm2-6b Tsinghua · Apache-2.0	1005±26	566
298	292300	RWKV-4-Raven-14B RWKV · Apache 2.0	1005±23	874
299	295301	fastchat-t5-3b LMSYS · Apache 2.0	992±24	744
300	295303	dolly-v2-12b Databricks · MIT	970±28	565
301	299303	chatglm-6b Tsinghua · Non-commercial	953±25	771
302	300303	stablelm-tuned-alpha-7b Stability AI · CC-BY-NC-SA-4.0	933±29	536
303	300303	llama-13b Meta · Non-commercial	933±34	431

Text Arena

Default Leaderboard Plots

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

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

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)