Text Arena | Creative Writing

View overall rankings across various AI models in text-to-text tasks across math, coding, creative writing, and other open-ended domains.

Feb 26, 2026

772,355 votes

314 models

	Rank Spread
1	16	claude-opus-4-6-thinking Anthropic · Proprietary	1491±19	1,003
2	16	gemini-3-pro Google · Proprietary	1486±9	5,474
3	110	grok-4.20-beta1 xAI · Proprietary	1483±26	516
4	111	gemini-3.1-pro-preview Google · Proprietary	1480±25	571
5	110	claude-opus-4-6 Anthropic · Proprietary	1477±18	1,075
6	314	claude-opus-4-5-20251101-thinking-32k Anthropic · Proprietary	1461±10	4,330
7	315	gemini-3-flash Google · Proprietary	1459±10	4,278
8	129	gpt-5.2-chat-latest-20260210 OpenAI · Proprietary	1456±26	512
9	318	claude-opus-4-5-20251101 Anthropic · Proprietary	1455±9	5,017
10	518	gemini-2.5-pro Google · Proprietary	1449±6	13,062
11	623	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1446±8	6,357
12	626	claude-opus-4-1-20250805-thinking-16k Anthropic · Proprietary	1444±8	6,548
13	628	gemini-3-flash (thinking-minimal) Google · Proprietary	1443±11	2,918
14	335	claude-sonnet-4-6 Anthropic · Proprietary	1441±25	515
15	828	claude-sonnet-4-5-20250929-thinking-32k Anthropic · Proprietary	1440±8	6,590
16	828	claude-opus-4-1-20250805 Anthropic · Proprietary	1440±6	10,259
17	831	gpt-4.5-preview-2025-02-27 OpenAI · Proprietary	1437±12	2,618
18	1031	grok-4.1-thinking xAI · Proprietary	1434±9	5,223
19	1031	gpt-5.1-high OpenAI · Proprietary	1434±9	4,765
20	738	glm-5 Z.ai · MIT	1430±19	929
21	1132	grok-4.1 xAI · Proprietary	1428±9	5,564
22	1132	claude-opus-4-20250514-thinking-16k Anthropic · Proprietary	1428±9	4,712
23	1037	ernie-5.0-0110 Baidu · Proprietary	1426±13	2,176
24	1636	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1421±6	11,337
25	1250	ernie-5.0-preview-1203 Baidu · Proprietary	1420±16	1,462
26	1059	qwen3.5-397b-a17b Alibaba · Apache 2.0	1419±21	752
27	1250	kimi-k2.5-thinking Moonshot · Modified MIT	1419±15	1,613
28	1643	claude-opus-4-20250514 Anthropic · Proprietary	1418±8	5,726
29	1162	ernie-5.0-preview-1022 Baidu · Proprietary	1415±23	637
30	1074	deepseek-v3.1-terminus DeepSeek · MIT	1412±27	456
31	1568	dola-seed-2.0-preview Bytedance · Proprietary	1410±21	758
32	2158	gpt-5.1 OpenAI · Proprietary	1409±9	5,077
33	1960	deepseek-v3.1-thinking DeepSeek · MIT	1409±14	1,707
34	2360	grok-4-1-fast-reasoning xAI · Proprietary	1405±9	4,414
35	2166	glm-4.7 Z.ai · MIT	1404±14	1,781
36	2172	deepseek-v3.2-exp DeepSeek · MIT	1403±15	1,458
37	2560	gpt-4.1-2025-04-14 OpenAI · Proprietary	1402±8	6,774
38	2562	glm-4.6 Z.ai · MIT	1401±9	4,706
39	2562	grok-3-preview-02-24 xAI · Proprietary	1401±9	4,938
40	2569	deepseek-v3.2 DeepSeek · MIT	1399±10	4,056
41	2472	gpt-5.2 OpenAI · Proprietary	1399±13	2,330
42	2282	kimi-k2.5-instant Moonshot · Modified MIT	1398±18	1,069
43	2865	gemini-2.5-flash Google · Proprietary	1396±6	12,802
44	2672	grok-4-0709 xAI · Proprietary	1396±8	5,456
45	2674	qwen3-max-preview Alibaba · Proprietary	1395±10	3,672
46	2677	gpt-5.2-high OpenAI · Proprietary	1395±12	2,733
47	2874	claude-sonnet-4-20250514-thinking-32k Anthropic · Proprietary	1395±9	4,537
48	2874	claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary	1394±8	5,427
49	2681	deepseek-v3.1 DeepSeek · MIT	1394±13	2,058
50	2584	qwen3-max-2025-09-23 Alibaba · Proprietary	1394±17	1,145
51	2876	gpt-5-chat OpenAI · Proprietary	1393±10	3,961
52	2586	deepseek-v3.2-exp-thinking DeepSeek · MIT	1393±18	1,146
53	2877	kimi-k2-thinking-turbo Moonshot · Modified MIT	1392±9	5,075
54	2977	deepseek-v3-0324 DeepSeek · MIT	1391±8	6,271
55	2884	deepseek-r1-0528 DeepSeek · MIT	1390±12	2,633
56	3084	deepseek-v3.2-thinking DeepSeek · MIT	1388±10	3,680
57	3386	claude-sonnet-4-20250514 Anthropic · Proprietary	1384±9	5,268
58	3684	o3-2025-04-16 OpenAI · Proprietary	1384±7	7,926
59	2698	hunyuan-t1-20250711 Tencent · Proprietary	1383±24	635
60	3984	qwen3-235b-a22b-instruct-2507 Alibaba · Apache 2.0	1383±6	9,598
61	3687	o1-2024-12-17 OpenAI · Proprietary	1382±9	4,646
62	2894	grok-4-fast-chat xAI · Proprietary	1382±19	988
63	3888	claude-haiku-4-5-20251001 Anthropic · Proprietary	1382±8	6,257
64	4086	mistral-medium-2508 Mistral · Proprietary	1381±7	9,092
65	3690	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1381±9	4,212
66	26106	deepseek-v3.1-terminus-thinking DeepSeek · MIT	1380±27	446
67	3394	kimi-k2-0905-preview Moonshot · Modified MIT	1379±15	1,481
68	4091	gpt-5-high OpenAI · Proprietary	1379±10	4,268
69	3792	grok-4-fast-reasoning xAI · Proprietary	1378±12	2,339
70	4092	glm-4.5 Z.ai · MIT	1377±11	3,169
71	4791	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1376±8	6,219
72	4393	deepseek-r1 DeepSeek · MIT	1376±10	3,295
73	4793	mistral-large-3 Mistral · Apache 2.0	1374±10	3,912
74	5194	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1373±9	4,377
75	38106	qwen3-235b-a22b-thinking-2507 Alibaba · Apache 2.0	1372±18	1,127
76	5396	qwen3-235b-a22b-no-thinking Alibaba · Apache 2.0	1371±9	4,851
77	5894	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1370±6	11,941
78	5398	kimi-k2-0711-preview Moonshot · Modified MIT	1369±10	3,645
79	28126	hunyuan-vision-1.5-thinking Tencent · Proprietary	1368±36	257
80	43108	minimax-m2.5 MiniMax · Modified MIT	1367±19	910
81	58102	o1-preview OpenAI · Proprietary	1366±10	4,506
82	52106	hunyuan-turbos-20250416 Tencent · Proprietary	1365±15	1,567
83	62105	mistral-medium-2505 Mistral · Proprietary	1364±9	4,383
84	61106	qwen3-coder-480b-a35b-instruct Alibaba · Apache 2.0	1364±10	3,424
85	51108	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1364±17	1,362
86	63106	mimo-v2-flash (non-thinking) Xiaomi · MIT	1362±11	2,945
87	64106	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1361±8	6,156
88	66106	gemini-1.5-pro-002 Google · Proprietary	1360±7	8,065
89	63109	mai-1-preview Microsoft AI · Proprietary	1359±13	2,230
90	48126	amazon-nova-experimental-chat-26-01-10 Amazon · Proprietary	1357±26	519
91	74109	qwen2.5-max Alibaba · Proprietary	1354±8	5,116
92	51141	glm-4.6v Z.ai · MIT	1352±29	386
93	75113	deepseek-v3 DeepSeek · DeepSeek	1351±10	3,624
94	78113	gemma-3-27b-it Google · Gemma	1349±8	6,552
95	77113	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1348±9	5,391
96	51143	trinity-large Arcee AI · Apache 2.0	1348±32	335
97	78113	gemini-2.0-flash-001 Google · Proprietary	1348±8	6,463
98	70128	step-3.5-flash StepFun · Apache 2.0	1348±17	1,201
99	77123	minimax-m2.1-preview MiniMax · MIT	1347±12	2,591
100	78119	gemini-2.0-flash-lite-preview-02-05 Google · Proprietary	1346±9	4,100
101	79123	gemini-advanced-0514 Google · Proprietary	1344±10	7,026
102	74138	qwen3-vl-235b-a22b-thinking Alibaba · Apache 2.0	1344±18	996
103	68142	amazon-nova-experimental-chat-12-10 Amazon · Proprietary	1341±24	578
104	86125	o4-mini-2025-04-16 OpenAI · Proprietary	1340±8	6,019
105	90126	gpt-4o-2024-05-13 OpenAI · Proprietary	1338±7	16,599
106	77142	step-2-16k-exp-202412 StepFun · Proprietary	1338±21	748
107	90130	command-a-03-2025 Cohere · CC-BY-NC-4.0	1336±7	7,791
108	88139	grok-3-mini-beta xAI · Proprietary	1336±11	2,959
109	86141	mimo-v2-flash (thinking) Xiaomi · MIT	1335±15	1,632
110	77147	gemma-3-12b-it Google · Gemma	1334±23	600
111	75155	llama-3.1-nemotron-ultra-253b-v1 Nvidia · Nvidia Open Model	1334±27	444
112	90141	grok-3-mini-high xAI · Proprietary	1331±13	2,183
113	94141	glm-4.5-air Z.ai · MIT	1330±10	3,976
114	90144	longcat-flash-chat Meituan · MIT	1330±16	1,375
115	94142	qwen3-235b-a22b Alibaba · Apache 2.0	1328±10	3,749
116	95141	gpt-4o-2024-08-06 OpenAI · Proprietary	1327±8	6,756
117	94143	gpt-5-mini-high OpenAI · Proprietary	1327±11	3,466
118	95144	qwen3-30b-a3b-instruct-2507 Alibaba · Apache 2.0	1325±11	3,039
119	94147	qwen3-next-80b-a3b-thinking Alibaba · Apache 2.0	1325±14	1,781
120	98143	gemini-1.5-pro-001 Google · Proprietary	1324±8	11,800
121	101143	gpt-4-turbo-2024-04-09 OpenAI · Proprietary	1323±8	14,398
122	101144	minimax-m1 MiniMax · Apache 2.0	1322±9	4,806
123	97152	mistral-small-2506 Mistral · Apache 2.0	1322±12	2,332
124	94162	glm-4-plus-0111 Zhipu · Proprietary	1319±19	920
125	103147	grok-2-2024-08-13 xAI · Proprietary	1318±7	9,339
126	95161	qwen-plus-0125 Alibaba · Proprietary	1318±18	933
127	103155	qwen3-next-80b-a3b-instruct Alibaba · Apache 2.0	1317±11	2,899
128	94174	glm-4.5v Z.ai · MIT	1316±23	628
129	105159	o3-mini-high OpenAI · Proprietary	1313±11	3,067
130	103172	deepseek-v2.5-1210 DeepSeek · DeepSeek	1311±17	1,088
131	97179	intellect-3 Prime Intellect · MIT	1310±22	756
132	105172	glm-4.7-flash Z.ai · MIT	1310±15	1,541
133	110161	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1309±8	5,388
134	95186	nvidia-llama-3.3-nemotron-super-49b-v1.5 Nvidia · Nvidia Open	1308±29	397
135	103177	gpt-4.1-nano-2025-04-14 OpenAI · Proprietary	1308±18	1,008
136	102183	qwen3-32b Alibaba · Apache 2.0	1307±22	622
137	103183	step-3 StepFun · Apache 2.0	1306±21	794
138	103184	hunyuan-large-2025-02-10 Tencent · Proprietary	1305±24	568
139	120167	llama-3.1-405b-instruct-fp8 Meta · Llama 3.1 Community	1305±8	8,950
140	113172	amazon-nova-experimental-chat-11-10 Amazon · Proprietary	1305±12	2,750
141	123167	claude-3-5-haiku-20241022 Anthropic · Proprietary	1304±6	10,120
142	120169	claude-3-5-sonnet-20240620 Anthropic · Proprietary	1304±7	12,430
143	102186	hunyuan-turbos-20250226 Tencent · Proprietary	1304±26	425
144	103186	hunyuan-turbo-0110 Tencent · Proprietary	1304±25	452
145	124169	o3-mini OpenAI · Proprietary	1302±7	8,418
146	123172	llama-3.1-405b-instruct-bf16 Meta · Llama 3.1 Community	1302±8	6,518
147	120176	gemma-3n-e4b-it Google · Gemma	1301±11	3,031
148	103192	llama-3.3-nemotron-49b-super-v1 Nvidia · Nvidia	1300±27	430
149	124175	gemini-1.5-flash-002 Google · Proprietary	1300±9	5,018
150	123178	yi-lightning 01 AI · Proprietary	1299±10	3,782
151	124180	qwq-32b Alibaba · Apache 2.0	1297±10	3,817
152	117186	step-1o-turbo-202506 StepFun · Proprietary	1297±18	1,098
153	126177	gpt-4o-mini-2024-07-18 OpenAI · Proprietary	1296±7	10,500
154	126183	llama-4-scout-17b-16e-instruct Meta · Llama	1293±10	3,970
155	104203	amazon-nova-experimental-chat-10-09 Amazon · Proprietary	1293±32	316
156	129182	gemma-2-27b-it Google · Gemma license	1293±7	11,430
157	127184	glm-4-plus Zhipu AI · Proprietary	1291±10	3,803
158	123193	minimax-m2 MiniMax · Apache 2.0	1289±21	798
159	134184	claude-3-opus-20240229 Anthropic · Proprietary	1288±6	28,394
160	130186	qwen3-30b-a3b Alibaba · Apache 2.0	1288±10	3,576
161	132185	mistral-large-2407 Mistral · Mistral Research	1288±9	6,693
162	126193	olmo-3.1-32b-instruct Ai2 · Apache 2.0	1288±15	1,676
163	134185	llama-3.3-70b-instruct Meta · Llama-3.3	1288±7	8,239
164	123199	hunyuan-large-vision Tencent · Proprietary	1288±23	672
165	134186	gpt-4-1106-preview OpenAI · Proprietary	1287±8	15,576
166	130189	qwen-max-0919 Alibaba · Qwen	1286±12	2,358
167	127193	amazon-nova-experimental-chat-10-20 Amazon · Proprietary	1285±16	1,461
168	130193	gemma-2-9b-it-simpo Princeton · MIT	1285±15	1,671
169	138189	gpt-oss-120b OpenAI · Apache 2.0	1284±10	3,908
170	141189	o1-mini OpenAI · Proprietary	1282±8	7,861
171	143192	gpt-4-0125-preview OpenAI · Proprietary	1281±8	13,941
172	132199	magistral-medium-2506 Mistral · Proprietary	1280±16	1,448
173	130204	llama-3.1-nemotron-70b-instruct Nvidia · Llama 3.1	1279±19	1,000
174	126205	hunyuan-standard-2025-02-10 Tencent · Proprietary	1278±24	590
175	138202	nova-2-lite Amazon · Proprietary	1278±15	1,596
176	147193	mistral-large-2411 Mistral · MRL	1277±9	4,441
177	130205	gemma-3-4b-it Google · Gemma	1277±22	667
178	146193	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1277±9	4,308
179	140203	qwen2.5-plus-1127 Alibaba · Proprietary	1276±14	1,589
180	153195	grok-2-mini-2024-08-13 xAI · Proprietary	1273±8	7,925
181	150204	athene-70b-0725 NexusFlow · CC-BY-NC-4.0	1272±11	3,098
182	139207	ling-flash-2.0 Ant Group · MIT	1271±21	818
183	146208	reka-core-20240904 Reka AI · Proprietary	1269±18	1,037
184	144212	olmo-3-32b-think Ai2 · Apache 2.0	1267±21	792
185	161205	deepseek-v2.5 DeepSeek · DeepSeek	1266±11	3,451
186	164204	gpt-4-0613 OpenAI · Proprietary	1266±8	13,932
187	166205	gemini-1.5-flash-001 Google · Proprietary	1264±8	9,032
188	155209	command-r-plus-08-2024 Cohere · CC-BY-NC-4.0	1264±15	1,474
189	145215	llama-3.1-nemotron-51b-instruct Nvidia · Llama 3.1	1262±26	482
190	161212	jamba-1.5-large AI21 Labs · Jamba Open	1262±16	1,379
191	172207	gemma-2-9b-it Google · Gemma license	1259±7	8,342
192	172207	llama-3.1-70b-instruct Meta · Llama 3.1 Community	1259±8	8,250
193	161215	ring-flash-2.0 Ant Group · MIT	1258±20	876
194	175211	qwen2.5-72b-instruct Alibaba · Qwen	1255±8	5,680
195	173212	athene-v2-chat NexusFlow · NexusFlow	1255±10	3,716
196	176211	llama-3-70b-instruct Meta · Llama 3 Community	1255±7	22,749
197	175212	gpt-4-0314 OpenAI · Proprietary	1254±10	8,230
198	164215	gpt-5-nano-high OpenAI · Proprietary	1254±20	920
199	173215	nvidia-nemotron-3-nano-30b-a3b-bf16 Nvidia · NVIDIA Open Model	1252±13	2,228
200	164221	llama-3.1-tulu-3-70b Ai2 · Llama 3.1	1249±25	441
201	175217	olmo-3.1-32b-think Ai2 · Apache 2.0	1246±18	1,252
202	185215	claude-3-sonnet-20240229 Anthropic · Proprietary	1246±8	15,593
203	178219	reka-flash-20240904 Reka AI · Proprietary	1244±18	1,037
204	181219	glm-4-0520 Zhipu AI · Proprietary	1242±15	1,547
205	173225	ibm-granite-h-small IBM · Apache 2.0	1242±24	694
206	190217	gemini-1.5-flash-8b-001 Google · Proprietary	1239±9	5,029
207	188219	nemotron-4-340b-instruct Nvidia · NVIDIA Open Model	1239±12	3,153
208	190217	amazon-nova-pro-v1.0 Amazon · Proprietary	1239±9	3,946
209	192217	command-r-plus Cohere · CC-BY-NC-4.0	1237±9	11,009
210	185225	gpt-oss-20b OpenAI · Apache 2.0	1236±18	1,274
211	196225	c4ai-aya-expanse-32b Cohere · CC-BY-NC-4.0	1229±10	3,850
212	196227	mistral-small-24b-instruct-2501 Mistral · Apache 2.0	1228±12	2,417
213	189236	olmo-2-0325-32b-instruct Ai2 · Apache-2.0	1225±25	568
214	173247	mercury Inception AI · Proprietary	1224±42	250
215	201228	qwen2-72b-instruct Alibaba · Qianwen LICENSE	1224±10	5,505
216	201228	amazon-nova-lite-v1.0 Amazon · Proprietary	1222±10	3,037
217	196236	ministral-8b-2410 Mistral · MRL	1222±22	678
218	209229	claude-3-haiku-20240307 Anthropic · Proprietary	1215±8	16,721
219	205240	jamba-1.5-mini AI21 Labs · Jamba Open	1212±16	1,399
220	209236	phi-4 Microsoft · MIT	1212±10	4,068
221	209236	mistral-large-2402 Mistral · Proprietary	1211±9	9,058
222	208241	command-r-08-2024 Cohere · CC-BY-NC-4.0	1210±16	1,421
223	205244	qwen2.5-coder-32b-instruct Alibaba · Apache 2.0	1209±19	835
224	212243	deepseek-coder-v2 DeepSeek · DeepSeek License	1204±13	2,271
225	212244	gemini-pro-dev-api Google · Proprietary	1203±14	3,045
226	215244	amazon-nova-micro-v1.0 Amazon · Proprietary	1199±11	3,060
227	213247	wizardlm-70b Microsoft · Llama 2 Community	1199±17	1,779
228	209250	llama-3.1-tulu-3-8b Ai2 · Llama 3.1	1198±25	471
229	216244	llama-3-8b-instruct Meta · Llama 3 Community	1197±8	15,364
230	208255	hunyuan-standard-256k Tencent · Proprietary	1196±29	357
231	216246	command-r Cohere · CC-BY-NC-4.0	1196±10	7,837
232	216247	mistral-medium Mistral · Proprietary	1194±11	5,549
233	216247	qwen1.5-110b-chat Alibaba · Qianwen LICENSE	1194±12	3,678
234	220247	mixtral-8x22b-instruct-v0.1 Mistral · Apache 2.0	1191±9	7,448
235	216249	c4ai-aya-expanse-8b Cohere · CC-BY-NC-4.0	1191±15	1,530
236	220248	qwen1.5-72b-chat Alibaba · Qianwen LICENSE	1189±10	5,889
237	220247	gpt-3.5-turbo-0125 OpenAI · Proprietary	1189±9	9,693
238	216255	openchat-3.5 OpenChat · Apache-2.0	1185±18	1,454
239	222249	gemma-2-2b-it Google · Gemma license	1184±8	7,095
240	216258	gemini-pro Google · Proprietary	1184±21	953
241	221255	reka-flash-21b-20240226-online Reka AI · Proprietary	1182±15	2,118
242	227251	llama-3.1-8b-instruct Meta · Llama 3.1 Community	1179±8	7,346
243	227258	reka-flash-21b-20240226 Reka AI · Proprietary	1175±12	3,490
244	228262	vicuna-33b LMSYS · Non-commercial	1173±12	4,010
245	220274	granite-3.1-8b-instruct IBM · Apache 2.0	1171±27	450
246	222274	zephyr-orpo-141b-A35b-v0.1 HuggingFace · Apache 2.0	1169±23	635
247	237270	dbrx-instruct-preview Databricks · DBRX LICENSE	1163±12	4,808
248	238271	yi-1.5-34b-chat 01 AI · Apache-2.0	1161±11	3,602
249	239271	mixtral-8x7b-instruct-v0.1 Mistral · Apache 2.0	1160±9	11,172
250	234277	openhermes-2.5-mistral-7b NousResearch · Apache-2.0	1158±22	811
251	239275	yi-34b-chat 01 AI · Yi License	1155±14	2,378
252	223284	falcon-180b-chat TII · Falcon-180B TII License	1153±37	270
253	239277	gpt-3.5-turbo-1106 OpenAI · Proprietary	1153±15	2,828
254	244275	phi-3-medium-4k-instruct Microsoft · MIT	1151±11	3,736
255	235282	granite-3.1-2b-instruct IBM · Apache 2.0	1149±29	443
256	245277	gemma-1.1-7b-it Google · Gemma license	1148±12	3,408
257	244277	openchat-3.5-0106 OpenChat · Apache-2.0	1147±15	1,859
258	242278	tulu-2-dpo-70b AllenAI/UW · AI2 ImpACT Low-risk	1147±19	1,125
259	242278	llama-3.2-3b-instruct Meta · Llama 3.2	1145±20	1,070
260	245278	snowflake-arctic-instruct Snowflake · Apache 2.0	1142±12	4,777
261	245278	wizardlm-13b Microsoft · Llama 2 Community	1141±18	1,375
262	244284	solar-10.7b-instruct-v1.0 Upstage AI · CC-BY-NC-4.0	1139±24	698
263	246279	qwen1.5-14b-chat Alibaba · Qianwen LICENSE	1138±14	2,392
264	245282	zephyr-7b-beta HuggingFace · MIT	1137±16	1,993
265	245282	starling-lm-7b-alpha UC Berkeley · CC-BY-NC-4.0	1137±16	1,701
266	245284	granite-3.0-8b-instruct IBM · Apache 2.0	1136±21	895
267	245286	nous-hermes-2-mixtral-8x7b-dpo NousResearch · Apache-2.0	1136±23	616
268	242290	guanaco-33b UW · Non-commercial	1136±28	515
269	239296	dolphin-2.2.1-mistral-7b Cognitive Computations · Apache-2.0	1135±34	291
270	245285	deepseek-llm-67b-chat DeepSeek · DeepSeek License	1135±22	789
271	248282	phi-3-small-8k-instruct Microsoft · MIT	1134±13	2,400
272	248284	internlm2_5-20b-chat InternLM · Other	1133±16	1,432
273	244296	mpt-30b-chat MosaicML · CC-BY-NC-SA-4.0	1133±29	452
274	250282	qwen1.5-32b-chat Alibaba · Qianwen LICENSE	1132±12	3,024
275	252285	vicuna-13b LMSYS · Llama 2 Community	1126±13	3,346
276	248299	llama2-70b-steerlm-chat Nvidia · Llama 2 Community	1120±25	603
277	261296	llama-2-70b-chat Meta · Llama 2 Community	1113±10	6,377
278	252301	qwq-32b-preview Alibaba · Apache 2.0	1109±29	454
279	260299	starling-lm-7b-beta Nexusflow · Apache-2.0	1109±15	2,378
280	266299	mistral-7b-instruct-v0.2 Mistral · Apache-2.0	1105±13	2,952
281	261301	qwen-14b-chat Alibaba · Qianwen LICENSE	1102±21	898
282	256302	zephyr-7b-alpha HuggingFace · MIT	1102±30	399
283	266301	gemma-7b-it Google · Gemma license	1101±18	1,345
284	261301	granite-3.0-2b-instruct IBM · Apache 2.0	1100±22	916
285	273301	phi-3-mini-4k-instruct-june-2024 Microsoft · MIT	1097±15	1,955
286	274301	llama-2-13b-chat Meta · Llama 2 Community	1092±13	3,296
287	273302	gemma-1.1-2b-it Google · Gemma license	1092±17	1,486
288	273302	mistral-7b-instruct Mistral · Apache 2.0	1091±17	1,689
289	272302	alpaca-13b Stanford · Non-commercial	1090±22	954
290	274302	vicuna-7b LMSYS · Llama 2 Community	1089±18	1,323
291	273302	stripedhyena-nous-7b Together AI · Apache 2.0	1089±21	869
292	274302	codellama-34b-instruct Meta · Llama 2 Community	1087±17	1,507
293	274302	palm-2 Google · Proprietary	1087±18	1,576
294	277302	phi-3-mini-128k-instruct Microsoft · MIT	1086±14	2,949
295	274305	llama-3.2-1b-instruct Meta · Llama 3.2	1083±21	1,091
296	274305	qwen1.5-7b-chat Alibaba · Qianwen LICENSE	1081±23	701
297	270305	smollm2-1.7b-instruct HuggingFace · Apache 2.0	1080±35	341
298	277305	gemma-2b-it Google · Gemma license	1077±23	696
299	280305	phi-3-mini-4k-instruct Microsoft · MIT	1074±13	2,812
300	280305	llama-2-7b-chat Meta · Llama 2 Community	1073±14	2,341
301	277308	gpt4all-13b-snoozy Nomic AI · Non-commercial	1063±38	250
302	286307	mpt-7b-chat MosaicML · CC-BY-NC-SA-4.0	1051±24	683
303	295307	qwen1.5-4b-chat Alibaba · Qianwen LICENSE	1049±19	1,082
304	295308	koala-13b UC Berkeley · Non-commercial	1046±21	1,199
305	295309	chatglm3-6b Tsinghua · Apache-2.0	1040±23	816
306	301311	oasst-pythia-12b OpenAssistant · Apache 2.0	1012±21	1,094
307	305311	olmo-7b-instruct Ai2 · Apache-2.0	1004±20	1,020
308	301311	chatglm2-6b Tsinghua · Apache-2.0	1004±26	566
309	303311	RWKV-4-Raven-14B RWKV · Apache 2.0	1004±23	874
310	306312	fastchat-t5-3b LMSYS · Apache 2.0	991±24	744
311	306314	dolly-v2-12b Databricks · MIT	968±28	565
312	310314	chatglm-6b Tsinghua · Non-commercial	952±25	771
313	311314	stablelm-tuned-alpha-7b Stability AI · CC-BY-NC-SA-4.0	932±29	536
314	311314	llama-13b Meta · Non-commercial	932±34	431

Text Arena | Creative Writing

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)