Text Arena | Hard Prompts

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

Mar 6, 2026

1,970,443 votes

323 models

	Rank Spread
1	13	claude-opus-4-6-thinking Anthropic · Proprietary	1535±9	4,495
2	13	claude-opus-4-6 Anthropic · Proprietary	1535±9	5,125
3	14	gemini-3.1-pro-preview Google · Proprietary	1523±12	2,285
4	312	grok-4.20-beta1 xAI · Proprietary	1508±11	2,734
5	412	gemini-3-pro Google · Proprietary	1503±5	21,762
6	412	claude-opus-4-5-20251101-thinking-32k Anthropic · Proprietary	1500±6	17,185
7	413	gpt-5.2-chat-latest-20260210 OpenAI · Proprietary	1499±10	3,271
8	412	claude-opus-4-5-20251101 Anthropic · Proprietary	1497±5	20,063
9	415	gemini-3-flash Google · Proprietary	1492±6	16,501
10	424	gpt-5.4-high OpenAI · Proprietary	1492±14	1,823
11	420	dola-seed-2.0-preview Bytedance · Proprietary	1490±10	3,715
12	424	claude-sonnet-4-6 Anthropic · Proprietary	1489±11	3,019
13	824	grok-4.1-thinking xAI · Proprietary	1484±5	20,814
14	924	claude-sonnet-4-5-20250929-thinking-32k Anthropic · Proprietary	1483±5	26,953
15	1025	claude-opus-4-1-20250805-thinking-16k Anthropic · Proprietary	1479±5	24,547
16	1025	gemini-3-flash (thinking-minimal) Google · Proprietary	1479±6	12,614
17	1025	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1479±5	26,127
18	1026	claude-opus-4-1-20250805 Anthropic · Proprietary	1477±4	38,746
19	1029	grok-4.1 xAI · Proprietary	1476±5	22,906
20	933	gpt-5.4 OpenAI · Proprietary	1474±14	1,712
21	1130	gpt-5.1-high OpenAI · Proprietary	1474±5	19,178
22	1130	kimi-k2.5-thinking Moonshot · Modified MIT	1472±7	6,985
23	1132	glm-5 Z.ai · MIT	1471±9	4,485
24	1132	qwen3.5-397b-a17b Alibaba · Apache 2.0	1470±9	3,830
25	1532	ernie-5.0-0110 Baidu · Proprietary	1469±7	8,380
26	1833	gpt-5.2-high OpenAI · Proprietary	1466±6	11,454
27	1935	gpt-5.2 OpenAI · Proprietary	1466±7	9,908
28	1940	kimi-k2.5-instant Moonshot · Modified MIT	1463±8	4,899
29	1940	ernie-5.0-preview-1203 Baidu · Proprietary	1463±9	5,185
30	2040	glm-4.7 Z.ai · MIT	1462±8	6,497
31	2238	gemini-2.5-pro Google · Proprietary	1460±4	47,984
32	2243	qwen3-max-preview Alibaba · Proprietary	1458±6	13,488
33	2744	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1455±4	38,355
34	2547	claude-opus-4-20250514-thinking-16k Anthropic · Proprietary	1454±6	16,571
35	2746	gpt-5.1 OpenAI · Proprietary	1454±5	20,948
36	2850	kimi-k2-thinking-turbo Moonshot · Modified MIT	1451±5	20,291
37	3255	gpt-5-chat OpenAI · Proprietary	1448±6	15,141
38	2960	qwen3-max-2025-09-23 Alibaba · Proprietary	1447±8	4,875
39	3454	qwen3-235b-a22b-instruct-2507 Alibaba · Apache 2.0	1447±4	36,929
40	2960	deepseek-v3.2-exp DeepSeek · MIT	1447±8	6,364
41	3359	gpt-5-high OpenAI · Proprietary	1446±6	15,070
42	2875	amazon-nova-experimental-chat-26-01-10 Amazon · Proprietary	1444±13	1,861
43	3268	deepseek-v3.2-exp-thinking DeepSeek · MIT	1444±9	4,628
44	3561	deepseek-v3.2 DeepSeek · MIT	1443±6	17,188
45	2875	deepseek-v3.1-terminus-thinking DeepSeek · MIT	1442±14	1,723
46	3663	deepseek-v3.2-thinking DeepSeek · MIT	1442±6	14,281
47	3663	glm-4.6 Z.ai · MIT	1442±5	18,852
48	3275	gemini-3.1-flash-lite-preview Google · Proprietary	1441±12	2,076
49	3768	grok-4-1-fast-reasoning xAI · Proprietary	1441±5	17,675
50	3475	gpt-4.5-preview-2025-02-27 OpenAI · Proprietary	1440±10	3,443
51	3769	o3-2025-04-16 OpenAI · Proprietary	1439±5	26,028
52	3675	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1439±9	5,764
53	3972	claude-haiku-4-5-20251001 Anthropic · Proprietary	1436±5	26,480
54	3775	deepseek-v3.1-thinking DeepSeek · MIT	1436±9	5,188
55	3879	kimi-k2-0905-preview Moonshot · Modified MIT	1434±8	5,616
56	4075	claude-opus-4-20250514 Anthropic · Proprietary	1434±5	19,463
57	3980	deepseek-r1-0528 DeepSeek · MIT	1433±8	7,148
58	3784	grok-4-fast-chat xAI · Proprietary	1433±11	3,179
59	3980	deepseek-v3.1 DeepSeek · MIT	1433±8	6,887
60	4280	glm-4.5 Z.ai · MIT	1432±6	11,268
61	4580	mistral-large-3 Mistral · Apache 2.0	1431±6	15,549
62	4582	kimi-k2-0711-preview Moonshot · Modified MIT	1430±6	12,470
63	4580	claude-sonnet-4-20250514-thinking-32k Anthropic · Proprietary	1430±6	15,870
64	4780	gpt-4.1-2025-04-14 OpenAI · Proprietary	1430±5	22,373
65	4880	mistral-medium-2508 Mistral · Proprietary	1429±4	34,753
66	3992	qwen3.5-27b Alibaba · Apache 2.0	1428±13	1,806
67	4589	minimax-m2.5 MiniMax · Modified MIT	1427±9	4,410
68	4394	ernie-5.0-preview-1022 Baidu · Proprietary	1425±12	2,466
69	4989	grok-3-preview-02-24 xAI · Proprietary	1425±6	10,954
70	4892	longcat-flash-chat Meituan · MIT	1425±8	5,619
71	4396	qwen3.5-122b-a10b Alibaba · Apache 2.0	1424±13	1,793
72	4596	deepseek-v3.1-terminus DeepSeek · MIT	1423±13	1,950
73	5692	qwen3-next-80b-a3b-instruct Alibaba · Apache 2.0	1421±6	11,784
74	5792	qwen3-235b-a22b-no-thinking Alibaba · Apache 2.0	1420±6	16,915
75	6492	grok-4-0709 xAI · Proprietary	1419±5	19,737
76	49100	qwen3.5-flash Alibaba · Proprietary	1419±12	2,402
77	6692	gemini-2.5-flash Google · Proprietary	1419±4	46,746
78	6594	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1418±5	17,328
79	5699	qwen3-235b-a22b-thinking-2507 Alibaba · Apache 2.0	1418±9	3,910
80	5699	qwen3-vl-235b-a22b-thinking Alibaba · Apache 2.0	1417±9	4,010
81	49103	amazon-nova-experimental-chat-12-10 Amazon · Proprietary	1417±13	1,868
82	5699	deepseek-r1 DeepSeek · MIT	1417±9	4,121
83	6499	o1-2024-12-17 OpenAI · Proprietary	1417±8	6,455
84	6696	claude-sonnet-4-20250514 Anthropic · Proprietary	1417±6	17,963
85	6696	claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary	1416±6	14,132
86	48108	hunyuan-vision-1.5-thinking Tencent · Proprietary	1416±17	1,090
87	66103	mimo-v2-flash (thinking) Xiaomi · MIT	1412±8	5,968
88	68101	mimo-v2-flash (non-thinking) Xiaomi · MIT	1412±6	11,678
89	68101	qwen3-coder-480b-a35b-instruct Alibaba · Apache 2.0	1412±6	11,897
90	68102	grok-4-fast-reasoning xAI · Proprietary	1412±6	9,749
91	66103	step-3.5-flash StepFun · Apache 2.0	1411±8	5,665
92	65110	qwen3.5-35b-a3b Alibaba · Apache 2.0	1410±13	1,875
93	74105	qwen3-30b-a3b-instruct-2507 Alibaba · Apache 2.0	1408±6	11,112
94	74107	minimax-m2.1-preview MiniMax · MIT	1407±7	9,083
95	76105	deepseek-v3-0324 DeepSeek · MIT	1407±5	18,943
96	80108	o4-mini-2025-04-16 OpenAI · Proprietary	1405±5	19,790
97	80110	mai-1-preview Microsoft AI · Proprietary	1403±7	8,007
98	84110	gpt-5-mini-high OpenAI · Proprietary	1401±6	12,700
99	80115	o3-mini-high OpenAI · Proprietary	1400±9	4,384
100	87113	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1400±6	16,599
101	76118	hunyuan-t1-20250711 Tencent · Proprietary	1399±13	1,981
102	88114	mistral-medium-2505 Mistral · Proprietary	1399±6	14,078
103	93114	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1396±4	27,604
104	91115	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1396±6	15,628
105	91118	o1-preview OpenAI · Proprietary	1395±8	8,494
106	85125	trinity-large Arcee AI · Apache 2.0	1395±12	2,272
107	93117	amazon-nova-experimental-chat-11-10 Amazon · Proprietary	1394±6	11,179
108	96121	qwen3-235b-a22b Alibaba · Apache 2.0	1391±6	10,687
109	94126	hunyuan-turbos-20250416 Tencent · Proprietary	1390±10	4,001
110	99121	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1390±5	24,904
111	99123	glm-4.5-air Z.ai · MIT	1389±6	14,809
112	100127	glm-4.7-flash Z.ai · MIT	1386±8	6,514
113	104127	qwen2.5-max Alibaba · Proprietary	1384±6	9,874
114	102129	qwen3-next-80b-a3b-thinking Alibaba · Apache 2.0	1384±8	6,705
115	105128	minimax-m1 MiniMax · Apache 2.0	1382±5	16,175
116	96139	glm-4.6v Z.ai · MIT	1382±15	1,489
117	107132	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1380±6	14,814
118	110136	grok-3-mini-high xAI · Proprietary	1376±7	7,714
119	107142	step-3 StepFun · Apache 2.0	1375±11	2,993
120	107145	glm-4.5v Z.ai · MIT	1374±12	2,383
121	99151	llama-3.1-nemotron-ultra-253b-v1 Nvidia · Nvidia Open Model	1373±21	713
122	111142	amazon-nova-experimental-chat-10-20 Amazon · Proprietary	1373±8	5,873
123	109145	intellect-3 Prime Intellect · MIT	1373±11	2,730
124	112142	mistral-small-2506 Mistral · Apache 2.0	1372±7	7,985
125	116142	o3-mini OpenAI · Proprietary	1370±5	20,445
126	116145	grok-3-mini-beta xAI · Proprietary	1369±7	9,910
127	114148	minimax-m2 MiniMax · Apache 2.0	1367±10	3,616
128	104158	hunyuan-turbos-20250226 Tencent · Proprietary	1367±23	531
129	110152	qwen3-32b Alibaba · Apache 2.0	1367±16	1,211
130	115148	ling-flash-2.0 Ant Group · MIT	1367±10	3,420
131	117145	command-a-03-2025 Cohere · CC-BY-NC-4.0	1366±5	23,922
132	117147	gemma-3-27b-it Google · Gemma	1364±5	18,131
133	118148	gpt-oss-120b OpenAI · Apache 2.0	1362±6	14,719
134	116158	nvidia-llama-3.3-nemotron-super-49b-v1.5 Nvidia · Nvidia Open	1360±15	1,458
135	119150	gemini-2.0-flash-001 Google · Proprietary	1360±5	14,421
136	118151	nova-2-lite Amazon · Proprietary	1360±8	6,405
137	109170	llama-3.3-nemotron-49b-super-v1 Nvidia · Nvidia	1360±24	510
138	119150	o1-mini OpenAI · Proprietary	1360±6	13,899
139	117158	amazon-nova-experimental-chat-10-09 Amazon · Proprietary	1358±15	1,430
140	123151	claude-3-5-sonnet-20240620 Anthropic · Proprietary	1358±6	23,252
141	123152	qwq-32b Alibaba · Apache 2.0	1356±6	8,997
142	123159	gpt-5-nano-high OpenAI · Proprietary	1353±10	3,815
143	119167	qwen-plus-0125 Alibaba · Proprietary	1352±14	1,483
144	127158	olmo-3.1-32b-instruct Ai2 · Apache 2.0	1351±8	6,508
145	127165	ring-flash-2.0 Ant Group · MIT	1350±10	3,582
146	128161	deepseek-v3 DeepSeek · DeepSeek	1350±8	5,407
147	131158	gemini-1.5-pro-002 Google · Proprietary	1349±6	14,848
148	117184	hunyuan-turbo-0110 Tencent · Proprietary	1348±23	496
149	131164	gemini-2.0-flash-lite-preview-02-05 Google · Proprietary	1347±7	6,187
150	136165	qwen3-30b-a3b Alibaba · Apache 2.0	1346±6	10,934
151	138167	claude-3-5-haiku-20241022 Anthropic · Proprietary	1342±5	24,067
152	138171	yi-lightning 01 AI · Proprietary	1340±8	6,961
153	138171	llama-3.1-405b-instruct-bf16 Meta · Llama 3.1 Community	1340±6	10,651
154	118196	molmo-2-8b Ai2 · Apache 2.0	1339±28	444
155	133185	step-2-16k-exp-202412 StepFun · Proprietary	1338±15	1,220
156	143172	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1337±6	16,262
157	144175	gpt-4o-2024-05-13 OpenAI · Proprietary	1336±5	32,415
158	145178	llama-3.1-405b-instruct-fp8 Meta · Llama 3.1 Community	1334±6	16,230
159	144184	step-1o-turbo-202506 StepFun · Proprietary	1333±10	3,885
160	146182	athene-v2-chat NexusFlow · NexusFlow	1332±7	6,516
161	138190	gpt-4.1-nano-2025-04-14 OpenAI · Proprietary	1332±14	1,670
162	148185	magistral-medium-2506 Mistral · Proprietary	1331±8	5,785
163	138195	gemma-3-12b-it Google · Gemma	1330±18	976
164	138196	hunyuan-large-2025-02-10 Tencent · Proprietary	1330±19	890
165	150186	nvidia-nemotron-3-nano-30b-a3b-bf16 Nvidia · NVIDIA Open Model	1329±7	8,096
166	151185	llama-4-scout-17b-16e-instruct Meta · Llama	1328±6	13,247
167	145195	deepseek-v2.5-1210 DeepSeek · DeepSeek	1328±13	1,791
168	154186	claude-3-opus-20240229 Anthropic · Proprietary	1327±5	55,076
169	150195	qwen2.5-plus-1127 Alibaba · Proprietary	1326±11	2,670
170	154188	gemini-1.5-pro-001 Google · Proprietary	1325±6	22,511
171	153189	gpt-4o-2024-08-06 OpenAI · Proprietary	1325±6	12,657
172	150195	olmo-3-32b-think Ai2 · Apache 2.0	1325±11	2,985
173	155188	grok-2-2024-08-13 xAI · Proprietary	1325±6	17,278
174	148197	glm-4-plus-0111 Zhipu · Proprietary	1325±14	1,468
175	154192	gemini-advanced-0514 Google · Proprietary	1324±7	14,098
176	145201	mercury Inception AI · Proprietary	1322±19	996
177	155195	gpt-oss-20b OpenAI · Apache 2.0	1320±9	4,811
178	156195	deepseek-v2.5 DeepSeek · DeepSeek	1320±8	6,872
179	157195	llama-3.3-70b-instruct Meta · Llama-3.3	1320±5	17,221
180	156195	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1319±6	14,904
181	157195	mistral-large-2407 Mistral · Mistral Research	1318±6	12,681
182	156196	glm-4-plus Zhipu AI · Proprietary	1318±8	7,069
183	156200	qwen-max-0919 Alibaba · Qwen	1318±9	4,445
184	159197	qwen2.5-72b-instruct Alibaba · Qwen	1316±6	10,543
185	164198	gpt-4-turbo-2024-04-09 OpenAI · Proprietary	1315±6	28,318
186	164201	gemma-3n-e4b-it Google · Gemma	1313±7	8,719
187	167201	mistral-large-2411 Mistral · MRL	1312±7	6,952
188	166202	athene-70b-0725 NexusFlow · CC-BY-NC-4.0	1311±9	5,449
189	169201	gpt-4o-mini-2024-07-18 OpenAI · Proprietary	1310±5	18,294
190	169201	gpt-4-1106-preview OpenAI · Proprietary	1310±6	26,243
191	155209	hunyuan-standard-2025-02-10 Tencent · Proprietary	1310±19	873
192	162204	llama-3.1-nemotron-70b-instruct Nvidia · Llama 3.1	1309±13	1,953
193	169204	olmo-3.1-32b-think Ai2 · Apache 2.0	1306±10	4,343
194	178203	gpt-4-0125-preview OpenAI · Proprietary	1305±6	25,574
195	168209	hunyuan-large-vision Tencent · Proprietary	1304±13	2,238
196	184203	grok-2-mini-2024-08-13 xAI · Proprietary	1303±6	14,212
197	181205	gpt-4-0314 OpenAI · Proprietary	1303±8	13,937
198	168214	qwen2.5-coder-32b-instruct Alibaba · Apache 2.0	1302±15	1,386
199	185205	gemini-1.5-flash-002 Google · Proprietary	1301±7	9,262
200	184205	amazon-nova-pro-v1.0 Amazon · Proprietary	1301±7	6,301
201	183214	ibm-granite-h-small IBM · Apache 2.0	1299±11	2,955
202	190209	llama-3.1-70b-instruct Meta · Llama 3.1 Community	1297±6	14,982
203	198219	gemini-1.5-flash-001 Google · Proprietary	1286±6	18,228
204	195223	deepseek-coder-v2 DeepSeek · DeepSeek License	1286±10	4,439
205	198219	gpt-4-0613 OpenAI · Proprietary	1286±7	23,040
206	198224	mistral-small-24b-instruct-2501 Mistral · Apache 2.0	1284±10	3,566
207	191227	gemma-3-4b-it Google · Gemma	1282±17	1,093
208	198224	jamba-1.5-large AI21 Labs · Jamba Open	1282±12	2,372
209	203224	gemma-2-27b-it Google · Gemma license	1280±5	20,496
210	203224	claude-3-sonnet-20240229 Anthropic · Proprietary	1280±6	30,724
211	193230	llama-3.1-nemotron-51b-instruct Nvidia · Llama 3.1	1279±17	1,002
212	201226	reka-core-20240904 Reka AI · Proprietary	1279±12	2,144
213	201224	nemotron-4-340b-instruct Nvidia · NVIDIA Open Model	1279±9	5,577
214	203224	llama-3-70b-instruct Meta · Llama 3 Community	1277±6	45,956
215	203225	phi-4 Microsoft · MIT	1276±8	5,750
216	201227	glm-4-0520 Zhipu AI · Proprietary	1276±11	2,970
217	201232	llama-3.1-tulu-3-70b Ai2 · Llama 3.1	1272±19	778
218	205230	qwen2-72b-instruct Alibaba · Qianwen LICENSE	1271±7	10,780
219	203231	gemma-2-9b-it-simpo Princeton · MIT	1271±11	2,552
220	205230	amazon-nova-lite-v1.0 Amazon · Proprietary	1270±8	4,913
221	201234	hunyuan-standard-256k Tencent · Proprietary	1269±21	700
222	205230	c4ai-aya-expanse-32b Cohere · CC-BY-NC-4.0	1269±8	7,236
223	206232	reka-flash-20240904 Reka AI · Proprietary	1265±11	2,288
224	213231	claude-3-haiku-20240307 Anthropic · Proprietary	1263±6	33,698
225	214233	mistral-large-2402 Mistral · Proprietary	1259±7	17,188
226	205244	olmo-2-0325-32b-instruct Ai2 · Apache-2.0	1259±20	789
227	212235	command-r-plus-08-2024 Cohere · CC-BY-NC-4.0	1259±11	2,822
228	216234	gemini-1.5-flash-8b-001 Google · Proprietary	1257±7	9,654
229	220234	gemma-2-9b-it Google · Gemma license	1255±6	14,756
230	216239	command-r-08-2024 Cohere · CC-BY-NC-4.0	1254±10	2,976
231	216248	ministral-8b-2410 Mistral · MRL	1249±15	1,257
232	222240	command-r-plus Cohere · CC-BY-NC-4.0	1249±6	22,394
233	224247	qwen1.5-110b-chat Alibaba · Qianwen LICENSE	1244±9	7,695
234	225247	amazon-nova-micro-v1.0 Amazon · Proprietary	1243±8	4,859
235	229248	mixtral-8x22b-instruct-v0.1 Mistral · Apache 2.0	1241±7	14,708
236	229251	qwen1.5-72b-chat Alibaba · Qianwen LICENSE	1237±8	10,851
237	229254	jamba-1.5-mini AI21 Labs · Jamba Open	1235±12	2,349
238	231253	mistral-medium Mistral · Proprietary	1233±9	8,651
239	230255	reka-flash-21b-20240226-online Reka AI · Proprietary	1233±11	4,506
240	231255	reka-flash-21b-20240226 Reka AI · Proprietary	1231±9	7,447
241	231257	gemini-pro-dev-api Google · Proprietary	1229±11	4,515
242	228259	granite-3.1-8b-instruct IBM · Apache 2.0	1228±20	798
243	232257	c4ai-aya-expanse-8b Cohere · CC-BY-NC-4.0	1228±11	2,576
244	229259	gemini-pro Google · Proprietary	1227±18	1,407
245	236256	gpt-3.5-turbo-0125 OpenAI · Proprietary	1226±7	18,543
246	232259	gpt-3.5-turbo-1106 OpenAI · Proprietary	1225±13	3,845
247	234259	internlm2_5-20b-chat InternLM · Other	1223±11	2,597
248	236258	yi-1.5-34b-chat 01 AI · Apache-2.0	1223±8	6,679
249	231262	llama-3.1-tulu-3-8b Ai2 · Llama 3.1	1221±20	726
250	237257	llama-3.1-8b-instruct Meta · Llama 3.1 Community	1221±6	13,534
251	237259	qwen1.5-32b-chat Alibaba · Qianwen LICENSE	1218±9	6,072
252	232263	granite-3.1-2b-instruct IBM · Apache 2.0	1217±19	832
253	239259	llama-3-8b-instruct Meta · Llama 3 Community	1217±6	30,218
254	238260	dbrx-instruct-preview Databricks · DBRX LICENSE	1214±9	8,865
255	236263	zephyr-orpo-141b-A35b-v0.1 HuggingFace · Apache 2.0	1213±17	1,241
256	241260	command-r Cohere · CC-BY-NC-4.0	1212±7	15,125
257	242261	phi-3-medium-4k-instruct Microsoft · MIT	1210±8	6,822
258	245262	mixtral-8x7b-instruct-v0.1 Mistral · Apache 2.0	1208±7	19,543
259	244274	granite-3.0-8b-instruct IBM · Apache 2.0	1200±15	1,669
260	252273	qwen1.5-14b-chat Alibaba · Qianwen LICENSE	1198±11	4,910
261	254277	starling-lm-7b-beta Nexusflow · Apache-2.0	1192±11	4,525
262	257276	gemma-1.1-7b-it Google · Gemma license	1190±9	6,987
263	259280	phi-3-small-8k-instruct Microsoft · MIT	1186±10	5,229
264	255283	tulu-2-dpo-70b AllenAI/UW · AI2 ImpACT Low-risk	1185±17	1,419
265	259281	openchat-3.5-0106 OpenChat · Apache-2.0	1184±11	3,435
266	259281	snowflake-arctic-instruct Snowflake · Apache 2.0	1183±9	9,593
267	259280	gemma-2-2b-it Google · Gemma license	1183±6	12,325
268	259283	yi-34b-chat 01 AI · Yi License	1182±11	3,838
269	259288	openhermes-2.5-mistral-7b NousResearch · Apache-2.0	1178±17	1,139
270	259289	granite-3.0-2b-instruct IBM · Apache 2.0	1174±15	1,739
271	259292	openchat-3.5 OpenChat · Apache-2.0	1173±16	1,663
272	261288	phi-3-mini-4k-instruct-june-2024 Microsoft · MIT	1173±11	3,155
273	259292	deepseek-llm-67b-chat DeepSeek · DeepSeek License	1173±19	1,120
274	261292	wizardlm-70b Microsoft · Llama 2 Community	1170±15	1,752
275	260293	qwq-32b-preview Alibaba · Apache 2.0	1167±19	852
276	263292	llama-3.2-3b-instruct Meta · Llama 3.2	1166±13	2,216
277	263292	starling-lm-7b-alpha UC Berkeley · CC-BY-NC-4.0	1165±13	2,471
278	267292	vicuna-33b LMSYS · Non-commercial	1162±10	5,072
279	269293	llama-2-70b-chat Meta · Llama 2 Community	1157±8	9,650
280	259304	codellama-70b-instruct Meta · Llama 2 Community	1157±31	306
281	265299	solar-10.7b-instruct-v1.0 Upstage AI · CC-BY-NC-4.0	1155±20	932
282	262302	mpt-30b-chat MosaicML · CC-BY-NC-SA-4.0	1155±27	434
283	269297	mistral-7b-instruct-v0.2 Mistral · Apache-2.0	1154±10	5,149
284	263305	dolphin-2.2.1-mistral-7b Cognitive Computations · Apache-2.0	1153±28	359
285	269299	gemma-7b-it Google · Gemma license	1151±14	2,267
286	271297	phi-3-mini-4k-instruct Microsoft · MIT	1151±10	5,872
287	267305	smollm2-1.7b-instruct HuggingFace · Apache 2.0	1148±25	572
288	269299	qwen1.5-7b-chat Alibaba · Qianwen LICENSE	1148±16	1,333
289	272302	palm-2 Google · Proprietary	1143±16	1,605
290	269305	llama2-70b-steerlm-chat Nvidia · Llama 2 Community	1143±21	787
291	272306	qwen-14b-chat Alibaba · Qianwen LICENSE	1139±19	1,006
292	280304	llama-2-13b-chat Meta · Llama 2 Community	1136±10	4,473
293	280305	gemma-1.1-2b-it Google · Gemma license	1135±12	3,183
294	280307	codellama-34b-instruct Meta · Llama 2 Community	1130±15	1,540
295	282307	vicuna-13b LMSYS · Llama 2 Community	1129±11	3,971
296	282307	phi-3-mini-128k-instruct Microsoft · MIT	1128±11	6,170
297	280307	nous-hermes-2-mixtral-8x7b-dpo NousResearch · Apache-2.0	1127±18	1,066
298	272310	falcon-180b-chat TII · Falcon-180B TII License	1124±35	231
299	278310	zephyr-7b-alpha HuggingFace · MIT	1120±30	333
300	285309	zephyr-7b-beta HuggingFace · MIT	1114±14	2,219
301	289309	llama-3.2-1b-instruct Meta · Llama 3.2	1112±13	2,247
302	285309	wizardlm-13b Microsoft · Llama 2 Community	1112±17	1,278
303	287309	mistral-7b-instruct Mistral · Apache 2.0	1111±15	1,917
304	287310	gemma-2b-it Google · Gemma license	1109±18	1,191
305	293310	stripedhyena-nous-7b Together AI · Apache 2.0	1105±17	1,237
306	285312	guanaco-33b UW · Non-commercial	1102±26	517
307	294310	vicuna-7b LMSYS · Llama 2 Community	1102±17	1,258
308	298310	llama-2-7b-chat Meta · Llama 2 Community	1094±11	3,289
309	298311	qwen1.5-4b-chat Alibaba · Qianwen LICENSE	1092±14	2,074
310	308315	olmo-7b-instruct Ai2 · Apache-2.0	1066±17	1,462
311	302317	gpt4all-13b-snoozy Nomic AI · Non-commercial	1061±30	347
312	309316	chatglm3-6b Tsinghua · Apache-2.0	1057±20	999
313	310319	koala-13b UC Berkeley · Non-commercial	1031±19	1,250
314	310319	mpt-7b-chat MosaicML · CC-BY-NC-SA-4.0	1029±22	714
315	310319	chatglm2-6b Tsinghua · Apache-2.0	1025±27	490
316	311319	oasst-pythia-12b OpenAssistant · Apache 2.0	1019±19	1,153
317	312320	RWKV-4-Raven-14B RWKV · Apache 2.0	1014±21	876
318	313320	alpaca-13b Stanford · Non-commercial	1005±20	1,057
319	313320	chatglm-6b Tsinghua · Non-commercial	997±22	848
320	317323	dolly-v2-12b Databricks · MIT	969±25	615
321	320323	stablelm-tuned-alpha-7b Stability AI · CC-BY-NC-SA-4.0	940±25	575
322	320323	fastchat-t5-3b LMSYS · Apache 2.0	935±22	797
323	320323	llama-13b Meta · Non-commercial	914±31	430

Text Arena | Hard Prompts

Default Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

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