Text Arena

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

Last Updated

Dec 23, 2025

Total Votes

440,128

Total Models

278

/

Style Control

	Rank Spread
1	1◄─►25	gemini-3-flash	1496	±34	306	Google	Proprietary
2	1◄─►11	gemini-3-pro	1492	±18	1,185	Google	Proprietary
3	1◄─►12	gpt-5.1-high	1491	±20	887	OpenAI	Proprietary
4	1◄─►27	gpt-5.2-high	1489	±31	360	OpenAI	Proprietary
5	1◄─►27	claude-opus-4-5-20251101	1483	±23	677	Anthropic	Proprietary
6	1◄─►29	claude-opus-4-5-20251101-thinking-32k	1480	±23	656	Anthropic	Proprietary
7	1◄─►25	claude-sonnet-4-5-20250929-thinking-32k	1477	±15	1,534	Anthropic	Proprietary
8	1◄─►45	gemini-3-flash (thinking-minimal)	1473	±32	320	Google	Proprietary
9	1◄─►42	grok-4.1-thinking	1462	±19	1,031	xAI	Proprietary
10	1◄─►42	claude-sonnet-4-5-20250929	1460	±16	1,422	Anthropic	Proprietary
11	3◄─►38	o3-2025-04-16	1459	±10	3,674	OpenAI	Proprietary
12	3◄─►38	gemini-2.5-pro	1458	±9	4,592	Google	Proprietary
13	3◄─►43	claude-opus-4-1-20250805-thinking-16k	1456	±12	2,403	Anthropic	Proprietary
14	1◄─►57	deepseek-v3.1-thinking	1453	±24	576	DeepSeek	MIT
15	3◄─►51	kimi-k2-thinking-turbo	1451	±19	991	Moonshot	Modified MIT
16	3◄─►51	qwen3-max-preview	1449	±16	1,330	Alibaba	Proprietary
17	5◄─►50	gpt-5-high	1447	±14	1,860	OpenAI	Proprietary
18	5◄─►53	glm-4.6	1446	±16	1,417	Z.ai	MIT
19	3◄─►58	gpt-5.1	1446	±18	1,049	OpenAI	Proprietary
20	8◄─►49	claude-opus-4-1-20250805	1446	±11	3,243	Anthropic	Proprietary
21	8◄─►53	grok-4-0709	1443	±13	2,258	xAI	Proprietary
22	2◄─►74	grok-4-fast-chat	1442	±31	328	xAI	Proprietary
23	7◄─►61	grok-4.1	1441	±17	1,223	xAI	Proprietary
24	3◄─►69	deepseek-v3.2	1441	±24	596	DeepSeek AI	MIT
25	3◄─►72	deepseek-v3.2-thinking	1440	±27	463	DeepSeek AI	MIT
26	3◄─►77	deepseek-v3.2-exp-thinking	1437	±30	382	DeepSeek AI	MIT
27	3◄─►76	ernie-5.0-preview-1103	1437	±27	460	Baidu	Proprietary
28	10◄─►59	qwen3-235b-a22b-instruct-2507	1437	±11	2,929	Alibaba	Apache 2.0
29	8◄─►68	gemini-2.5-flash-preview-09-2025	1435	±15	1,619	Google	Proprietary
30	7◄─►76	qwen3-235b-a22b-thinking-2507	1434	±24	518	Alibaba	Apache 2.0
31	3◄─►82	qwen3-vl-235b-a22b-thinking	1433	±29	372	Alibaba	Apache 2.0
32	8◄─►77	longcat-flash-chat	1431	±24	547	Meituan	MIT
33	3◄─►85	qwen3-32b	1430	±32	283	Alibaba	Apache 2.0
34	10◄─►72	glm-4.5	1429	±17	1,301	Z.ai	MIT
35	10◄─►75	qwen3-next-80b-a3b-instruct	1428	±18	1,049	Alibaba	Apache 2.0
36	3◄─►91	ernie-5.0-preview-1203	1428	±40	213	Baidu	Proprietary
37	8◄─►82	kimi-k2-0905-preview	1428	±23	637	Moonshot	Modified MIT
38	13◄─►72	claude-haiku-4-5-20251001	1428	±15	1,513	Anthropic	Proprietary
39	8◄─►82	deepseek-v3.2-exp	1426	±23	663	DeepSeek AI	MIT
40	14◄─►71	minimax-m1	1426	±13	2,128	MiniMax	Apache 2.0
41	14◄─►71	claude-opus-4-20250514-thinking-16k	1426	±12	2,186	Anthropic	Proprietary
42	8◄─►85	qwen3-max-2025-09-23	1425	±26	492	Alibaba	Proprietary
43	13◄─►82	deepseek-v3.1	1424	±19	853	DeepSeek	MIT
44	12◄─►85	grok-4-1-fast-reasoning	1421	±22	707	xAI	Proprietary
45	21◄─►74	gemini-2.5-flash	1420	±9	4,868	Google	Proprietary
46	15◄─►82	gpt-4.5-preview-2025-02-27	1419	±15	1,288	OpenAI	Proprietary
47	14◄─►85	grok-4-fast-reasoning	1418	±19	947	xAI	Proprietary
48	20◄─►77	o1-2024-12-17	1418	±11	2,659	OpenAI	Proprietary
49	18◄─►82	claude-sonnet-4-20250514-thinking-32k	1418	±13	2,047	Anthropic	Proprietary
50	18◄─►82	o3-mini-high	1417	±14	1,716	OpenAI	Proprietary
51	22◄─►80	o4-mini-2025-04-16	1416	±11	2,919	OpenAI	Proprietary
52	20◄─►85	deepseek-r1	1415	±14	1,524	DeepSeek	MIT
53	16◄─►85	deepseek-r1-0528	1415	±18	1,025	DeepSeek	MIT
54	8◄─►103	intellect-3	1414	±35	261	Prime Intellect	MIT
55	23◄─►84	mistral-medium-2508	1413	±12	2,633	Mistral	Proprietary
56	20◄─►85	gpt-5-mini-high	1413	±16	1,305	OpenAI	Proprietary
57	14◄─►92	qwen3-vl-235b-a22b-instruct	1412	±25	502	Alibaba	Apache 2.0
58	24◄─►83	chatgpt-4o-latest-20250326	1412	±9	4,383	OpenAI	Proprietary
59	8◄─►105	amazon-nova-experimental-chat-11-10	1411	±42	173	Amazon	Proprietary
60	24◄─►85	claude-opus-4-20250514	1409	±11	2,848	Anthropic	Proprietary
61	24◄─►85	qwen3-235b-a22b-no-thinking	1409	±12	2,459	Alibaba	Apache 2.0
62	24◄─►86	gpt-5-chat	1409	±15	1,614	OpenAI	Proprietary
63	24◄─►86	qwen3-235b-a22b	1408	±14	1,590	Alibaba	Apache 2.0
64	24◄─►90	qwen3-30b-a3b-instruct-2507	1407	±16	1,254	Alibaba	Apache 2.0
65	10◄─►105	nvidia-llama-3.3-nemotron-super-49b-v1.5	1407	±39	192	Nvidia	Nvidia Open
66	20◄─►103	mistral-large-3	1403	±26	515	Mistral	Apache 2.0
67	24◄─►98	mai-1-preview	1403	±20	830	Microsoft AI	Proprietary
68	33◄─►90	o1-preview	1401	±10	3,885	OpenAI	Proprietary
69	34◄─►92	grok-3-preview-02-24	1399	±11	2,599	xAI	Proprietary
70	39◄─►91	o3-mini	1397	±9	4,565	OpenAI	Proprietary
71	25◄─►105	qwen3-next-80b-a3b-thinking	1396	±22	669	Alibaba	Apache 2.0
72	31◄─►102	glm-4.5-air	1396	±15	1,460	Z.ai	MIT
73	40◄─►98	claude-3-7-sonnet-20250219-thinking-32k	1394	±11	2,706	Anthropic	Proprietary
74	39◄─►98	claude-sonnet-4-20250514	1394	±12	2,527	Anthropic	Proprietary
75	26◄─►105	amazon-nova-experimental-chat-10-20	1393	±24	604	Amazon	Proprietary
76	39◄─►103	gpt-oss-120b	1391	±15	1,577	OpenAI	Apache 2.0
77	40◄─►103	kimi-k2-0711-preview	1391	±14	1,657	Moonshot	Modified MIT
78	47◄─►105	qwen3-coder-480b-a35b-instruct	1388	±15	1,465	Alibaba	Apache 2.0
79	23◄─►115	hunyuan-t1-20250711	1387	±38	229	Tencent	Proprietary
80	26◄─►114	step-3	1384	±33	306	StepFun	Apache 2.0
81	49◄─►107	grok-3-mini-high	1383	±18	1,038	xAI	Proprietary
82	64◄─►105	o1-mini	1380	±8	6,347	OpenAI	Proprietary
83	60◄─►107	qwen3-30b-a3b	1378	±14	1,663	Alibaba	Apache 2.0
84	60◄─►108	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1378	±15	1,633	Google	Proprietary
85	28◄─►119	minimax-m2	1378	±35	287	MiniMax	Apache 2.0
86	31◄─►119	nvidia-nemotron-3-nano-30b-a3b-bf16	1376	±35	284	Nvidia	NVIDIA Open Model
87	66◄─►107	qwen2.5-max	1375	±10	3,066	Alibaba	Proprietary
88	66◄─►107	gpt-4.1-2025-04-14	1375	±10	3,310	OpenAI	Proprietary
89	66◄─►109	gemini-2.5-flash-lite-preview-06-17-thinking	1374	±13	2,111	Google	Proprietary
90	48◄─►119	ring-flash-2.0	1371	±30	364	Ant Group	MIT
91	69◄─►110	deepseek-v3-0324	1371	±11	3,097	DeepSeek	MIT
92	36◄─►126	llama-3.3-nemotron-49b-super-v1	1371	±37	208	Nvidia	Nvidia
93	70◄─►111	gpt-4.1-mini-2025-04-14	1369	±11	2,613	OpenAI	Proprietary
94	69◄─►112	grok-3-mini-beta	1368	±14	1,610	xAI	Proprietary
95	69◄─►113	qwq-32b	1367	±14	1,669	Alibaba	Apache 2.0
96	58◄─►122	ling-flash-2.0	1367	±29	380	Ant Group	MIT
97	74◄─►111	gemini-2.0-flash-001	1366	±9	3,937	Google	Proprietary
98	60◄─►124	gpt-5-nano-high	1364	±28	442	OpenAI	Proprietary
99	74◄─►112	claude-3-7-sonnet-20250219	1364	±10	3,360	Anthropic	Proprietary
100	66◄─►119	hunyuan-turbos-20250416	1364	±20	844	Tencent	Proprietary
101	69◄─►119	mistral-small-2506	1363	±18	1,047	Mistral	Apache 2.0
102	66◄─►126	nova-2-lite	1360	±26	510	Amazon	Proprietary
103	80◄─►113	claude-3-5-sonnet-20241022	1359	±6	8,832	Anthropic	Proprietary
104	84◄─►117	gemini-1.5-pro-002	1356	±7	6,532	Google	Proprietary
105	80◄─►119	mistral-medium-2505	1356	±12	2,373	Mistral	Proprietary
106	66◄─►134	gemma-3-12b-it	1353	±30	333	Google	Gemma
107	60◄─►143	olmo-3-32b-think	1353	±39	206	Allen AI	Apache 2.0
108	62◄─►141	glm-4.5v	1352	±37	238	Z.ai	MIT
109	91◄─►126	gemma-3-27b-it	1344	±10	3,388	Google	Gemma
110	96◄─►126	claude-3-5-sonnet-20240620	1341	±7	10,072	Anthropic	Proprietary
111	93◄─►128	gemini-2.0-flash-lite-preview-02-05	1341	±11	2,421	Google	Proprietary
112	86◄─►139	qwen-plus-0125	1340	±21	631	Alibaba	Proprietary
113	85◄─►139	step-1o-turbo-202506	1340	±22	698	StepFun	Proprietary
114	87◄─►144	gpt-oss-20b	1335	±23	616	OpenAI	Apache 2.0
115	102◄─►136	command-a-03-2025	1330	±9	3,842	Cohere	CC-BY-NC-4.0
116	89◄─►156	hunyuan-large-2025-02-10	1329	±26	432	Tencent	Proprietary
117	94◄─►155	step-2-16k-exp-202412	1328	±22	546	StepFun	Proprietary
118	104◄─►141	athene-v2-chat	1326	±10	2,951	NexusFlow	NexusFlow
119	103◄─►142	llama-4-maverick-17b-128e-instruct	1325	±11	2,762	Meta	Llama 4
120	104◄─►144	deepseek-v3	1323	±11	2,340	DeepSeek	DeepSeek
121	103◄─►154	qwen2.5-plus-1127	1323	±14	1,272	Alibaba	Proprietary
122	108◄─►144	yi-lightning	1322	±10	3,216	01 AI	Proprietary
123	95◄─►163	hunyuan-large-vision	1322	±27	405	Tencent	Proprietary
124	109◄─►141	llama-3.1-405b-instruct-fp8	1322	±7	7,259	Meta	Llama 3.1 Community
125	109◄─►144	llama-3.1-405b-instruct-bf16	1321	±8	4,394	Meta	Llama 3.1 Community
126	108◄─►155	llama-4-scout-17b-16e-instruct	1320	±13	1,950	Meta	Llama
127	109◄─►154	gemini-advanced-0514	1318	±10	5,805	Google	Proprietary
128	109◄─►154	gpt-4o-2024-08-06	1316	±8	5,813	OpenAI	Proprietary
129	95◄─►171	hunyuan-turbo-0110	1316	±34	219	Tencent	Proprietary
130	110◄─►155	qwen2.5-72b-instruct	1314	±8	4,583	Alibaba	Qwen
131	102◄─►166	hunyuan-standard-2025-02-10	1314	±26	440	Tencent	Proprietary
132	111◄─►155	gpt-4o-2024-05-13	1314	±7	13,353	OpenAI	Proprietary
133	111◄─►155	gpt-4-1106-preview	1312	±8	11,583	OpenAI	Proprietary
134	111◄─►155	gemini-1.5-pro-001	1312	±8	9,370	Google	Proprietary
135	113◄─►155	claude-3-opus-20240229	1312	±6	23,110	Anthropic	Proprietary
136	96◄─►175	ibm-granite-h-small	1310	±35	285	IBM	Apache 2.0
137	109◄─►167	glm-4-plus-0111	1308	±21	640	Zhipu	Proprietary
138	102◄─►175	hunyuan-turbos-20250226	1307	±32	226	Tencent	Proprietary
139	118◄─►160	llama-3.3-70b-instruct	1305	±8	5,373	Meta	Llama-3.3
140	117◄─►162	gemini-1.5-flash-002	1305	±9	4,123	Google	Proprietary
141	113◄─►165	qwen-max-0919	1305	±13	1,808	Alibaba	Qwen
142	116◄─►163	glm-4-plus	1304	±10	2,999	Zhipu AI	Proprietary
143	110◄─►170	llama-3.1-nemotron-70b-instruct	1304	±18	875	Nvidia	Llama 3.1
144	122◄─►163	grok-2-2024-08-13	1303	±7	7,633	xAI	Proprietary
145	109◄─►173	magistral-medium-2506	1303	±25	629	Mistral	Proprietary
146	122◄─►163	gpt-4-turbo-2024-04-09	1302	±7	11,878	OpenAI	Proprietary
147	122◄─►164	mistral-large-2407	1302	±8	5,769	Mistral	Mistral Research
148	122◄─►163	gpt-4-0125-preview	1301	±8	10,895	OpenAI	Proprietary
149	122◄─►165	claude-3-5-haiku-20241022	1301	±8	5,947	Anthropic	Proprietary
150	122◄─►165	deepseek-v2.5	1300	±10	3,057	DeepSeek	DeepSeek
151	122◄─►170	mistral-small-3.1-24b-instruct-2503	1297	±13	2,071	Mistral	Apache 2.0
152	122◄─►173	gemma-3n-e4b-it	1294	±15	1,541	Google	Gemma
153	122◄─►175	deepseek-v2.5-1210	1292	±18	895	DeepSeek	DeepSeek
154	134◄─►171	gpt-4o-mini-2024-07-18	1290	±7	8,023	OpenAI	Proprietary
155	133◄─►173	gpt-4-0314	1289	±10	6,147	OpenAI	Proprietary
156	135◄─►171	grok-2-mini-2024-08-13	1289	±7	6,275	xAI	Proprietary
157	133◄─►173	amazon-nova-pro-v1.0	1288	±10	2,670	Amazon	Proprietary
158	134◄─►173	mistral-large-2411	1287	±10	3,050	Mistral	MRL
159	122◄─►183	gpt-4.1-nano-2025-04-14	1285	±24	533	OpenAI	Proprietary
160	141◄─►177	phi-4	1282	±11	2,366	Microsoft	MIT
161	146◄─►177	llama-3.1-70b-instruct	1279	±7	6,548	Meta	Llama 3.1 Community
162	133◄─►188	llama-3.1-nemotron-51b-instruct	1278	±25	422	Nvidia	Llama 3.1
163	146◄─►180	qwen2-72b-instruct	1277	±9	4,246	Alibaba	Qianwen LICENSE
164	125◄─►191	gemma-3-4b-it	1277	±30	364	Google	Gemma
165	132◄─►191	llama-3.1-tulu-3-70b	1277	±27	350	Ai2	Llama 3.1
166	144◄─►185	mistral-small-24b-instruct-2501	1274	±14	1,451	Mistral	Apache 2.0
167	151◄─►180	gemini-1.5-flash-001	1273	±8	7,345	Google	Proprietary
168	140◄─►188	qwen2.5-coder-32b-instruct	1273	±21	620	Alibaba	Apache 2.0
169	146◄─►185	deepseek-coder-v2	1272	±14	1,672	DeepSeek AI	DeepSeek License
170	145◄─►186	reka-core-20240904	1272	±15	1,044	Reka AI	Proprietary
171	133◄─►198	hunyuan-standard-256k	1271	±31	292	Tencent	Proprietary
172	151◄─►185	athene-70b-0725	1270	±11	2,570	NexusFlow	CC-BY-NC-4.0
173	156◄─►183	gpt-4-0613	1269	±8	9,894	OpenAI	Proprietary
174	148◄─►190	glm-4-0520	1267	±16	1,077	Zhipu AI	Proprietary
175	161◄─►187	claude-3-sonnet-20240229	1263	±8	12,508	Anthropic	Proprietary
176	161◄─►186	gemma-2-27b-it	1263	±7	8,902	Google	Gemma license
177	159◄─►191	amazon-nova-lite-v1.0	1262	±11	2,188	Amazon	Proprietary
178	161◄─►187	llama-3-70b-instruct	1262	±7	18,859	Meta	Llama 3 Community
179	159◄─►191	nemotron-4-340b-instruct	1261	±12	2,149	Nvidia	NVIDIA Open Model
180	156◄─►193	jamba-1.5-large	1260	±17	963	AI21 Labs	Jamba Open
181	163◄─►191	gemini-1.5-flash-8b-001	1255	±9	4,179	Google	Proprietary
182	163◄─►203	command-r-plus-08-2024	1248	±15	1,247	Cohere	CC-BY-NC-4.0
183	168◄─►199	c4ai-aya-expanse-32b	1248	±10	3,249	Cohere	CC-BY-NC-4.0
184	163◄─►207	reka-flash-20240904	1247	±15	1,115	Reka AI	Proprietary
185	174◄─►202	mistral-large-2402	1243	±9	7,095	Mistral	Proprietary
186	175◄─►209	amazon-nova-micro-v1.0	1240	±12	2,029	Amazon	Proprietary
187	180◄─►207	claude-3-haiku-20240307	1239	±7	13,556	Anthropic	Proprietary
188	174◄─►211	gemma-2-9b-it-simpo	1236	±16	1,141	Princeton	MIT
189	181◄─►208	gemma-2-9b-it	1236	±8	6,321	Google	Gemma license
190	180◄─►210	qwen1.5-110b-chat	1234	±11	2,876	Alibaba	Qianwen LICENSE
191	165◄─►222	granite-3.1-2b-instruct	1232	±28	345	IBM	Apache 2.0
192	181◄─►210	mixtral-8x22b-instruct-v0.1	1232	±9	6,044	Mistral	Apache 2.0
193	165◄─►223	granite-3.1-8b-instruct	1230	±30	324	IBM	Apache 2.0
194	170◄─►222	qwq-32b-preview	1229	±26	423	Alibaba	Apache 2.0
195	181◄─►212	mistral-medium	1229	±11	3,820	Mistral	Proprietary
196	183◄─►213	phi-3-medium-4k-instruct	1227	±11	2,737	Microsoft	MIT
197	183◄─►213	yi-1.5-34b-chat	1226	±11	2,578	01 AI	Apache-2.0
198	182◄─►216	command-r-08-2024	1225	±14	1,368	Cohere	CC-BY-NC-4.0
199	171◄─►225	olmo-2-0325-32b-instruct	1225	±30	338	Allen AI	Apache-2.0
200	184◄─►213	qwen1.5-72b-chat	1224	±10	4,546	Alibaba	Qianwen LICENSE
201	187◄─►214	command-r-plus	1221	±8	8,863	Cohere	CC-BY-NC-4.0
202	181◄─►225	ministral-8b-2410	1220	±22	545	Mistral	MRL
203	185◄─►221	reka-flash-21b-20240226-online	1219	±14	1,878	Reka AI	Proprietary
204	185◄─►223	internlm2_5-20b-chat	1217	±16	1,085	InternLM	Other
205	185◄─►223	c4ai-aya-expanse-8b	1217	±16	1,155	Cohere	CC-BY-NC-4.0
206	188◄─►222	qwen1.5-32b-chat	1216	±12	2,423	Alibaba	Qianwen LICENSE
207	183◄─►225	granite-3.0-8b-instruct	1214	±21	675	IBM	Apache 2.0
208	181◄─►228	llama-3.1-tulu-3-8b	1213	±29	304	Ai2	Llama 3.1
209	185◄─►226	gemini-pro	1212	±21	843	Google	Proprietary
210	191◄─►224	reka-flash-21b-20240226	1211	±12	2,978	Reka AI	Proprietary
211	192◄─►226	phi-3-small-8k-instruct	1205	±13	1,858	Microsoft	MIT
212	189◄─►230	zephyr-orpo-141b-A35b-v0.1	1203	±24	527	HuggingFace	Apache 2.0
213	198◄─►225	llama-3-8b-instruct	1203	±8	12,901	Meta	Llama 3 Community
214	193◄─►228	gpt-3.5-turbo-1106	1202	±16	1,747	OpenAI	Proprietary
215	198◄─►226	llama-3.1-8b-instruct	1199	±8	6,003	Meta	Llama 3.1 Community
216	197◄─►228	phi-3-mini-4k-instruct-june-2024	1199	±14	1,363	Microsoft	MIT
217	198◄─►227	mixtral-8x7b-instruct-v0.1	1197	±8	8,519	Mistral	Apache 2.0
218	197◄─►230	jamba-1.5-mini	1196	±17	933	AI21 Labs	Jamba Open
219	199◄─►228	gpt-3.5-turbo-0125	1196	±8	7,543	OpenAI	Proprietary
220	198◄─►230	gemini-pro-dev-api	1194	±15	1,985	Google	Proprietary
221	202◄─►230	dbrx-instruct-preview	1191	±12	3,625	Databricks	DBRX LICENSE
222	198◄─►237	granite-3.0-2b-instruct	1190	±21	753	IBM	Apache 2.0
223	206◄─►230	command-r	1189	±10	5,940	Cohere	CC-BY-NC-4.0
224	205◄─►234	qwen1.5-14b-chat	1186	±13	1,993	Alibaba	Qianwen LICENSE
225	213◄─►233	gemma-2-2b-it	1181	±8	5,653	Google	Gemma license
226	196◄─►248	smollm2-1.7b-instruct	1180	±34	242	HuggingFace	Apache 2.0
227	210◄─►240	llama-3.2-3b-instruct	1176	±17	980	Meta	Llama 3.2
228	214◄─►240	starling-lm-7b-beta	1173	±14	1,825	Nexusflow	Apache-2.0
229	223◄─►246	yi-34b-chat	1162	±14	1,729	01 AI	Yi License
230	224◄─►246	snowflake-arctic-instruct	1162	±12	4,248	Snowflake	Apache 2.0
231	218◄─►251	openhermes-2.5-mistral-7b	1160	±22	568	NousResearch	Apache-2.0
232	225◄─►246	gemma-1.1-7b-it	1159	±12	2,669	Google	Gemma license
233	223◄─►251	wizardlm-70b	1158	±20	764	Microsoft	Llama 2 Community
234	225◄─►248	phi-3-mini-4k-instruct	1158	±13	2,206	Microsoft	MIT
235	218◄─►254	qwen1.5-7b-chat	1157	±23	581	Alibaba	Qianwen LICENSE
236	225◄─►250	openchat-3.5-0106	1155	±15	1,474	OpenChat	Apache-2.0
237	223◄─►255	deepseek-llm-67b-chat	1151	±26	485	DeepSeek AI	DeepSeek License
238	226◄─►255	tulu-2-dpo-70b	1145	±20	751	AllenAI/UW	AI2 ImpACT Low-risk
239	226◄─►255	llama-3.2-1b-instruct	1144	±18	977	Meta	Llama 3.2
240	228◄─►254	phi-3-mini-128k-instruct	1144	±13	2,585	Microsoft	MIT
241	228◄─►254	llama-2-70b-chat	1142	±11	4,073	Meta	Llama 2 Community
242	226◄─►256	qwen-14b-chat	1141	±26	468	Alibaba	Qianwen LICENSE
243	228◄─►255	mistral-7b-instruct-v0.2	1138	±13	2,207	Mistral	Apache-2.0
244	228◄─►255	starling-lm-7b-alpha	1136	±17	1,101	UC Berkeley	CC-BY-NC-4.0
245	228◄─►258	openchat-3.5	1132	±20	826	OpenChat	Apache-2.0
246	233◄─►255	vicuna-33b	1131	±13	2,355	LMSYS	Non-commercial
247	236◄─►258	llama-2-13b-chat	1123	±14	1,982	Meta	Llama 2 Community
248	234◄─►260	gemma-7b-it	1122	±17	989	Google	Gemma license
249	233◄─►260	palm-2	1121	±21	801	Google	Proprietary
250	231◄─►264	llama2-70b-steerlm-chat	1117	±30	353	Nvidia	Llama 2 Community
251	235◄─►262	codellama-34b-instruct	1116	±21	667	Meta	Llama 2 Community
252	228◄─►266	mpt-30b-chat	1114	±37	218	MosaicML	CC-BY-NC-SA-4.0
253	231◄─►266	dolphin-2.2.1-mistral-7b	1112	±34	201	Cognitive Computations	Apache-2.0
254	239◄─►262	gemma-1.1-2b-it	1112	±17	1,225	Google	Gemma license
255	236◄─►264	solar-10.7b-instruct-v1.0	1112	±23	529	Upstage AI	CC-BY-NC-4.0
256	246◄─►266	zephyr-7b-beta	1096	±18	1,112	HuggingFace	MIT
257	248◄─►266	llama-2-7b-chat	1092	±15	1,401	Meta	Llama 2 Community
258	245◄─►267	nous-hermes-2-mixtral-8x7b-dpo	1092	±26	464	NousResearch	Apache-2.0
259	250◄─►266	vicuna-13b	1085	±15	1,889	LMSYS	Llama 2 Community
260	248◄─►267	stripedhyena-nous-7b	1083	±23	530	Together AI	Apache 2.0
261	246◄─►268	guanaco-33b	1077	±35	236	UW	Non-commercial
262	250◄─►268	gemma-2b-it	1074	±24	527	Google	Gemma license
263	252◄─►268	mistral-7b-instruct	1073	±21	814	Mistral	Apache 2.0
264	252◄─►268	wizardlm-13b	1072	±23	567	Microsoft	Llama 2 Community
265	254◄─►268	qwen1.5-4b-chat	1067	±20	821	Alibaba	Qianwen LICENSE
266	254◄─►268	olmo-7b-instruct	1063	±20	734	Allen AI	Apache-2.0
267	259◄─►268	vicuna-7b	1045	±24	591	LMSYS	Llama 2 Community
268	261◄─►271	chatglm3-6b	1029	±26	466	Tsinghua	Apache-2.0
269	268◄─►274	RWKV-4-Raven-14B	992	±26	488	RWKV	Apache 2.0
270	268◄─►275	koala-13b	987	±23	692	UC Berkeley	Non-commercial
271	268◄─►276	mpt-7b-chat	984	±28	397	MosaicML	CC-BY-NC-SA-4.0
272	269◄─►276	alpaca-13b	975	±25	565	Stanford	Non-commercial
273	269◄─►277	chatglm-6b	974	±28	466	Tsinghua	Non-commercial
274	269◄─►277	oasst-pythia-12b	970	±25	629	OpenAssistant	Apache 2.0
275	271◄─►278	dolly-v2-12b	931	±31	343	Databricks	MIT
276	270◄─►278	llama-13b	928	±37	228	Meta	Non-commercial
277	273◄─►278	fastchat-t5-3b	921	±28	400	LMSYS	Apache 2.0
278	275◄─►278	stablelm-tuned-alpha-7b	896	±31	294	Stability AI	CC-BY-NC-SA-4.0

Text Arena

Default Leaderboard Plots

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

Confidence Intervals on Model Strength (via Bootstrapping)