Text Arena

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

Last Updated

Nov 20, 2025

Total Votes

643,309

Total Models

252

/

Style Control

	Rank Spread (Upper-Lower)
1	1◄─►5	gemini-3-pro	1491	±17	1,320	Google	Proprietary
2	1◄─►5	claude-opus-4-1-20250805-thinking-16k	1484	±8	7,144	Anthropic	Proprietary
3	1◄─►5	claude-sonnet-4-5-20250929-thinking-32k	1484	±10	4,162	Anthropic	Proprietary
4	1◄─►11	claude-sonnet-4-5-20250929	1472	±11	3,120	Anthropic	Proprietary
5	4◄─►12	claude-opus-4-1-20250805	1466	±7	9,828	Anthropic	Proprietary
6	1◄─►16	gpt-5.1-high	1466	±18	1,146	OpenAI	Proprietary
7	4◄─►14	gemini-2.5-pro	1462	±6	13,676	Google	Proprietary
8	4◄─►15	claude-opus-4-20250514-thinking-16k	1460	±8	6,848	Anthropic	Proprietary
9	4◄─►27	grok-4.1-thinking	1453	±16	1,391	xAI	Proprietary
10	4◄─►29	gpt-5.1	1452	±16	1,341	OpenAI	Proprietary
11	4◄─►31	grok-4.1	1450	±15	1,461	xAI	Proprietary
12	6◄─►31	deepseek-v3.1-thinking	1446	±12	2,368	DeepSeek	MIT
13	7◄─►26	qwen3-max-preview	1446	±8	5,881	Alibaba	Proprietary
14	8◄─►30	claude-opus-4-20250514	1443	±7	8,353	Anthropic	Proprietary
15	6◄─►36	gpt-4.5-preview-2025-02-27	1442	±14	1,812	OpenAI	Proprietary
16	5◄─►48	deepseek-v3.1-terminus-thinking	1438	±23	669	DeepSeek AI	MIT
17	9◄─►33	chatgpt-4o-latest-20250326	1438	±7	9,947	OpenAI	Proprietary
18	9◄─►34	claude-sonnet-4-20250514-thinking-32k	1438	±8	6,714	Anthropic	Proprietary
19	9◄─►38	glm-4.6	1436	±10	3,757	Z.ai	MIT
20	9◄─►36	qwen3-235b-a22b-instruct-2507	1435	±7	8,876	Alibaba	Apache 2.0
21	9◄─►37	gpt-5-chat	1435	±8	6,610	OpenAI	Proprietary
22	9◄─►39	claude-haiku-4-5-20251001	1434	±10	3,853	Anthropic	Proprietary
23	9◄─►40	deepseek-v3.2-exp-thinking	1433	±13	1,983	DeepSeek AI	MIT
24	9◄─►40	qwen3-max-2025-09-23	1433	±13	2,029	Alibaba	Proprietary
25	11◄─►40	grok-3-preview-02-24	1429	±9	4,985	xAI	Proprietary
26	9◄─►50	kimi-k2-thinking-turbo	1428	±14	1,932	Moonshot	Modified MIT
27	15◄─►48	claude-3-7-sonnet-20250219-thinking-32k	1424	±8	6,168	Anthropic	Proprietary
28	13◄─►52	deepseek-v3.1	1424	±11	3,217	DeepSeek	MIT
29	9◄─►52	grok-4-fast	1424	±15	1,506	xAI	Proprietary
30	10◄─►52	qwen3-vl-235b-a22b-instruct	1424	±14	1,844	Alibaba	Apache 2.0
31	17◄─►47	gpt-4.1-2025-04-14	1423	±7	9,790	OpenAI	Proprietary
32	17◄─►50	claude-sonnet-4-20250514	1422	±7	7,721	Anthropic	Proprietary
33	16◄─►52	glm-4.5	1422	±9	4,940	Z.ai	MIT
34	15◄─►52	deepseek-v3.2-exp	1420	±12	2,481	DeepSeek AI	MIT
35	11◄─►55	ernie-5.0-preview-1022	1420	±17	1,120	Baidu	Proprietary
36	20◄─►52	gemini-2.5-flash	1420	±6	12,914	Google	Proprietary
37	19◄─►52	gemini-2.5-flash-preview-09-2025	1419	±9	4,627	Google	Proprietary
38	21◄─►52	gpt-5-high	1417	±8	6,741	OpenAI	Proprietary
39	22◄─►52	grok-4-0709	1417	±7	8,597	xAI	Proprietary
40	12◄─►63	deepseek-v3.1-terminus	1416	±20	828	DeepSeek AI	MIT
41	25◄─►56	mistral-medium-2508	1410	±7	7,929	Mistral	Proprietary
42	25◄─►60	o1-2024-12-17	1409	±10	3,589	OpenAI	Proprietary
43	25◄─►60	grok-4-fast-reasoning	1409	±10	4,128	xAI	Proprietary
44	28◄─►56	o3-2025-04-16	1409	±6	11,387	OpenAI	Proprietary
45	28◄─►58	claude-3-7-sonnet-20250219	1408	±8	6,768	Anthropic	Proprietary
46	25◄─►62	deepseek-r1-0528	1408	±11	3,178	DeepSeek	MIT
47	30◄─►60	qwen3-235b-a22b-no-thinking	1407	±8	7,124	Alibaba	Apache 2.0
48	30◄─►63	qwen3-coder-480b-a35b-instruct	1405	±9	4,585	Alibaba	Apache 2.0
49	25◄─►68	qwen3-vl-235b-a22b-thinking	1404	±14	1,674	Alibaba	Apache 2.0
50	26◄─►65	kimi-k2-0905-preview	1404	±13	2,209	Moonshot	Modified MIT
51	25◄─►69	qwen3-235b-a22b-thinking-2507	1403	±14	1,659	Alibaba	Apache 2.0
52	39◄─►72	deepseek-r1	1396	±12	2,329	DeepSeek	MIT
53	39◄─►72	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1396	±9	4,554	Google	Proprietary
54	40◄─►72	qwen3-next-80b-a3b-instruct	1394	±9	5,053	Alibaba	Apache 2.0
55	25◄─►90	hunyuan-vision-1.5-thinking	1393	±26	478	Tencent	Proprietary
56	42◄─►76	mai-1-preview	1392	±10	3,479	Microsoft AI	Proprietary
57	46◄─►72	deepseek-v3-0324	1391	±7	8,443	DeepSeek	MIT
58	43◄─►73	kimi-k2-0711-preview	1391	±8	5,424	Moonshot	Modified MIT
59	47◄─►72	claude-3-5-sonnet-20241022	1391	±6	13,891	Anthropic	Proprietary
60	46◄─►74	mistral-medium-2505	1390	±8	5,959	Mistral	Proprietary
61	43◄─►81	longcat-flash-chat	1388	±12	2,320	Meituan	MIT
62	49◄─►79	gpt-4.1-mini-2025-04-14	1387	±8	7,106	OpenAI	Proprietary
63	39◄─►90	hunyuan-t1-20250711	1386	±20	871	Tencent	Proprietary
64	50◄─►82	gemini-2.5-flash-lite-preview-06-17-thinking	1383	±8	6,313	Google	Proprietary
65	50◄─►82	qwen2.5-max	1383	±8	4,622	Alibaba	Proprietary
66	50◄─►84	qwen3-30b-a3b-instruct-2507	1382	±9	4,829	Alibaba	Apache 2.0
67	52◄─►84	glm-4.5-air	1380	±8	6,516	Z.ai	MIT
68	51◄─►88	qwen3-235b-a22b	1380	±9	4,648	Alibaba	Apache 2.0
69	52◄─►89	o1-preview	1379	±9	4,601	OpenAI	Proprietary
70	49◄─►93	hunyuan-turbos-20250416	1378	±15	1,594	Tencent	Proprietary
71	52◄─►90	grok-3-mini-high	1378	±10	3,288	xAI	Proprietary
72	58◄─►91	gpt-5-mini-high	1374	±9	5,595	OpenAI	Proprietary
73	42◄─►112	hunyuan-large-2025-02-10	1374	±28	373	Tencent	Proprietary
74	59◄─►96	deepseek-v3	1372	±10	3,166	DeepSeek	DeepSeek
75	59◄─►100	o3-mini-high	1370	±12	2,188	OpenAI	Proprietary
76	60◄─►100	qwen3-next-80b-a3b-thinking	1369	±11	2,758	Alibaba	Apache 2.0
77	61◄─►96	minimax-m1	1369	±8	6,918	MiniMax	Apache 2.0
78	64◄─►96	command-a-03-2025	1367	±6	10,438	Cohere	CC-BY-NC-4.0
79	61◄─►100	grok-3-mini-beta	1367	±9	4,197	xAI	Proprietary
80	64◄─►99	o4-mini-2025-04-16	1367	±7	8,520	OpenAI	Proprietary
81	66◄─►104	gemma-3-27b-it	1364	±7	6,827	Google	Gemma
82	66◄─►104	gemini-2.0-flash-001	1364	±7	6,601	Google	Proprietary
83	60◄─►119	qwen-plus-0125	1360	±21	692	Alibaba	Proprietary
84	68◄─►107	mistral-small-2506	1359	±10	3,412	Mistral	Apache 2.0
85	72◄─►105	o3-mini	1358	±6	9,324	OpenAI	Proprietary
86	60◄─►131	qwen3-32b	1355	±25	507	Alibaba	Apache 2.0
87	76◄─►109	gemini-1.5-pro-002	1354	±7	8,409	Google	Proprietary
88	57◄─►139	hunyuan-turbos-20250226	1352	±32	288	Tencent	Proprietary
89	67◄─►129	amazon-nova-experimental-chat-10-20	1350	±20	883	Amazon	Proprietary
90	71◄─►124	step-3	1350	±16	1,253	StepFun	Apache 2.0
91	80◄─►117	claude-3-5-sonnet-20240620	1349	±8	10,620	Anthropic	Proprietary
92	73◄─►126	minimax-m2	1348	±15	1,536	MiniMax	Apache 2.0
93	62◄─►141	gemma-3-12b-it	1347	±29	378	Google	Gemma
94	73◄─►129	step-1o-turbo-202506	1346	±16	1,357	StepFun	Proprietary
95	80◄─►121	gemini-2.0-flash-lite-preview-02-05	1346	±10	2,967	Google	Proprietary
96	82◄─►120	gemini-1.5-pro-001	1346	±8	9,799	Google	Proprietary
97	83◄─►123	o1-mini	1342	±7	7,927	OpenAI	Proprietary
98	66◄─►143	llama-3.1-nemotron-ultra-253b-v1	1342	±30	327	Nvidia	Nvidia Open Model
99	66◄─►143	hunyuan-turbo-0110	1341	±30	314	Tencent	Proprietary
100	73◄─►141	nvidia-llama-3.3-nemotron-super-49b-v1.5	1340	±22	668	Nvidia	Nvidia Open
101	86◄─►124	claude-3-5-haiku-20241022	1339	±6	11,035	Anthropic	Propretary
102	84◄─►129	qwen3-30b-a3b	1339	±9	4,527	Alibaba	Apache 2.0
103	76◄─►141	step-2-16k-exp-202412	1339	±21	695	StepFun	Proprietary
104	80◄─►139	glm-4.5v	1339	±19	1,030	Z.ai	MIT
105	77◄─►141	glm-4-plus-0111	1338	±20	764	Zhipu	Proprietary
106	76◄─►143	amazon-nova-experimental-chat-10-09	1337	±24	576	Amazon	Proprietary
107	86◄─►134	qwq-32b	1335	±9	4,043	Alibaba	Apache 2.0
108	72◄─►149	llama-3.3-nemotron-49b-super-v1	1334	±30	320	Nvidia	Nvidia
109	85◄─►136	magistral-medium-2506	1334	±12	2,358	Mistral	Proprietary
110	86◄─►134	gpt-4o-2024-08-06	1334	±8	6,162	OpenAI	Proprietary
111	86◄─►134	llama-4-maverick-17b-128e-instruct	1334	±8	7,096	Meta	Llama 4
112	83◄─►141	deepseek-v2.5-1210	1334	±17	1,042	DeepSeek	DeepSeek
113	84◄─►142	ring-flash-2.0	1332	±16	1,358	Ant Group	MIT
114	88◄─►134	grok-2-2024-08-13	1331	±7	8,910	xAI	Proprietary
115	85◄─►142	gpt-5-nano-high	1331	±15	1,571	OpenAI	Proprietary
116	80◄─►150	hunyuan-standard-2025-02-10	1330	±27	432	Tencent	Proprietary
117	85◄─►143	ling-flash-2.0	1329	±16	1,253	Ant Group	MIT
118	90◄─►137	gpt-4o-2024-05-13	1328	±7	14,995	OpenAI	Proprietary
119	90◄─►141	llama-4-scout-17b-16e-instruct	1327	±8	5,724	Meta	Llama
120	93◄─►141	mistral-small-3.1-24b-instruct-2503	1325	±8	6,315	Mistral	Apache 2.0
121	86◄─►148	gpt-4.1-nano-2025-04-14	1325	±20	738	OpenAI	Proprietary
122	94◄─►142	gpt-oss-120b	1324	±8	6,340	OpenAI	Apache 2.0
123	97◄─►141	claude-3-opus-20240229	1324	±6	23,481	Anthropic	Proprietary
124	94◄─►143	llama-3.1-405b-instruct-bf16	1323	±8	5,520	Meta	Llama 3.1 Community
125	91◄─►144	qwen-max-0919	1323	±12	2,452	Alibaba	Qwen
126	93◄─►143	yi-lightning	1323	±10	3,648	01 AI	Proprietary
127	94◄─►143	glm-4-plus	1322	±10	4,013	Zhipu AI	Proprietary
128	98◄─►143	gpt-4o-mini-2024-07-18	1322	±7	9,035	OpenAI	Proprietary
129	97◄─►145	gemini-advanced-0514	1320	±10	5,543	Google	Proprietary
130	98◄─►143	gemini-1.5-flash-002	1320	±8	5,485	Google	Proprietary
131	98◄─►146	athene-v2-chat	1318	±9	3,672	NexusFlow	NexusFlow
132	89◄─►153	hunyuan-large-vision	1317	±20	898	Tencent	Proprietary
133	102◄─►146	llama-3.1-405b-instruct-fp8	1315	±7	8,072	Meta	Llama 3.1 Community
134	87◄─►165	mercury	1314	±27	495	Inception AI	Proprietary
135	103◄─►147	qwen2.5-72b-instruct	1314	±8	6,033	Alibaba	Qwen
136	104◄─►147	grok-2-mini-2024-08-13	1314	±7	7,052	xAI	Proprietary
137	102◄─►152	gemma-3n-e4b-it	1312	±11	2,983	Google	Gemma
138	87◄─►165	gemma-3-4b-it	1312	±27	447	Google	Gemma
139	106◄─►149	gpt-4-turbo-2024-04-09	1311	±8	11,620	OpenAI	Proprietary
140	104◄─►152	deepseek-v2.5	1311	±10	3,505	DeepSeek	DeepSeek
141	117◄─►150	llama-3.3-70b-instruct	1309	±7	8,405	Meta	Llama-3.3
142	106◄─►163	qwen2.5-plus-1127	1305	±14	1,592	Alibaba	Proprietary
143	114◄─►163	gpt-oss-20b	1303	±14	2,069	OpenAI	Apache 2.0
144	127◄─►159	gpt-4-0125-preview	1302	±8	9,722	OpenAI	Proprietary
145	126◄─►161	mistral-large-2411	1302	±9	3,640	Mistral	MRL
146	128◄─►162	mistral-large-2407	1300	±9	5,897	Mistral	Mistral Research
147	130◄─►165	amazon-nova-pro-v1.0	1297	±10	3,430	Amazon	Proprietary
148	132◄─►165	gemini-1.5-flash-001	1297	±9	7,872	Google	Proprietary
149	133◄─►165	gpt-4-1106-preview	1296	±8	9,201	OpenAI	Proprietary
150	137◄─►164	gemma-2-27b-it	1296	±7	9,969	Google	Gemma license
151	140◄─►166	llama-3.1-70b-instruct	1290	±7	7,646	Meta	Llama 3.1 Community
152	139◄─►171	athene-70b-0725	1288	±12	2,120	NexusFlow	CC-BY-NC-4.0
153	140◄─►171	c4ai-aya-expanse-32b	1286	±9	4,183	Cohere	CC-BY-NC-4.0
154	135◄─►180	gemma-2-9b-it-simpo	1284	±19	837	Princeton	MIT
155	140◄─►176	nemotron-4-340b-instruct	1283	±13	2,156	Nvidia	NVIDIA Open Model
156	137◄─►180	qwen2.5-coder-32b-instruct	1283	±19	807	Alibaba	Apache 2.0
157	140◄─►178	deepseek-coder-v2	1282	±14	1,854	DeepSeek AI	DeepSeek License
158	145◄─►175	claude-3-sonnet-20240229	1281	±9	11,940	Anthropic	Proprietary
159	140◄─►181	llama-3.1-nemotron-70b-instruct	1278	±18	1,057	Nvidia	Llama 3.1
160	143◄─►180	mistral-small-24b-instruct-2501	1277	±14	1,782	Mistral	Apache 2.0
161	142◄─►180	command-r-plus-08-2024	1277	±15	1,365	Cohere	CC-BY-NC-4.0
162	141◄─►181	reka-core-20240904	1276	±18	960	Reka AI	Proprietary
163	152◄─►180	gpt-4-0613	1272	±9	7,566	OpenAI	Proprietary
164	151◄─►181	gpt-4-0314	1271	±11	4,264	OpenAI	Proprietary
165	152◄─►180	amazon-nova-lite-v1.0	1271	±11	2,810	Amazon	Proprietary
166	140◄─►187	llama-3.1-tulu-3-70b	1269	±25	468	Ai2	Llama 3.1
167	141◄─►188	hunyuan-standard-256k	1267	±27	417	Tencent	Proprietary
168	146◄─►187	llama-3.1-nemotron-51b-instruct	1265	±23	588	Nvidia	Llama 3.1
169	154◄─►184	phi-4	1263	±11	2,912	Microsoft	MIT
170	155◄─►183	gemini-1.5-flash-8b-001	1263	±8	5,591	Google	Proprietary
171	152◄─►186	glm-4-0520	1262	±17	1,186	Zhipu AI	Proprietary
172	156◄─►184	gemma-2-9b-it	1261	±8	6,919	Google	Gemma license
173	156◄─►184	claude-3-haiku-20240307	1261	±8	14,062	Anthropic	Proprietary
174	152◄─►188	reka-flash-20240904	1259	±18	992	Reka AI	Proprietary
175	154◄─►187	command-r-08-2024	1258	±15	1,423	Cohere	CC-BY-NC-4.0
176	154◄─►188	jamba-1.5-large	1257	±17	1,019	AI21 Labs	Jamba Open
177	157◄─►186	command-r-plus	1257	±9	9,194	Cohere	CC-BY-NC-4.0
178	157◄─►186	qwen2-72b-instruct	1256	±10	4,633	Alibaba	Qianwen LICENSE
179	154◄─►191	ministral-8b-2410	1255	±20	722	Mistral	MRL
180	166◄─►188	llama-3-70b-instruct	1247	±7	17,609	Meta	Llama 3 Community
181	163◄─►191	c4ai-aya-expanse-8b	1246	±15	1,493	Cohere	CC-BY-NC-4.0
182	166◄─►191	amazon-nova-micro-v1.0	1245	±11	2,646	Amazon	Proprietary
183	152◄─►204	olmo-2-0325-32b-instruct	1243	±34	266	Allen AI	Apache-2.0
184	170◄─►193	mistral-large-2402	1240	±10	6,252	Mistral	Proprietary
185	176◄─►200	qwen1.5-72b-chat	1230	±12	3,506	Alibaba	Qianwen LICENSE
186	167◄─►210	granite-3.1-8b-instruct	1228	±27	463	IBM	Apache 2.0
187	180◄─►200	command-r	1227	±10	6,191	Cohere	CC-BY-NC-4.0
188	180◄─►204	qwen1.5-110b-chat	1223	±12	3,379	Alibaba	Qianwen LICENSE
189	170◄─►212	llama-3.1-tulu-3-8b	1223	±26	455	Ai2	Llama 3.1
190	184◄─►203	llama-3.1-8b-instruct	1220	±8	6,761	Meta	Llama 3.1 Community
191	173◄─►213	granite-3.1-2b-instruct	1219	±26	492	IBM	Apache 2.0
192	183◄─►207	qwen1.5-32b-chat	1218	±13	2,590	Alibaba	Qianwen LICENSE
193	180◄─►210	gemini-pro-dev-api	1218	±18	1,364	Google	Proprietary
194	184◄─►209	mistral-medium	1215	±13	2,747	Mistral	Proprietary
195	184◄─►207	gpt-3.5-turbo-0125	1214	±9	6,763	OpenAI	Proprietary
196	183◄─►212	jamba-1.5-mini	1213	±18	1,017	AI21 Labs	Jamba Open
197	184◄─►209	mixtral-8x22b-instruct-v0.1	1212	±10	5,905	Mistral	Apache 2.0
198	184◄─►211	reka-flash-21b-20240226	1212	±13	2,744	Reka AI	Proprietary
199	184◄─►212	reka-flash-21b-20240226-online	1211	±16	1,658	Reka AI	Proprietary
200	187◄─►213	llama-3-8b-instruct	1203	±8	11,241	Meta	Llama 3 Community
201	186◄─►216	yi-1.5-34b-chat	1199	±13	2,112	01 AI	Apache-2.0
202	184◄─►222	granite-3.0-8b-instruct	1197	±24	605	IBM	Apache 2.0
203	186◄─►219	internlm2_5-20b-chat	1197	±16	1,272	InternLM	Other
204	193◄─►223	qwen1.5-14b-chat	1187	±15	2,110	Alibaba	Qianwen LICENSE
205	195◄─►221	phi-3-medium-4k-instruct	1186	±13	2,163	Microsoft	MIT
206	201◄─►221	gemma-2-2b-it	1183	±9	5,881	Google	Gemma license
207	199◄─►223	dbrx-instruct-preview	1183	±13	3,513	Databricks	DBRX LICENSE
208	196◄─►230	gpt-3.5-turbo-1106	1178	±20	942	OpenAI	Proprietary
209	189◄─►232	openchat-3.5	1178	±28	418	OpenChat	Apache-2.0
210	189◄─►232	zephyr-orpo-141b-A35b-v0.1	1178	±28	450	HuggingFace	Apache 2.0
211	201◄─►225	mixtral-8x7b-instruct-v0.1	1177	±9	6,615	Mistral	Apache 2.0
212	189◄─►234	wizardlm-70b	1177	±32	358	Microsoft	Llama 2 Community
213	191◄─►232	qwq-32b-preview	1176	±26	476	Alibaba	Apache 2.0
214	186◄─►236	deepseek-llm-67b-chat	1176	±37	245	DeepSeek AI	DeepSeek License
215	191◄─►237	tulu-2-dpo-70b	1171	±34	282	AllenAI/UW	AI2 ImpACT Low-risk
216	202◄─►232	yi-34b-chat	1166	±18	1,112	01 AI	Yi License
217	202◄─►235	openchat-3.5-0106	1163	±19	1,102	OpenChat	Apache-2.0
218	203◄─►233	starling-lm-7b-beta	1162	±16	1,685	Nexusflow	Apache-2.0
219	206◄─►232	gemma-1.1-7b-it	1160	±13	2,679	Google	Gemma license
220	201◄─►238	qwen1.5-7b-chat	1158	±30	372	Alibaba	Qianwen LICENSE
221	208◄─►236	phi-3-small-8k-instruct	1157	±13	2,257	Microsoft	MIT
222	205◄─►237	llama-3.2-3b-instruct	1155	±18	1,048	Meta	Llama 3.2
223	209◄─►241	starling-lm-7b-alpha	1145	±23	669	UC Berkeley	CC-BY-NC-4.0
224	208◄─►241	granite-3.0-2b-instruct	1144	±25	649	IBM	Apache 2.0
225	202◄─►246	wizardlm-13b	1140	±41	205	Microsoft	Llama 2 Community
226	209◄─►243	vicuna-13b	1138	±22	759	LMSYS	Llama 2 Community
227	203◄─►250	vicuna-7b	1136	±45	164	LMSYS	Llama 2 Community
228	210◄─►243	llama-2-13b-chat	1135	±18	1,208	Meta	Llama 2 Community
229	209◄─►246	openhermes-2.5-mistral-7b	1134	±34	273	NousResearch	Apache-2.0
230	216◄─►241	llama-2-70b-chat	1133	±13	2,830	Meta	Llama 2 Community
231	209◄─►247	smollm2-1.7b-instruct	1130	±33	329	HuggingFace	Apache 2.0
232	218◄─►244	mistral-7b-instruct-v0.2	1129	±15	1,595	Mistral	Apache-2.0
233	209◄─►250	palm-2	1128	±38	253	Google	Proprietary
234	215◄─►246	vicuna-33b	1128	±19	1,053	LMSYS	Non-commercial
235	220◄─►245	snowflake-arctic-instruct	1124	±14	2,812	Snowflake	Apache 2.0
236	210◄─►251	qwen-14b-chat	1118	±38	217	Alibaba	Qianwen LICENSE
237	223◄─►249	gemma-1.1-2b-it	1110	±18	1,186	Google	Gemma license
238	217◄─►252	nous-hermes-2-mixtral-8x7b-dpo	1109	±36	232	NousResearch	Apache-2.0
239	222◄─►250	gemma-7b-it	1106	±23	679	Google	Gemma license
240	226◄─►251	phi-3-mini-4k-instruct-june-2024	1100	±19	1,040	Microsoft	MIT
241	223◄─►252	zephyr-7b-beta	1099	±28	465	HuggingFace	MIT
242	228◄─►251	llama-3.2-1b-instruct	1097	±19	1,059	Meta	Llama 3.2
243	229◄─►251	phi-3-mini-4k-instruct	1097	±15	1,761	Microsoft	MIT
244	223◄─►252	codellama-34b-instruct	1092	±33	323	Meta	Llama 2 Community
245	226◄─►252	mistral-7b-instruct	1090	±27	452	Mistral	Apache 2.0
246	230◄─►252	gemma-2b-it	1079	±31	379	Google	Gemma license
247	234◄─►252	qwen1.5-4b-chat	1072	±24	693	Alibaba	Qianwen LICENSE
248	235◄─►252	llama-2-7b-chat	1070	±20	838	Meta	Llama 2 Community
249	238◄─►252	phi-3-mini-128k-instruct	1067	±16	2,085	Microsoft	MIT
250	233◄─►252	stripedhyena-nous-7b	1065	±33	335	Together AI	Apache 2.0
251	234◄─►252	llama2-70b-steerlm-chat	1052	±44	210	Nvidia	Llama 2 Community
252	242◄─►252	chatglm3-6b	1034	±41	205	Tsinghua	Apache-2.0

Text Arena

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)