Text Arena

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

Last Updated

Dec 23, 2025

Total Votes

274,108

Total Models

265

/

Style Control

	Rank Spread
1	1◄─►13	gemini-3-flash (thinking-minimal)	1513	±34	326	Google	Proprietary
2	1◄─►18	gemini-3-flash	1506	±33	317	Google	Proprietary
3	1◄─►10	grok-4.1-thinking	1504	±17	1,394	xAI	Proprietary
4	1◄─►10	gemini-3-pro	1503	±17	1,292	Google	Proprietary
5	1◄─►24	claude-opus-4-5-20251101	1481	±20	963	Anthropic	Proprietary
6	1◄─►23	grok-4.1	1480	±17	1,431	xAI	Proprietary
7	1◄─►27	claude-opus-4-5-20251101-thinking-32k	1479	±20	912	Anthropic	Proprietary
8	3◄─►23	gemini-2.5-pro	1472	±9	5,307	Google	Proprietary
9	1◄─►35	gpt-4.5-preview-2025-02-27	1469	±22	706	OpenAI	Proprietary
10	1◄─►52	deepseek-v3.1-terminus-thinking	1463	±36	264	DeepSeek AI	MIT
11	4◄─►32	claude-opus-4-1-20250805-thinking-16k	1462	±12	2,927	Anthropic	Proprietary
12	3◄─►37	gpt-5.1-high	1461	±18	1,173	OpenAI	Proprietary
13	4◄─►35	gpt-5-chat	1460	±14	1,917	OpenAI	Proprietary
14	5◄─►34	chatgpt-4o-latest-20250326	1460	±10	4,042	OpenAI	Proprietary
15	4◄─►35	gpt-5-high	1459	±15	1,883	OpenAI	Proprietary
16	5◄─►35	claude-opus-4-1-20250805	1458	±10	3,949	Anthropic	Proprietary
17	4◄─►37	claude-sonnet-4-5-20250929	1458	±15	1,725	Anthropic	Proprietary
18	4◄─►44	kimi-k2-0905-preview	1457	±21	783	Moonshot	Modified MIT
19	5◄─►35	o3-2025-04-16	1456	±10	3,864	OpenAI	Proprietary
20	1◄─►62	ernie-5.0-preview-1203	1456	±38	244	Baidu	Proprietary
21	3◄─►54	gpt-5.2-high	1453	±27	444	OpenAI	Proprietary
22	5◄─►49	gpt-5.1	1449	±18	1,196	OpenAI	Proprietary
23	7◄─►46	claude-sonnet-4-5-20250929-thinking-32k	1448	±14	1,925	Anthropic	Proprietary
24	5◄─►62	mistral-large-3	1442	±24	661	Mistral	Apache 2.0
25	9◄─►50	claude-opus-4-20250514	1441	±11	2,937	Anthropic	Proprietary
26	10◄─►52	gpt-4.1-2025-04-14	1439	±11	3,264	OpenAI	Proprietary
27	8◄─►62	grok-4-1-fast-reasoning	1439	±21	865	xAI	Proprietary
28	11◄─►55	claude-opus-4-20250514-thinking-16k	1437	±13	2,454	Anthropic	Proprietary
29	8◄─►71	ernie-5.0-preview-1103	1436	±24	561	Baidu	Proprietary
30	9◄─►72	qwen3-vl-235b-a22b-instruct	1434	±24	608	Alibaba	Apache 2.0
31	9◄─►63	kimi-k2-thinking-turbo	1433	±18	1,199	Moonshot	Modified MIT
32	9◄─►72	deepseek-v3.2	1432	±22	737	DeepSeek AI	MIT
33	8◄─►77	grok-4-fast-chat	1432	±28	451	xAI	Proprietary
34	16◄─►64	glm-4.6	1429	±15	1,713	Z.ai	MIT
35	18◄─►68	qwen3-max-preview	1428	±15	1,693	Alibaba	Proprietary
36	10◄─►77	deepseek-v3.2-thinking	1427	±24	644	DeepSeek AI	MIT
37	18◄─►63	gemini-2.5-flash	1427	±9	5,182	Google	Proprietary
38	18◄─►71	kimi-k2-0711-preview	1425	±15	1,797	Moonshot	Modified MIT
39	18◄─►77	grok-4-fast-reasoning	1423	±17	1,136	xAI	Proprietary
40	18◄─►77	deepseek-v3.1	1422	±18	1,016	DeepSeek	MIT
41	19◄─►71	grok-4-0709	1422	±12	2,684	xAI	Proprietary
42	20◄─►71	qwen3-235b-a22b-instruct-2507	1422	±11	3,411	Alibaba	Apache 2.0
43	19◄─►75	gemini-2.5-flash-preview-09-2025	1422	±14	2,083	Google	Proprietary
44	20◄─►72	mistral-medium-2508	1421	±12	3,066	Mistral	Proprietary
45	9◄─►95	deepseek-v3.1-terminus	1420	±35	276	DeepSeek AI	MIT
46	18◄─►81	deepseek-v3.1-thinking	1420	±21	783	DeepSeek	MIT
47	16◄─►90	deepseek-v3.2-exp-thinking	1419	±25	509	DeepSeek AI	MIT
48	18◄─►90	qwen3-max-2025-09-23	1416	±24	562	Alibaba	Proprietary
49	21◄─►81	glm-4.5	1415	±16	1,520	Z.ai	MIT
50	22◄─►80	grok-3-preview-02-24	1415	±14	1,945	xAI	Proprietary
51	24◄─►79	claude-sonnet-4-20250514	1414	±12	2,720	Anthropic	Proprietary
52	22◄─►84	qwen3-next-80b-a3b-instruct	1413	±16	1,402	Alibaba	Apache 2.0
53	25◄─►81	claude-sonnet-4-20250514-thinking-32k	1412	±13	2,306	Anthropic	Proprietary
54	20◄─►90	deepseek-v3.2-exp	1412	±21	760	DeepSeek AI	MIT
55	24◄─►89	deepseek-r1-0528	1410	±16	1,413	DeepSeek	MIT
56	26◄─►83	mistral-medium-2505	1410	±13	2,193	Mistral	Proprietary
57	26◄─►82	deepseek-v3-0324	1410	±11	2,959	DeepSeek	MIT
58	26◄─►90	o1-2024-12-17	1409	±15	1,457	OpenAI	Proprietary
59	26◄─►89	claude-3-7-sonnet-20250219-thinking-32k	1406	±12	2,549	Anthropic	Proprietary
60	32◄─►90	o4-mini-2025-04-16	1402	±12	2,809	OpenAI	Proprietary
61	32◄─►90	gpt-4.1-mini-2025-04-14	1402	±12	2,511	OpenAI	Proprietary
62	32◄─►90	qwen3-235b-a22b-no-thinking	1401	±12	2,597	Alibaba	Apache 2.0
63	32◄─►91	claude-3-7-sonnet-20250219	1401	±12	2,553	Anthropic	Proprietary
64	29◄─►98	deepseek-r1	1400	±18	1,102	DeepSeek	MIT
65	26◄─►114	qwen3-vl-235b-a22b-thinking	1398	±26	498	Alibaba	Apache 2.0
66	33◄─►99	qwen3-coder-480b-a35b-instruct	1398	±16	1,463	Alibaba	Apache 2.0
67	31◄─►102	mai-1-preview	1397	±18	1,151	Microsoft AI	Proprietary
68	37◄─►102	claude-haiku-4-5-20251001	1395	±15	1,829	Anthropic	Proprietary
69	40◄─►101	o1-preview	1395	±14	1,946	OpenAI	Proprietary
70	40◄─►107	gpt-5-mini-high	1393	±15	1,669	OpenAI	Proprietary
71	41◄─►105	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1392	±14	2,029	Google	Proprietary
72	50◄─►99	claude-3-5-sonnet-20241022	1390	±9	5,600	Anthropic	Proprietary
73	33◄─►120	qwen3-235b-a22b-thinking-2507	1388	±24	566	Alibaba	Apache 2.0
74	40◄─►118	longcat-flash-chat	1387	±21	775	Meituan	MIT
75	45◄─►116	deepseek-v3	1387	±16	1,314	DeepSeek	DeepSeek
76	47◄─►114	qwen2.5-max	1386	±14	1,913	Alibaba	Proprietary
77	26◄─►141	hunyuan-t1-20250711	1385	±34	282	Tencent	Proprietary
78	53◄─►114	gemini-2.0-flash-001	1384	±12	2,666	Google	Proprietary
79	53◄─►116	gemini-2.5-flash-lite-preview-06-17-thinking	1384	±13	2,149	Google	Proprietary
80	51◄─►117	gemini-2.0-flash-lite-preview-02-05	1382	±15	1,439	Google	Proprietary
81	55◄─►115	gemma-3-27b-it	1382	±12	2,782	Google	Gemma
82	33◄─►140	glm-4-plus-0111	1382	±30	368	Zhipu	Proprietary
83	53◄─►117	gemini-advanced-0514	1381	±14	2,969	Google	Proprietary
84	26◄─►158	gemma-3-12b-it	1381	±39	217	Google	Gemma
85	53◄─►119	qwen3-30b-a3b-instruct-2507	1380	±15	1,499	Alibaba	Apache 2.0
86	52◄─►120	grok-3-mini-high	1380	±17	1,195	xAI	Proprietary
87	46◄─►127	hunyuan-turbos-20250416	1379	±21	755	Tencent	Proprietary
88	41◄─►142	qwen-plus-0125	1379	±28	393	Alibaba	Proprietary
89	63◄─►118	command-a-03-2025	1376	±10	3,491	Cohere	CC-BY-NC-4.0
90	64◄─►118	gpt-4o-2024-05-13	1376	±9	6,753	OpenAI	Proprietary
91	63◄─►120	llama-3.1-405b-instruct-bf16	1375	±12	2,333	Meta	Llama 3.1 Community
92	63◄─►120	llama-3.1-405b-instruct-fp8	1375	±11	3,393	Meta	Llama 3.1 Community
93	62◄─►134	mistral-small-2506	1372	±17	1,184	Mistral	Apache 2.0
94	67◄─►122	gemini-1.5-pro-002	1370	±11	3,367	Google	Proprietary
95	64◄─►135	yi-lightning	1368	±15	1,706	01 AI	Proprietary
96	67◄─►134	glm-4.5-air	1368	±14	1,918	Z.ai	MIT
97	45◄─►162	glm-4.5v	1368	±35	270	Z.ai	MIT
98	72◄─►131	grok-2-2024-08-13	1366	±10	3,830	xAI	Proprietary
99	70◄─►135	minimax-m1	1366	±12	2,435	MiniMax	Apache 2.0
100	70◄─►141	qwen3-235b-a22b	1365	±14	1,773	Alibaba	Apache 2.0
101	70◄─►157	o3-mini-high	1361	±18	1,024	OpenAI	Proprietary
102	63◄─►165	minimax-m2	1359	±29	416	MiniMax	Apache 2.0
103	78◄─►144	claude-3-5-sonnet-20240620	1359	±10	4,842	Anthropic	Proprietary
104	72◄─►158	grok-3-mini-beta	1357	±15	1,543	xAI	Proprietary
105	71◄─►162	qwen3-next-80b-a3b-thinking	1357	±21	858	Alibaba	Apache 2.0
106	84◄─►149	claude-3-opus-20240229	1355	±9	11,129	Anthropic	Proprietary
107	53◄─►181	amazon-nova-experimental-chat-11-10	1355	±40	222	Amazon	Proprietary
108	65◄─►169	gpt-4.1-nano-2025-04-14	1353	±29	386	OpenAI	Proprietary
109	83◄─►158	gpt-4o-2024-08-06	1353	±12	2,685	OpenAI	Proprietary
110	88◄─►157	claude-3-5-haiku-20241022	1352	±10	4,346	Anthropic	Proprietary
111	80◄─►162	glm-4-plus	1352	±15	1,733	Zhipu AI	Proprietary
112	89◄─►162	gpt-4o-mini-2024-07-18	1349	±10	3,878	OpenAI	Proprietary
113	64◄─►181	nvidia-llama-3.3-nemotron-super-49b-v1.5	1348	±36	244	Nvidia	Nvidia Open
114	89◄─►162	llama-3.3-70b-instruct	1348	±10	3,216	Meta	Llama-3.3
115	68◄─►181	step-2-16k-exp-202412	1347	±33	278	StepFun	Proprietary
116	72◄─►175	ling-flash-2.0	1346	±28	433	Ant Group	MIT
117	89◄─►162	llama-4-scout-17b-16e-instruct	1346	±14	2,023	Meta	Llama
118	90◄─►162	llama-4-maverick-17b-128e-instruct	1345	±12	2,689	Meta	Llama 4
119	91◄─►162	o1-mini	1344	±11	3,146	OpenAI	Proprietary
120	91◄─►163	mistral-large-2407	1343	±12	2,743	Mistral	Mistral Research
121	75◄─►181	step-3	1343	±29	422	StepFun	Apache 2.0
122	95◄─►162	gpt-4-turbo-2024-04-09	1342	±11	5,395	OpenAI	Proprietary
123	72◄─►183	hunyuan-standard-2025-02-10	1342	±34	288	Tencent	Proprietary
124	98◄─►165	o3-mini	1341	±10	3,683	OpenAI	Proprietary
125	93◄─►168	gpt-oss-120b	1340	±14	1,907	OpenAI	Apache 2.0
126	76◄─►183	intellect-3	1339	±32	350	Prime Intellect	MIT
127	72◄─►184	llama-3.1-nemotron-51b-instruct	1339	±36	236	Nvidia	Llama 3.1
128	95◄─►169	qwq-32b	1339	±15	1,693	Alibaba	Apache 2.0
129	71◄─►191	amazon-nova-experimental-chat-10-09	1338	±40	210	Amazon	Proprietary
130	72◄─►188	hunyuan-large-2025-02-10	1338	±36	252	Tencent	Proprietary
131	72◄─►188	gemma-3-4b-it	1337	±36	248	Google	Gemma
132	100◄─►169	gemini-1.5-pro-001	1336	±11	4,799	Google	Proprietary
133	99◄─►173	deepseek-v2.5	1335	±15	1,529	DeepSeek	DeepSeek
134	90◄─►181	amazon-nova-experimental-chat-10-20	1335	±22	740	Amazon	Proprietary
135	95◄─►181	athene-70b-0725	1334	±19	1,011	NexusFlow	CC-BY-NC-4.0
136	88◄─►184	reka-core-20240904	1333	±29	371	Reka AI	Proprietary
137	101◄─►171	gpt-4-0125-preview	1333	±11	5,056	OpenAI	Proprietary
138	101◄─►173	qwen2.5-72b-instruct	1333	±12	2,396	Alibaba	Qwen
139	101◄─►172	llama-3.1-70b-instruct	1332	±11	3,185	Meta	Llama 3.1 Community
140	101◄─►175	gemini-1.5-flash-002	1331	±13	2,169	Google	Proprietary
141	89◄─►186	gpt-5-nano-high	1331	±28	470	OpenAI	Proprietary
142	91◄─►184	gemma-2-9b-it-simpo	1331	±25	543	Princeton	MIT
143	106◄─►175	grok-2-mini-2024-08-13	1330	±11	3,019	xAI	Proprietary
144	90◄─►187	jamba-1.5-large	1330	±27	448	AI21 Labs	Jamba Open
145	95◄─►184	gpt-oss-20b	1329	±24	703	OpenAI	Apache 2.0
146	89◄─►190	deepseek-v2.5-1210	1329	±29	375	DeepSeek	DeepSeek
147	101◄─►181	mistral-large-2411	1329	±15	1,595	Mistral	MRL
148	100◄─►182	qwen-max-0919	1329	±18	1,087	Alibaba	Qwen
149	101◄─►181	athene-v2-chat	1328	±15	1,444	NexusFlow	NexusFlow
150	101◄─►181	amazon-nova-pro-v1.0	1328	±16	1,297	Amazon	Proprietary
151	95◄─►189	llama-3.1-nemotron-70b-instruct	1327	±27	491	Nvidia	Llama 3.1
152	99◄─►187	qwen2.5-plus-1127	1326	±24	590	Alibaba	Proprietary
153	90◄─►196	qwen3-32b	1325	±33	285	Alibaba	Apache 2.0
154	106◄─►182	qwen3-30b-a3b	1325	±14	1,824	Alibaba	Apache 2.0
155	100◄─►188	command-r-plus-08-2024	1324	±23	592	Cohere	CC-BY-NC-4.0
156	106◄─►183	gemma-3n-e4b-it	1324	±16	1,465	Google	Gemma
157	100◄─►189	step-1o-turbo-202506	1323	±23	672	StepFun	Proprietary
158	106◄─►184	nemotron-4-340b-instruct	1322	±18	1,178	Nvidia	NVIDIA Open Model
159	101◄─►191	nova-2-lite	1321	±24	667	Amazon	Proprietary
160	116◄─►182	gpt-4-1106-preview	1320	±11	5,588	OpenAI	Proprietary
161	116◄─►184	command-r-plus	1319	±12	4,417	Cohere	CC-BY-NC-4.0
162	96◄─►199	nvidia-nemotron-3-nano-30b-a3b-bf16	1318	±34	303	Nvidia	NVIDIA Open Model
163	103◄─►195	glm-4-0520	1318	±24	560	Zhipu AI	Proprietary
164	118◄─►184	gemma-2-27b-it	1316	±10	4,474	Google	Gemma license
165	100◄─►200	qwen2.5-coder-32b-instruct	1313	±34	273	Alibaba	Apache 2.0
166	122◄─►190	claude-3-sonnet-20240229	1311	±11	6,080	Anthropic	Proprietary
167	122◄─►191	mistral-small-3.1-24b-instruct-2503	1310	±13	2,211	Mistral	Apache 2.0
168	123◄─►191	gemini-1.5-flash-001	1310	±12	3,786	Google	Proprietary
169	115◄─►199	command-r-08-2024	1308	±24	569	Cohere	CC-BY-NC-4.0
170	129◄─►191	llama-3-70b-instruct	1307	±10	8,348	Meta	Llama 3 Community
171	118◄─►200	magistral-medium-2506	1304	±22	861	Mistral	Proprietary
172	129◄─►197	gpt-4-0314	1304	±14	2,902	OpenAI	Proprietary
173	129◄─►197	c4ai-aya-expanse-32b	1303	±14	1,742	Cohere	CC-BY-NC-4.0
174	126◄─►199	phi-4	1302	±16	1,344	Microsoft	MIT
175	138◄─►199	gemini-1.5-flash-8b-001	1298	±13	2,140	Google	Proprietary
176	119◄─►208	hunyuan-large-vision	1294	±32	395	Tencent	Proprietary
177	118◄─►209	ibm-granite-h-small	1293	±36	312	IBM	Apache 2.0
178	152◄─►200	claude-3-haiku-20240307	1293	±10	6,819	Anthropic	Proprietary
179	124◄─►208	reka-flash-20240904	1291	±30	415	Reka AI	Proprietary
180	129◄─►206	jamba-1.5-mini	1290	±25	531	AI21 Labs	Jamba Open
181	126◄─►208	ring-flash-2.0	1290	±29	437	Ant Group	MIT
182	157◄─►200	gemma-2-9b-it	1289	±11	3,251	Google	Gemma license
183	154◄─►202	command-r	1289	±13	3,077	Cohere	CC-BY-NC-4.0
184	141◄─►206	reka-flash-21b-20240226-online	1288	±21	880	Reka AI	Proprietary
185	151◄─►205	amazon-nova-lite-v1.0	1286	±18	1,082	Amazon	Proprietary
186	129◄─►213	olmo-3-32b-think	1285	±32	387	Allen AI	Apache 2.0
187	166◄─►204	gpt-4-0613	1283	±12	4,702	OpenAI	Proprietary
188	151◄─►207	deepseek-coder-v2	1283	±20	890	DeepSeek AI	DeepSeek License
189	166◄─►204	qwen2-72b-instruct	1282	±14	2,263	Alibaba	Qianwen LICENSE
190	161◄─►209	mistral-small-24b-instruct-2501	1279	±21	870	Mistral	Apache 2.0
191	129◄─►220	olmo-2-0325-32b-instruct	1277	±41	202	Allen AI	Apache-2.0
192	168◄─►207	mistral-large-2402	1277	±13	3,317	Mistral	Proprietary
193	167◄─►209	qwen1.5-110b-chat	1276	±17	1,511	Alibaba	Qianwen LICENSE
194	144◄─►217	ministral-8b-2410	1274	±34	324	Mistral	MRL
195	166◄─►213	gemini-pro-dev-api	1273	±21	972	Google	Proprietary
196	170◄─►213	reka-flash-21b-20240226	1269	±18	1,353	Reka AI	Proprietary
197	170◄─►213	amazon-nova-micro-v1.0	1269	±18	1,085	Amazon	Proprietary
198	166◄─►217	c4ai-aya-expanse-8b	1269	±25	551	Cohere	CC-BY-NC-4.0
199	174◄─►213	qwen1.5-72b-chat	1268	±15	2,096	Alibaba	Qianwen LICENSE
200	178◄─►213	mixtral-8x22b-instruct-v0.1	1264	±13	2,810	Mistral	Apache 2.0
201	178◄─►217	mistral-medium	1261	±16	1,811	Mistral	Proprietary
202	179◄─►214	gpt-3.5-turbo-0125	1261	±12	3,586	OpenAI	Proprietary
203	159◄─►238	granite-3.1-8b-instruct	1258	±42	215	IBM	Apache 2.0
204	179◄─►217	yi-1.5-34b-chat	1257	±16	1,515	01 AI	Apache-2.0
205	186◄─►217	llama-3-8b-instruct	1252	±11	5,589	Meta	Llama 3 Community
206	189◄─►220	llama-3.1-8b-instruct	1248	±12	2,890	Meta	Llama 3.1 Community
207	182◄─►240	openchat-3.5	1239	±28	467	OpenChat	Apache-2.0
208	192◄─►237	qwen1.5-32b-chat	1237	±18	1,234	Alibaba	Qianwen LICENSE
209	199◄─►233	mixtral-8x7b-instruct-v0.1	1233	±12	3,962	Mistral	Apache 2.0
210	184◄─►244	gemini-pro	1230	±34	308	Google	Proprietary
211	181◄─►245	zephyr-orpo-141b-A35b-v0.1	1230	±38	241	HuggingFace	Apache 2.0
212	198◄─►240	yi-34b-chat	1228	±22	857	01 AI	Yi License
213	192◄─►244	wizardlm-70b	1227	±29	434	Microsoft	Llama 2 Community
214	192◄─►244	tulu-2-dpo-70b	1225	±30	378	AllenAI/UW	AI2 ImpACT Low-risk
215	206◄─►239	gemma-2-2b-it	1224	±12	2,662	Google	Gemma license
216	192◄─►250	openhermes-2.5-mistral-7b	1221	±36	275	NousResearch	Apache-2.0
217	206◄─►240	phi-3-medium-4k-instruct	1219	±16	1,479	Microsoft	MIT
218	206◄─►241	dbrx-instruct-preview	1218	±16	1,751	Databricks	DBRX LICENSE
219	206◄─►242	gemma-1.1-7b-it	1217	±17	1,421	Google	Gemma license
220	204◄─►244	gpt-3.5-turbo-1106	1216	±22	944	OpenAI	Proprietary
221	204◄─►246	openchat-3.5-0106	1214	±24	637	OpenChat	Apache-2.0
222	206◄─►244	qwen1.5-14b-chat	1213	±19	1,045	Alibaba	Qianwen LICENSE
223	206◄─►245	starling-lm-7b-beta	1213	±21	879	Nexusflow	Apache-2.0
224	199◄─►253	deepseek-llm-67b-chat	1211	±35	300	DeepSeek AI	DeepSeek License
225	204◄─►250	starling-lm-7b-alpha	1210	±27	504	UC Berkeley	CC-BY-NC-4.0
226	206◄─►246	snowflake-arctic-instruct	1207	±18	1,539	Snowflake	Apache 2.0
227	199◄─►255	hunyuan-standard-256k	1204	±44	200	Tencent	Proprietary
228	207◄─►250	phi-3-small-8k-instruct	1202	±18	1,189	Microsoft	MIT
229	206◄─►253	wizardlm-13b	1202	±32	365	Microsoft	Llama 2 Community
230	206◄─►254	granite-3.0-8b-instruct	1201	±34	428	IBM	Apache 2.0
231	208◄─►253	vicuna-33b	1198	±19	1,246	LMSYS	Non-commercial
232	206◄─►253	internlm2_5-20b-chat	1198	±23	685	InternLM	Other
233	210◄─►252	llama-2-70b-chat	1196	±15	2,076	Meta	Llama 2 Community
234	207◄─►253	zephyr-7b-beta	1194	±26	621	HuggingFace	MIT
235	206◄─►255	llama-3.2-3b-instruct	1194	±28	506	Meta	Llama 3.2
236	209◄─►253	mistral-7b-instruct-v0.2	1192	±20	978	Mistral	Apache-2.0
237	206◄─►257	solar-10.7b-instruct-v1.0	1191	±40	219	Upstage AI	CC-BY-NC-4.0
238	206◄─►255	granite-3.0-2b-instruct	1190	±32	437	IBM	Apache 2.0
239	206◄─►260	qwen1.5-7b-chat	1186	±41	231	Alibaba	Qianwen LICENSE
240	207◄─►260	qwen-14b-chat	1182	±38	274	Alibaba	Qianwen LICENSE
241	213◄─►255	vicuna-13b	1180	±22	902	LMSYS	Llama 2 Community
242	214◄─►261	palm-2	1168	±32	428	Google	Proprietary
243	215◄─►261	codellama-34b-instruct	1166	±32	384	Meta	Llama 2 Community
244	220◄─►261	gemma-7b-it	1165	±29	461	Google	Gemma license
245	227◄─►261	llama-2-13b-chat	1162	±21	1,007	Meta	Llama 2 Community
246	228◄─►261	phi-3-mini-4k-instruct	1161	±19	1,127	Microsoft	MIT
247	224◄─►261	phi-3-mini-4k-instruct-june-2024	1161	±25	708	Microsoft	MIT
248	224◄─►261	mistral-7b-instruct	1160	±29	489	Mistral	Apache 2.0
249	215◄─►263	qwq-32b-preview	1157	±43	215	Alibaba	Apache 2.0
250	224◄─►262	llama-3.2-1b-instruct	1155	±30	489	Meta	Llama 3.2
251	222◄─►262	vicuna-7b	1155	±35	306	LMSYS	Llama 2 Community
252	227◄─►262	qwen1.5-4b-chat	1150	±32	390	Alibaba	Qianwen LICENSE
253	224◄─►263	gemma-2b-it	1147	±38	273	Google	Gemma license
254	235◄─►262	llama-2-7b-chat	1143	±22	762	Meta	Llama 2 Community
255	240◄─►263	phi-3-mini-128k-instruct	1126	±22	1,039	Microsoft	MIT
256	239◄─►263	gemma-1.1-2b-it	1126	±28	577	Google	Gemma license
257	239◄─►264	stripedhyena-nous-7b	1122	±36	309	Together AI	Apache 2.0
258	234◄─►264	RWKV-4-Raven-14B	1120	±48	190	RWKV	Apache 2.0
259	240◄─►264	olmo-7b-instruct	1111	±35	301	Allen AI	Apache-2.0
260	240◄─►264	alpaca-13b	1106	±44	230	Stanford	Non-commercial
261	242◄─►264	chatglm3-6b	1102	±41	268	Tsinghua	Apache-2.0
262	249◄─►265	koala-13b	1090	±41	248	UC Berkeley	Non-commercial
263	253◄─►265	oasst-pythia-12b	1076	±41	266	OpenAssistant	Apache 2.0
264	257◄─►265	fastchat-t5-3b	1040	±47	184	LMSYS	Apache 2.0
265	262◄─►265	chatglm-6b	1002	±48	195	Tsinghua	Non-commercial

Text Arena

Default Leaderboard Plots

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

Confidence Intervals on Model Strength (via Bootstrapping)

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

Battle Count for Each Combination of Models (without Ties)