Text Arena

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

Last Updated

Jan 16, 2026

Total Votes

725,974

Total Models

297

/

Style Control

	Rank Spread
1	1◄─►1	gemini-3-pro	1489	±11	3,877	Google	Proprietary
2	2◄─►10	claude-opus-4-5-20251101	1464	±12	2,925	Anthropic	Proprietary
3	2◄─►13	gemini-3-flash	1462	±14	1,956	Google	Proprietary
4	2◄─►14	claude-opus-4-5-20251101-thinking-32k	1456	±12	2,727	Anthropic	Proprietary
5	2◄─►14	gemini-2.5-pro	1451	±7	11,664	Google	Proprietary
6	2◄─►17	claude-sonnet-4-5-20250929	1446	±9	4,759	Anthropic	Proprietary
7	2◄─►18	claude-sonnet-4-5-20250929-thinking-32k	1445	±9	5,109	Anthropic	Proprietary
8	2◄─►18	claude-opus-4-1-20250805-thinking-16k	1444	±8	6,671	Anthropic	Proprietary
9	2◄─►21	gemini-3-flash (thinking-minimal)	1443	±17	1,290	Google	Proprietary
10	2◄─►19	grok-4.1-thinking	1442	±10	3,863	xAI	Proprietary
11	3◄─►18	claude-opus-4-1-20250805	1441	±7	8,893	Anthropic	Proprietary
12	3◄─►21	gpt-4.5-preview-2025-02-27	1437	±12	2,618	OpenAI	Proprietary
13	4◄─►21	gpt-5.1-high	1436	±11	3,381	OpenAI	Proprietary
14	6◄─►23	claude-opus-4-20250514-thinking-16k	1428	±9	4,736	Anthropic	Proprietary
15	6◄─►26	grok-4.1	1428	±10	4,150	xAI	Proprietary
16	3◄─►35	ernie-5.0-0110	1427	±20	797	Baidu	Proprietary
17	6◄─►35	ernie-5.0-preview-1203	1423	±16	1,478	Baidu	Proprietary
18	11◄─►26	chatgpt-4o-latest-20250326	1421	±6	10,201	OpenAI	Proprietary
19	11◄─►34	claude-opus-4-20250514	1418	±8	5,770	Anthropic	Proprietary
20	7◄─►66	deepseek-v3.1-terminus	1410	±27	459	DeepSeek	MIT
21	10◄─►61	ernie-5.0-preview-1022	1409	±23	669	Baidu	Proprietary
22	14◄─►50	deepseek-v3.1-thinking	1409	±14	1,709	DeepSeek	MIT
23	15◄─►49	gpt-5.1	1408	±11	3,565	OpenAI	Proprietary
24	15◄─►59	deepseek-v3.2-exp	1404	±15	1,517	DeepSeek	MIT
25	15◄─►60	glm-4.7	1403	±16	1,432	Z.ai	MIT
26	17◄─►53	grok-4-1-fast-reasoning	1403	±11	2,932	xAI	Proprietary
27	17◄─►50	gpt-4.1-2025-04-14	1403	±8	6,870	OpenAI	Proprietary
28	17◄─►52	glm-4.6	1401	±9	4,525	Z.ai	MIT
29	17◄─►59	deepseek-v3.2	1401	±13	2,595	DeepSeek	MIT
30	17◄─►52	grok-3-preview-02-24	1401	±9	4,974	xAI	Proprietary
31	14◄─►73	gpt-5.2	1399	±23	693	OpenAI	Proprietary
32	20◄─►53	gemini-2.5-flash	1398	±6	11,386	Google	Proprietary
33	20◄─►59	grok-4-0709	1397	±8	5,572	xAI	Proprietary
34	17◄─►71	gpt-5.2-high	1396	±19	1,117	OpenAI	Proprietary
35	20◄─►60	claude-sonnet-4-20250514-thinking-32k	1396	±9	4,580	Anthropic	Proprietary
36	17◄─►71	qwen3-max-2025-09-23	1396	±17	1,155	Alibaba	Proprietary
37	20◄─►62	qwen3-max-preview	1396	±10	3,733	Alibaba	Proprietary
38	20◄─►62	claude-3-7-sonnet-20250219-thinking-32k	1395	±8	5,473	Anthropic	Proprietary
39	20◄─►62	gpt-5-chat	1394	±10	4,022	OpenAI	Proprietary
40	20◄─►63	kimi-k2-thinking-turbo	1394	±10	3,633	Moonshot	Modified MIT
41	20◄─►70	deepseek-v3.1	1393	±13	2,069	DeepSeek	MIT
42	20◄─►69	deepseek-v3.2-thinking	1393	±13	2,249	DeepSeek	MIT
43	17◄─►73	deepseek-v3.2-exp-thinking	1393	±18	1,161	DeepSeek	MIT
44	20◄─►64	deepseek-v3-0324	1391	±8	6,329	DeepSeek	MIT
45	20◄─►73	deepseek-r1-0528	1388	±12	2,662	DeepSeek	MIT
46	23◄─►72	claude-sonnet-4-20250514	1385	±9	5,321	Anthropic	Proprietary
47	27◄─►73	o3-2025-04-16	1383	±7	8,029	OpenAI	Proprietary
48	25◄─►74	o1-2024-12-17	1383	±9	4,646	OpenAI	Proprietary
49	27◄─►73	qwen3-235b-a22b-instruct-2507	1383	±7	8,198	Alibaba	Apache 2.0
50	20◄─►83	hunyuan-t1-20250711	1383	±23	643	Tencent	Proprietary
51	18◄─►91	deepseek-v3.1-terminus-thinking	1382	±28	444	DeepSeek	MIT
52	27◄─►73	mistral-medium-2508	1382	±7	7,633	Mistral	Proprietary
53	20◄─►81	grok-4-fast-chat	1381	±19	994	xAI	Proprietary
54	27◄─►77	gemini-2.5-flash-preview-09-2025	1381	±10	4,318	Google	Proprietary
55	23◄─►77	grok-4-fast-reasoning	1381	±12	2,403	xAI	Proprietary
56	21◄─►79	kimi-k2-0905-preview	1380	±15	1,482	Moonshot	Modified MIT
57	27◄─►77	gpt-5-high	1380	±10	4,352	OpenAI	Proprietary
58	30◄─►77	claude-haiku-4-5-20251001	1379	±9	4,915	Anthropic	Proprietary
59	36◄─►77	claude-3-7-sonnet-20250219	1377	±8	6,256	Anthropic	Proprietary
60	33◄─►79	deepseek-r1	1376	±10	3,295	DeepSeek	MIT
61	32◄─►79	glm-4.5	1376	±11	3,212	Z.ai	MIT
62	38◄─►79	gemini-2.5-flash-lite-preview-06-17-thinking	1374	±9	4,414	Google	Proprietary
63	27◄─►91	qwen3-235b-a22b-thinking-2507	1371	±18	1,146	Alibaba	Apache 2.0
64	40◄─►81	qwen3-235b-a22b-no-thinking	1371	±9	4,888	Alibaba	Apache 2.0
65	43◄─►79	claude-3-5-sonnet-20241022	1371	±6	11,986	Anthropic	Proprietary
66	38◄─►84	mistral-large-3	1371	±12	2,393	Mistral	Apache 2.0
67	41◄─►83	kimi-k2-0711-preview	1370	±10	3,690	Moonshot	Modified MIT
68	20◄─►109	hunyuan-vision-1.5-thinking	1368	±36	259	Tencent	Proprietary
69	37◄─►91	mimo-v2-flash (non-thinking)	1367	±16	1,434	Xiaomi	MIT
70	39◄─►91	hunyuan-turbos-20250416	1367	±15	1,578	Tencent	Proprietary
71	44◄─►85	o1-preview	1367	±10	4,506	OpenAI	Proprietary
72	39◄─►92	qwen3-vl-235b-a22b-instruct	1364	±17	1,371	Alibaba	Apache 2.0
73	50◄─►91	qwen3-coder-480b-a35b-instruct	1364	±10	3,456	Alibaba	Apache 2.0
74	51◄─►91	mistral-medium-2505	1364	±9	4,428	Mistral	Proprietary
75	56◄─►91	gemini-1.5-pro-002	1360	±7	8,065	Google	Proprietary
76	51◄─►92	mai-1-preview	1359	±13	2,243	Microsoft AI	Proprietary
77	56◄─►91	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1358	±9	5,237	Google	Proprietary
78	61◄─►93	qwen2.5-max	1354	±8	5,130	Alibaba	Proprietary
79	38◄─►123	glm-4.6v	1354	±29	398	Z.ai	MIT
80	63◄─►97	deepseek-v3	1351	±10	3,624	DeepSeek	DeepSeek
81	67◄─►97	gemma-3-27b-it	1349	±8	6,591	Google	Gemma
82	67◄─►97	gemini-2.0-flash-001	1349	±8	6,488	Google	Proprietary
83	67◄─►97	gpt-4.1-mini-2025-04-14	1348	±9	5,415	OpenAI	Proprietary
84	51◄─►124	amazon-nova-experimental-chat-12-10	1347	±25	549	Amazon	Proprietary
85	67◄─►101	gemini-2.0-flash-lite-preview-02-05	1347	±9	4,100	Google	Proprietary
86	61◄─►118	qwen3-vl-235b-a22b-thinking	1346	±18	1,004	Alibaba	Apache 2.0
87	67◄─►107	gemini-advanced-0514	1345	±10	7,026	Google	Proprietary
88	75◄─►108	o4-mini-2025-04-16	1340	±8	6,072	OpenAI	Proprietary
89	67◄─►124	minimax-m2.1-preview	1339	±17	1,351	MiniMax	MIT
90	78◄─►109	gpt-4o-2024-05-13	1339	±7	16,599	OpenAI	Proprietary
91	65◄─►126	step-2-16k-exp-202412	1338	±21	748	StepFun	Proprietary
92	78◄─►117	command-a-03-2025	1336	±7	7,860	Cohere	CC-BY-NC-4.0
93	77◄─►123	grok-3-mini-beta	1335	±11	2,998	xAI	Proprietary
94	66◄─►131	gemma-3-12b-it	1335	±23	600	Google	Gemma
95	63◄─►139	llama-3.1-nemotron-ultra-253b-v1	1334	±27	444	Nvidia	Nvidia Open Model
96	78◄─►125	grok-3-mini-high	1333	±13	2,201	xAI	Proprietary
97	78◄─►126	longcat-flash-chat	1330	±16	1,381	Meituan	MIT
98	82◄─►125	glm-4.5-air	1329	±10	4,055	Z.ai	MIT
99	83◄─►125	gpt-4o-2024-08-06	1328	±8	6,756	OpenAI	Proprietary
100	82◄─►125	qwen3-235b-a22b	1328	±10	3,781	Alibaba	Apache 2.0
101	83◄─►126	gpt-5-mini-high	1327	±10	3,526	OpenAI	Proprietary
102	83◄─►126	qwen3-30b-a3b-instruct-2507	1325	±11	3,050	Alibaba	Apache 2.0
103	85◄─►126	gemini-1.5-pro-001	1324	±8	11,800	Google	Proprietary
104	87◄─►126	gpt-4-turbo-2024-04-09	1324	±8	14,398	OpenAI	Proprietary
105	82◄─►135	qwen3-next-80b-a3b-thinking	1324	±14	1,794	Alibaba	Apache 2.0
106	84◄─►132	mistral-small-2506	1323	±12	2,364	Mistral	Apache 2.0
107	87◄─►126	minimax-m1	1323	±9	4,874	MiniMax	Apache 2.0
108	82◄─►144	glm-4-plus-0111	1319	±19	920	Zhipu	Proprietary
109	89◄─►131	grok-2-2024-08-13	1319	±7	9,339	xAI	Proprietary
110	83◄─►143	qwen-plus-0125	1319	±18	933	Alibaba	Proprietary
111	87◄─►139	qwen3-next-80b-a3b-instruct	1318	±11	2,946	Alibaba	Apache 2.0
112	83◄─►157	glm-4.5v	1315	±23	632	Z.ai	MIT
113	91◄─►141	o3-mini-high	1313	±11	3,067	OpenAI	Proprietary
114	88◄─►155	deepseek-v2.5-1210	1312	±17	1,088	DeepSeek	DeepSeek
115	97◄─►143	llama-4-maverick-17b-128e-instruct	1310	±8	5,428	Meta	Llama 4
116	87◄─►163	intellect-3	1309	±22	759	Prime Intellect	MIT
117	83◄─►168	nvidia-llama-3.3-nemotron-super-49b-v1.5	1309	±28	406	Nvidia	Nvidia Open
118	89◄─►161	gpt-4.1-nano-2025-04-14	1308	±18	1,008	OpenAI	Proprietary
119	87◄─►165	qwen3-32b	1308	±22	622	Alibaba	Apache 2.0
120	89◄─►164	step-3	1307	±21	795	StepFun	Apache 2.0
121	104◄─►147	llama-3.1-405b-instruct-fp8	1306	±8	8,950	Meta	Llama 3.1 Community
122	87◄─►167	hunyuan-large-2025-02-10	1306	±24	568	Tencent	Proprietary
123	104◄─►150	claude-3-5-sonnet-20240620	1305	±7	12,430	Anthropic	Proprietary
124	87◄─►170	hunyuan-turbos-20250226	1304	±26	425	Tencent	Proprietary
125	87◄─►169	hunyuan-turbo-0110	1304	±25	452	Tencent	Proprietary
126	107◄─►149	claude-3-5-haiku-20241022	1304	±6	10,156	Anthropic	Proprietary
127	108◄─►152	o3-mini	1303	±7	8,444	OpenAI	Proprietary
128	107◄─►154	llama-3.1-405b-instruct-bf16	1303	±7	6,518	Meta	Llama 3.1 Community
129	104◄─►159	gemma-3n-e4b-it	1301	±11	3,068	Google	Gemma
130	108◄─►157	gemini-1.5-flash-002	1301	±9	5,018	Google	Proprietary
131	89◄─►175	llama-3.3-nemotron-49b-super-v1	1300	±27	430	Nvidia	Nvidia
132	107◄─►161	yi-lightning	1300	±10	3,782	01 AI	Proprietary
133	108◄─►163	qwq-32b	1297	±10	3,847	Alibaba	Apache 2.0
134	110◄─►160	gpt-4o-mini-2024-07-18	1296	±7	10,501	OpenAI	Proprietary
135	93◄─►176	olmo-3.1-32b-instruct	1296	±26	533	Allen AI	Apache 2.0
136	104◄─►169	amazon-nova-experimental-chat-11-10	1296	±16	1,357	Amazon	Proprietary
137	104◄─►172	step-1o-turbo-202506	1295	±18	1,115	StepFun	Proprietary
138	89◄─►185	amazon-nova-experimental-chat-10-09	1294	±32	319	Amazon	Proprietary
139	113◄─►163	gemma-2-27b-it	1294	±7	11,430	Google	Gemma license
140	111◄─►167	llama-4-scout-17b-16e-instruct	1293	±10	4,001	Meta	Llama
141	111◄─►167	glm-4-plus	1292	±10	3,803	Zhipu AI	Proprietary
142	118◄─►167	claude-3-opus-20240229	1289	±6	28,394	Anthropic	Proprietary
143	114◄─►169	qwen3-30b-a3b	1289	±10	3,609	Alibaba	Apache 2.0
144	117◄─►168	mistral-large-2407	1289	±8	6,693	Mistral	Mistral Research
145	119◄─►167	llama-3.3-70b-instruct	1288	±7	8,258	Meta	Llama-3.3
146	118◄─►169	gpt-4-1106-preview	1288	±8	15,576	OpenAI	Proprietary
147	106◄─►182	hunyuan-large-vision	1288	±23	674	Tencent	Proprietary
148	115◄─►173	qwen-max-0919	1287	±12	2,358	Alibaba	Qwen
149	108◄─►182	minimax-m2	1286	±21	820	MiniMax	Apache 2.0
150	114◄─►176	gemma-2-9b-it-simpo	1285	±15	1,671	Princeton	MIT
151	120◄─►174	gpt-oss-120b	1284	±10	3,968	OpenAI	Apache 2.0
152	123◄─►172	o1-mini	1283	±7	7,861	OpenAI	Proprietary
153	116◄─►180	amazon-nova-experimental-chat-10-20	1282	±16	1,490	Amazon	Proprietary
154	123◄─►174	gpt-4-0125-preview	1282	±8	13,941	OpenAI	Proprietary
155	117◄─►182	magistral-medium-2506	1280	±16	1,462	Mistral	Proprietary
156	115◄─►187	llama-3.1-nemotron-70b-instruct	1280	±19	1,000	Nvidia	Llama 3.1
157	110◄─►189	hunyuan-standard-2025-02-10	1279	±24	590	Tencent	Proprietary
158	129◄─►177	mistral-large-2411	1278	±9	4,441	Mistral	MRL
159	114◄─►189	gemma-3-4b-it	1278	±22	667	Google	Gemma
160	122◄─►185	qwen2.5-plus-1127	1276	±14	1,589	Alibaba	Proprietary
161	130◄─►178	mistral-small-3.1-24b-instruct-2503	1276	±9	4,350	Mistral	Apache 2.0
162	122◄─►187	nova-2-lite	1276	±15	1,632	Amazon	Proprietary
163	136◄─►179	grok-2-mini-2024-08-13	1274	±8	7,925	xAI	Proprietary
164	120◄─►190	ling-flash-2.0	1273	±20	835	Ant Group	MIT
165	131◄─►187	athene-70b-0725	1273	±11	3,098	NexusFlow	CC-BY-NC-4.0
166	126◄─►191	reka-core-20240904	1270	±18	1,037	Reka AI	Proprietary
167	143◄─►188	deepseek-v2.5	1267	±11	3,451	DeepSeek	DeepSeek
168	145◄─►187	gpt-4-0613	1267	±8	13,932	OpenAI	Proprietary
169	138◄─►192	command-r-plus-08-2024	1265	±15	1,474	Cohere	CC-BY-NC-4.0
170	148◄─►188	gemini-1.5-flash-001	1265	±8	9,032	Google	Proprietary
171	126◄─►198	llama-3.1-nemotron-51b-instruct	1263	±26	482	Nvidia	Llama 3.1
172	142◄─►195	jamba-1.5-large	1263	±16	1,379	AI21 Labs	Jamba Open
173	131◄─►197	olmo-3-32b-think	1262	±22	804	Allen AI	Apache 2.0
174	153◄─►190	gemma-2-9b-it	1260	±7	8,342	Google	Gemma license
175	152◄─►190	llama-3.1-70b-instruct	1260	±8	8,250	Meta	Llama 3.1 Community
176	143◄─►198	ring-flash-2.0	1258	±20	891	Ant Group	MIT
177	158◄─►194	qwen2.5-72b-instruct	1256	±8	5,680	Alibaba	Qwen
178	158◄─►193	llama-3-70b-instruct	1256	±7	22,749	Meta	Llama 3 Community
179	155◄─►195	athene-v2-chat	1256	±10	3,716	NexusFlow	NexusFlow
180	155◄─►195	gpt-4-0314	1255	±10	8,230	OpenAI	Proprietary
181	149◄─►200	gpt-5-nano-high	1253	±20	930	OpenAI	Proprietary
182	146◄─►204	llama-3.1-tulu-3-70b	1249	±25	441	Ai2	Llama 3.1
183	168◄─►198	claude-3-sonnet-20240229	1247	±8	15,593	Anthropic	Proprietary
184	160◄─►200	nvidia-nemotron-3-nano-30b-a3b-bf16	1246	±15	1,697	Nvidia	NVIDIA Open Model
185	151◄─►206	ibm-granite-h-small	1246	±23	709	IBM	Apache 2.0
186	158◄─►202	olmo-3.1-32b-think	1245	±18	1,275	Allen AI	Apache 2.0
187	160◄─►202	reka-flash-20240904	1244	±17	1,037	Reka AI	Proprietary
188	164◄─►202	glm-4-0520	1243	±15	1,547	Zhipu AI	Proprietary
189	173◄─►200	gemini-1.5-flash-8b-001	1240	±9	5,029	Google	Proprietary
190	171◄─►200	nemotron-4-340b-instruct	1240	±12	3,153	Nvidia	NVIDIA Open Model
191	174◄─►200	amazon-nova-pro-v1.0	1239	±9	3,946	Amazon	Proprietary
192	175◄─►200	command-r-plus	1238	±9	11,009	Cohere	CC-BY-NC-4.0
193	166◄─►208	gpt-oss-20b	1237	±18	1,290	OpenAI	Apache 2.0
194	179◄─►208	c4ai-aya-expanse-32b	1230	±10	3,850	Cohere	CC-BY-NC-4.0
195	178◄─►210	mistral-small-24b-instruct-2501	1229	±12	2,417	Mistral	Apache 2.0
196	154◄─►230	mercury	1226	±41	267	Inception AI	Proprietary
197	172◄─►220	olmo-2-0325-32b-instruct	1226	±25	568	Allen AI	Apache-2.0
198	182◄─►211	qwen2-72b-instruct	1225	±9	5,505	Alibaba	Qianwen LICENSE
199	182◄─►211	amazon-nova-lite-v1.0	1223	±10	3,037	Amazon	Proprietary
200	178◄─►220	ministral-8b-2410	1223	±22	678	Mistral	MRL
201	192◄─►212	claude-3-haiku-20240307	1216	±7	16,721	Anthropic	Proprietary
202	188◄─►224	jamba-1.5-mini	1213	±16	1,399	AI21 Labs	Jamba Open
203	193◄─►219	mistral-large-2402	1212	±9	9,058	Mistral	Proprietary
204	193◄─►219	phi-4	1212	±10	4,068	Microsoft	MIT
205	191◄─►224	command-r-08-2024	1211	±16	1,421	Cohere	CC-BY-NC-4.0
206	188◄─►227	qwen2.5-coder-32b-instruct	1209	±19	835	Alibaba	Apache 2.0
207	195◄─►226	deepseek-coder-v2	1205	±13	2,271	DeepSeek	DeepSeek License
208	195◄─►227	gemini-pro-dev-api	1204	±14	3,045	Google	Proprietary
209	198◄─►227	amazon-nova-micro-v1.0	1200	±11	3,060	Amazon	Proprietary
210	196◄─►230	wizardlm-70b	1199	±17	1,779	Microsoft	Llama 2 Community
211	192◄─►233	llama-3.1-tulu-3-8b	1199	±25	471	Ai2	Llama 3.1
212	199◄─►227	llama-3-8b-instruct	1198	±8	15,364	Meta	Llama 3 Community
213	199◄─►229	command-r	1197	±10	7,837	Cohere	CC-BY-NC-4.0
214	191◄─►238	hunyuan-standard-256k	1196	±29	357	Tencent	Proprietary
215	199◄─►230	mistral-medium	1195	±11	5,549	Mistral	Proprietary
216	199◄─►230	qwen1.5-110b-chat	1195	±12	3,678	Alibaba	Qianwen LICENSE
217	201◄─►230	mixtral-8x22b-instruct-v0.1	1192	±9	7,448	Mistral	Apache 2.0
218	199◄─►232	c4ai-aya-expanse-8b	1191	±15	1,530	Cohere	CC-BY-NC-4.0
219	203◄─►230	gpt-3.5-turbo-0125	1190	±9	9,693	OpenAI	Proprietary
220	203◄─►231	qwen1.5-72b-chat	1190	±10	5,889	Alibaba	Qianwen LICENSE
221	199◄─►238	openchat-3.5	1186	±18	1,454	OpenChat	Apache-2.0
222	199◄─►241	gemini-pro	1185	±21	953	Google	Proprietary
223	205◄─►232	gemma-2-2b-it	1185	±8	7,095	Google	Gemma license
224	203◄─►238	reka-flash-21b-20240226-online	1183	±14	2,118	Reka AI	Proprietary
225	210◄─►234	llama-3.1-8b-instruct	1180	±8	7,346	Meta	Llama 3.1 Community
226	210◄─►241	reka-flash-21b-20240226	1176	±12	3,490	Reka AI	Proprietary
227	211◄─►245	vicuna-33b	1174	±12	4,010	LMSYS	Non-commercial
228	203◄─►257	granite-3.1-8b-instruct	1172	±27	450	IBM	Apache 2.0
229	205◄─►256	zephyr-orpo-141b-A35b-v0.1	1170	±23	635	HuggingFace	Apache 2.0
230	220◄─►253	dbrx-instruct-preview	1164	±12	4,808	Databricks	DBRX LICENSE
231	221◄─►254	yi-1.5-34b-chat	1161	±11	3,602	01 AI	Apache-2.0
232	222◄─►254	mixtral-8x7b-instruct-v0.1	1161	±8	11,172	Mistral	Apache 2.0
233	217◄─►260	openhermes-2.5-mistral-7b	1159	±22	811	NousResearch	Apache-2.0
234	222◄─►258	yi-34b-chat	1155	±14	2,378	01 AI	Yi License
235	206◄─►267	falcon-180b-chat	1154	±37	270	TII	Falcon-180B TII License
236	222◄─►259	gpt-3.5-turbo-1106	1154	±15	2,828	OpenAI	Proprietary
237	227◄─►258	phi-3-medium-4k-instruct	1152	±11	3,736	Microsoft	MIT
238	218◄─►265	granite-3.1-2b-instruct	1149	±29	443	IBM	Apache 2.0
239	228◄─►260	gemma-1.1-7b-it	1149	±12	3,408	Google	Gemma license
240	227◄─►260	openchat-3.5-0106	1148	±15	1,859	OpenChat	Apache-2.0
241	225◄─►261	tulu-2-dpo-70b	1148	±19	1,125	AllenAI/UW	AI2 ImpACT Low-risk
242	225◄─►261	llama-3.2-3b-instruct	1146	±20	1,070	Meta	Llama 3.2
243	228◄─►261	snowflake-arctic-instruct	1143	±12	4,777	Snowflake	Apache 2.0
244	228◄─►261	wizardlm-13b	1142	±18	1,375	Microsoft	Llama 2 Community
245	227◄─►267	solar-10.7b-instruct-v1.0	1140	±24	698	Upstage AI	CC-BY-NC-4.0
246	229◄─►262	qwen1.5-14b-chat	1138	±14	2,392	Alibaba	Qianwen LICENSE
247	228◄─►265	zephyr-7b-beta	1138	±16	1,993	HuggingFace	MIT
248	228◄─►265	starling-lm-7b-alpha	1138	±16	1,701	UC Berkeley	CC-BY-NC-4.0
249	228◄─►267	granite-3.0-8b-instruct	1137	±21	895	IBM	Apache 2.0
250	228◄─►269	nous-hermes-2-mixtral-8x7b-dpo	1137	±23	616	NousResearch	Apache-2.0
251	225◄─►273	guanaco-33b	1137	±28	515	UW	Non-commercial
252	222◄─►279	dolphin-2.2.1-mistral-7b	1136	±34	291	Cognitive Computations	Apache-2.0
253	228◄─►268	deepseek-llm-67b-chat	1136	±22	789	DeepSeek	DeepSeek License
254	231◄─►265	phi-3-small-8k-instruct	1135	±13	2,400	Microsoft	MIT
255	231◄─►267	internlm2_5-20b-chat	1134	±16	1,432	InternLM	Other
256	227◄─►279	mpt-30b-chat	1134	±29	452	MosaicML	CC-BY-NC-SA-4.0
257	233◄─►265	qwen1.5-32b-chat	1133	±12	3,024	Alibaba	Qianwen LICENSE
258	235◄─►268	vicuna-13b	1127	±13	3,346	LMSYS	Llama 2 Community
259	232◄─►282	llama2-70b-steerlm-chat	1121	±25	603	Nvidia	Llama 2 Community
260	244◄─►279	llama-2-70b-chat	1114	±10	6,377	Meta	Llama 2 Community
261	243◄─►282	starling-lm-7b-beta	1110	±15	2,378	Nexusflow	Apache-2.0
262	235◄─►284	qwq-32b-preview	1110	±29	454	Alibaba	Apache 2.0
263	249◄─►282	mistral-7b-instruct-v0.2	1106	±12	2,952	Mistral	Apache-2.0
264	244◄─►284	qwen-14b-chat	1103	±21	898	Alibaba	Qianwen LICENSE
265	239◄─►285	zephyr-7b-alpha	1103	±30	399	HuggingFace	MIT
266	249◄─►284	gemma-7b-it	1101	±18	1,345	Google	Gemma license
267	244◄─►284	granite-3.0-2b-instruct	1101	±22	916	IBM	Apache 2.0
268	256◄─►284	phi-3-mini-4k-instruct-june-2024	1098	±15	1,955	Microsoft	MIT
269	257◄─►284	llama-2-13b-chat	1093	±13	3,296	Meta	Llama 2 Community
270	256◄─►285	gemma-1.1-2b-it	1093	±17	1,486	Google	Gemma license
271	256◄─►285	mistral-7b-instruct	1092	±17	1,689	Mistral	Apache 2.0
272	255◄─►285	alpaca-13b	1092	±22	954	Stanford	Non-commercial
273	257◄─►285	vicuna-7b	1090	±18	1,323	LMSYS	Llama 2 Community
274	256◄─►285	stripedhyena-nous-7b	1090	±21	869	Together AI	Apache 2.0
275	257◄─►285	palm-2	1088	±18	1,576	Google	Proprietary
276	257◄─►285	codellama-34b-instruct	1088	±17	1,507	Meta	Llama 2 Community
277	260◄─►285	phi-3-mini-128k-instruct	1087	±14	2,949	Microsoft	MIT
278	257◄─►288	llama-3.2-1b-instruct	1084	±21	1,091	Meta	Llama 3.2
279	257◄─►288	qwen1.5-7b-chat	1082	±23	701	Alibaba	Qianwen LICENSE
280	253◄─►288	smollm2-1.7b-instruct	1081	±35	341	HuggingFace	Apache 2.0
281	260◄─►288	gemma-2b-it	1078	±23	696	Google	Gemma license
282	263◄─►288	phi-3-mini-4k-instruct	1075	±13	2,812	Microsoft	MIT
283	263◄─►288	llama-2-7b-chat	1074	±14	2,341	Meta	Llama 2 Community
284	260◄─►291	gpt4all-13b-snoozy	1064	±38	250	Nomic AI	Non-commercial
285	269◄─►290	mpt-7b-chat	1052	±24	683	MosaicML	CC-BY-NC-SA-4.0
286	278◄─►290	qwen1.5-4b-chat	1050	±19	1,082	Alibaba	Qianwen LICENSE
287	278◄─►291	koala-13b	1047	±21	1,199	UC Berkeley	Non-commercial
288	278◄─►292	chatglm3-6b	1041	±23	816	Tsinghua	Apache-2.0
289	284◄─►294	oasst-pythia-12b	1013	±21	1,094	OpenAssistant	Apache 2.0
290	288◄─►294	olmo-7b-instruct	1005	±20	1,020	Allen AI	Apache-2.0
291	284◄─►294	chatglm2-6b	1005	±26	566	Tsinghua	Apache-2.0
292	286◄─►294	RWKV-4-Raven-14B	1005	±23	874	RWKV	Apache 2.0
293	289◄─►295	fastchat-t5-3b	992	±24	744	LMSYS	Apache 2.0
294	289◄─►297	dolly-v2-12b	970	±28	565	Databricks	MIT
295	293◄─►297	chatglm-6b	953	±25	771	Tsinghua	Non-commercial
296	294◄─►297	stablelm-tuned-alpha-7b	933	±29	536	Stability AI	CC-BY-NC-SA-4.0
297	294◄─►297	llama-13b	933	±34	431	Meta	Non-commercial

Text Arena

Default Leaderboard Plots

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

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

Battle Count for Each Combination of Models (without Ties)

Confidence Intervals on Model Strength (via Bootstrapping)