Text Arena

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

Last Updated

Jan 12, 2026

Total Votes

859,697

Total Models

292

/

Style Control

	Rank Spread
1	1◄─►3	claude-opus-4-5-20251101-thinking-32k	1538	±11	3,589	Anthropic	Proprietary
2	1◄─►6	claude-sonnet-4-5-20250929-thinking-32k	1524	±7	7,837	Anthropic	Proprietary
3	1◄─►13	claude-opus-4-5-20251101	1520	±10	4,017	Anthropic	Proprietary
4	2◄─►13	gemini-3-pro	1517	±9	5,492	Google	Proprietary
5	2◄─►14	claude-opus-4-1-20250805-thinking-16k	1512	±7	9,896	Anthropic	Proprietary
6	2◄─►17	grok-4.1-thinking	1510	±9	5,299	xAI	Proprietary
7	3◄─►17	claude-sonnet-4-5-20250929	1508	±8	6,926	Anthropic	Proprietary
8	3◄─►17	claude-opus-4-1-20250805	1504	±6	13,174	Anthropic	Proprietary
9	3◄─►20	gemini-3-flash	1502	±13	2,310	Google	Proprietary
10	3◄─►26	gpt-5.2-high	1499	±16	1,443	OpenAI	Proprietary
11	6◄─►20	claude-opus-4-20250514-thinking-16k	1497	±8	6,759	Anthropic	Proprietary
12	3◄─►32	ernie-5.0-0110	1497	±19	936	Baidu	Proprietary
13	3◄─►29	gemini-3-flash (thinking-minimal)	1497	±17	1,164	Google	Proprietary
14	5◄─►23	gpt-5.1-high	1496	±10	4,515	OpenAI	Proprietary
15	6◄─►23	grok-4.1	1495	±9	6,086	xAI	Proprietary
16	3◄─►43	gpt-5.2	1493	±22	746	OpenAI	Proprietary
17	6◄─►37	glm-4.7	1489	±15	1,632	Z.ai	MIT
18	9◄─►35	kimi-k2-thinking-turbo	1485	±9	5,124	Moonshot	Modified MIT
19	9◄─►37	qwen3-max-preview	1482	±8	5,368	Alibaba	Proprietary
20	11◄─►43	gpt-5.1	1480	±9	5,095	OpenAI	Proprietary
21	13◄─►43	claude-haiku-4-5-20251001	1478	±8	7,538	Anthropic	Proprietary
22	9◄─►51	qwen3-max-2025-09-23	1476	±13	2,043	Alibaba	Proprietary
23	11◄─►54	longcat-flash-chat	1474	±13	2,266	Meituan	MIT
24	11◄─►56	deepseek-v3.2-exp-thinking	1473	±13	1,907	DeepSeek	MIT
25	14◄─►50	claude-sonnet-4-20250514-thinking-32k	1472	±8	6,518	Anthropic	Proprietary
26	16◄─►47	qwen3-235b-a22b-instruct-2507	1472	±6	11,966	Alibaba	Apache 2.0
27	14◄─►56	mistral-large-3	1471	±11	3,100	Mistral	Apache 2.0
28	13◄─►62	ernie-5.0-preview-1203	1470	±14	1,681	Baidu	Proprietary
29	15◄─►58	deepseek-v3.2	1469	±11	3,716	DeepSeek	MIT
30	17◄─►56	gpt-5-high	1468	±8	6,462	OpenAI	Proprietary
31	19◄─►54	gemini-2.5-pro	1468	±6	16,550	Google	Proprietary
32	14◄─►62	kimi-k2-0905-preview	1468	±13	2,271	Moonshot	Modified MIT
33	15◄─►62	deepseek-v3.2-exp	1467	±12	2,516	DeepSeek	MIT
34	15◄─►63	deepseek-v3.2-thinking	1466	±12	2,580	DeepSeek	MIT
35	19◄─►56	chatgpt-4o-latest-20250326	1466	±6	13,869	OpenAI	Proprietary
36	17◄─►64	deepseek-r1-0528	1464	±11	2,792	DeepSeek	MIT
37	16◄─►67	qwen3-vl-235b-a22b-instruct	1464	±13	2,369	Alibaba	Apache 2.0
38	19◄─►62	gpt-5-chat	1463	±8	6,013	OpenAI	Proprietary
39	16◄─►67	ernie-5.0-preview-1103	1463	±14	1,724	Baidu	Proprietary
40	22◄─►62	claude-opus-4-20250514	1463	±7	8,024	Anthropic	Proprietary
41	13◄─►79	deepseek-v3.1-terminus-thinking	1461	±23	649	DeepSeek	MIT
42	22◄─►64	glm-4.6	1461	±8	6,882	Z.ai	MIT
43	22◄─►67	kimi-k2-0711-preview	1460	±8	5,360	Moonshot	Modified MIT
44	19◄─►70	gpt-4.5-preview-2025-02-27	1459	±13	1,939	OpenAI	Proprietary
45	23◄─►66	o3-2025-04-16	1458	±6	11,947	OpenAI	Proprietary
46	19◄─►70	deepseek-v3.1-thinking	1458	±13	1,910	DeepSeek	MIT
47	19◄─►75	grok-4-fast-chat	1457	±16	1,258	xAI	Proprietary
48	22◄─►72	qwen3-vl-235b-a22b-thinking	1456	±14	1,639	Alibaba	Apache 2.0
49	25◄─►67	gpt-4.1-2025-04-14	1456	±7	9,437	OpenAI	Proprietary
50	23◄─►70	grok-4-1-fast-reasoning	1455	±10	3,993	xAI	Proprietary
51	24◄─►69	qwen3-coder-480b-a35b-instruct	1455	±9	4,986	Alibaba	Apache 2.0
52	25◄─►70	glm-4.5	1455	±9	4,809	Z.ai	MIT
53	27◄─►69	mistral-medium-2508	1454	±6	11,116	Mistral	Proprietary
54	31◄─►70	claude-3-7-sonnet-20250219-thinking-32k	1451	±8	6,291	Anthropic	Proprietary
55	23◄─►82	minimax-m2.1-preview	1450	±16	1,427	MiniMax	MIT
56	32◄─►73	claude-sonnet-4-20250514	1448	±7	7,516	Anthropic	Proprietary
57	32◄─►82	deepseek-v3.1	1446	±12	2,656	DeepSeek	MIT
58	37◄─►79	qwen3-next-80b-a3b-instruct	1446	±9	4,811	Alibaba	Apache 2.0
59	40◄─►79	qwen3-235b-a22b-no-thinking	1445	±8	7,131	Alibaba	Apache 2.0
60	32◄─►85	deepseek-r1	1445	±12	2,318	DeepSeek	MIT
61	40◄─►81	grok-3-preview-02-24	1444	±8	5,501	xAI	Proprietary
62	32◄─►90	qwen3-235b-a22b-thinking-2507	1442	±15	1,627	Alibaba	Apache 2.0
63	45◄─►86	qwen3-30b-a3b-instruct-2507	1439	±9	4,698	Alibaba	Apache 2.0
64	27◄─►100	amazon-nova-experimental-chat-12-10	1439	±23	623	Amazon	Proprietary
65	45◄─►88	grok-4-fast-reasoning	1439	±9	3,967	xAI	Proprietary
66	31◄─►100	deepseek-v3.1-terminus	1438	±21	793	DeepSeek	MIT
67	41◄─►95	mimo-v2-flash (non-thinking)	1437	±15	1,561	Xiaomi	MIT
68	25◄─►102	hunyuan-vision-1.5-thinking	1436	±27	439	Tencent	Proprietary
69	38◄─►100	ernie-5.0-preview-1022	1436	±19	910	Baidu	Proprietary
70	52◄─►88	grok-4-0709	1435	±7	8,280	xAI	Proprietary
71	47◄─►95	o3-mini-high	1434	±11	2,595	OpenAI	Proprietary
72	55◄─►89	claude-3-5-sonnet-20241022	1434	±5	15,079	Anthropic	Proprietary
73	54◄─►91	gpt-4.1-mini-2025-04-14	1433	±7	7,075	OpenAI	Proprietary
74	53◄─►94	qwen3-235b-a22b	1433	±9	4,418	Alibaba	Apache 2.0
75	52◄─►94	o1-2024-12-17	1433	±9	3,974	OpenAI	Proprietary
76	55◄─►93	o4-mini-2025-04-16	1431	±7	8,838	OpenAI	Proprietary
77	55◄─►94	mistral-medium-2505	1431	±8	6,009	Mistral	Proprietary
78	54◄─►100	mai-1-preview	1430	±11	2,809	Microsoft AI	Proprietary
79	55◄─►99	gpt-5-mini-high	1429	±9	5,523	OpenAI	Proprietary
80	58◄─►97	claude-3-7-sonnet-20250219	1429	±7	7,273	Anthropic	Proprietary
81	59◄─►99	gemini-2.5-flash-preview-09-2025	1428	±8	6,899	Google	Proprietary
82	61◄─►99	deepseek-v3-0324	1427	±7	8,501	DeepSeek	MIT
83	61◄─►100	glm-4.5-air	1426	±8	6,152	Z.ai	MIT
84	65◄─►100	gemini-2.5-flash	1423	±6	15,930	Google	Proprietary
85	58◄─►103	amazon-nova-experimental-chat-11-10	1422	±14	1,666	Amazon	Proprietary
86	61◄─►102	qwen3-next-80b-a3b-thinking	1422	±11	2,705	Alibaba	Apache 2.0
87	68◄─►102	minimax-m1	1417	±8	6,637	MiniMax	Apache 2.0
88	67◄─►104	o1-preview	1417	±9	5,123	OpenAI	Proprietary
89	74◄─►102	o3-mini	1416	±6	9,601	OpenAI	Proprietary
90	66◄─►111	ling-flash-2.0	1413	±15	1,535	Ant Group	MIT
91	75◄─►108	mistral-small-2506	1412	±10	3,419	Mistral	Apache 2.0
92	63◄─►124	intellect-3	1411	±19	982	Prime Intellect	MIT
93	74◄─►114	amazon-nova-experimental-chat-10-20	1409	±12	2,317	Amazon	Proprietary
94	69◄─►126	step-3	1408	±17	1,247	StepFun	Apache 2.0
95	62◄─►129	qwen3-32b	1407	±25	513	Alibaba	Apache 2.0
96	72◄─►128	glm-4.5v	1405	±18	994	Z.ai	MIT
97	68◄─►131	nvidia-llama-3.3-nemotron-super-49b-v1.5	1403	±22	669	Nvidia	Nvidia Open
98	84◄─►119	qwen2.5-max	1403	±8	5,183	Alibaba	Proprietary
99	63◄─►143	hunyuan-turbos-20250226	1399	±31	275	Tencent	Proprietary
100	78◄─►132	hunyuan-t1-20250711	1399	±20	812	Tencent	Proprietary
101	90◄─►127	claude-3-5-sonnet-20240620	1397	±7	13,609	Anthropic	Proprietary
102	90◄─►128	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1396	±7	7,958	Google	Proprietary
103	89◄─►129	nova-2-lite	1396	±12	2,562	Amazon	Proprietary
104	88◄─►131	hunyuan-turbos-20250416	1395	±14	1,803	Tencent	Proprietary
105	75◄─►150	llama-3.1-nemotron-ultra-253b-v1	1391	±30	367	Nvidia	Nvidia Open Model
106	90◄─►136	ring-flash-2.0	1390	±15	1,550	Ant Group	MIT
107	92◄─►129	gpt-oss-120b	1390	±8	6,530	OpenAI	Apache 2.0
108	93◄─►129	command-a-03-2025	1389	±6	10,361	Cohere	CC-BY-NC-4.0
109	84◄─►147	amazon-nova-experimental-chat-10-09	1389	±24	556	Amazon	Proprietary
110	91◄─►132	grok-3-mini-high	1389	±10	3,360	xAI	Proprietary
111	93◄─►132	qwen3-30b-a3b	1388	±9	4,625	Alibaba	Apache 2.0
112	91◄─►136	magistral-medium-2506	1387	±12	2,301	Mistral	Proprietary
113	92◄─►135	deepseek-v3	1387	±10	3,281	DeepSeek	DeepSeek
114	94◄─►132	o1-mini	1387	±7	8,482	OpenAI	Proprietary
115	93◄─►135	grok-3-mini-beta	1386	±9	4,356	xAI	Proprietary
116	94◄─►136	qwq-32b	1385	±9	4,113	Alibaba	Apache 2.0
117	97◄─►132	claude-3-5-haiku-20241022	1384	±6	11,365	Anthropic	Proprietary
118	94◄─►136	gemini-2.5-flash-lite-preview-06-17-thinking	1384	±8	6,108	Google	Proprietary
119	91◄─►143	minimax-m2	1384	±15	1,537	MiniMax	Apache 2.0
120	93◄─►145	gpt-5-nano-high	1381	±15	1,697	OpenAI	Proprietary
121	92◄─►152	qwen-plus-0125	1379	±18	893	Alibaba	Proprietary
122	103◄─►145	llama-3.1-405b-instruct-bf16	1374	±7	6,251	Meta	Llama 3.1 Community
123	95◄─►155	deepseek-v2.5-1210	1374	±17	1,079	DeepSeek	DeepSeek
124	94◄─►158	gpt-4.1-nano-2025-04-14	1374	±19	807	OpenAI	Proprietary
125	105◄─►147	llama-4-maverick-17b-128e-instruct	1373	±7	7,133	Meta	Llama 4
126	90◄─►170	hunyuan-turbo-0110	1372	±30	299	Tencent	Proprietary
127	96◄─►163	step-2-16k-exp-202412	1371	±20	738	StepFun	Proprietary
128	110◄─►154	athene-v2-chat	1369	±9	4,019	NexusFlow	NexusFlow
129	116◄─►150	gpt-4o-2024-05-13	1369	±6	19,526	OpenAI	Proprietary
130	110◄─►154	yi-lightning	1369	±10	4,316	01 AI	Proprietary
131	103◄─►155	gpt-oss-20b	1368	±13	2,175	OpenAI	Apache 2.0
132	93◄─►172	mercury	1368	±29	398	Inception AI	Proprietary
133	110◄─►155	deepseek-v2.5	1368	±9	4,252	DeepSeek	DeepSeek
134	116◄─►153	llama-3.1-405b-instruct-fp8	1367	±7	9,714	Meta	Llama 3.1 Community
135	95◄─►170	hunyuan-large-2025-02-10	1366	±25	519	Tencent	Proprietary
136	99◄─►165	olmo-3-32b-think	1366	±19	1,057	Allen AI	Apache 2.0
137	116◄─►155	gemini-2.0-flash-001	1364	±7	7,126	Google	Proprietary
138	116◄─►159	mistral-small-3.1-24b-instruct-2503	1362	±8	6,244	Mistral	Apache 2.0
139	94◄─►176	llama-3.3-nemotron-49b-super-v1	1362	±32	285	Nvidia	Nvidia
140	116◄─►161	llama-4-scout-17b-16e-instruct	1362	±8	5,358	Meta	Llama
141	116◄─►165	nvidia-nemotron-3-nano-30b-a3b-bf16	1361	±13	2,158	Nvidia	NVIDIA Open Model
142	118◄─►162	gpt-4o-2024-08-06	1360	±8	7,319	OpenAI	Proprietary
143	120◄─►162	gemma-3-27b-it	1359	±7	8,211	Google	Gemma
144	120◄─►163	grok-2-2024-08-13	1359	±7	10,367	xAI	Proprietary
145	112◄─►171	hunyuan-large-vision	1358	±19	993	Tencent	Proprietary
146	116◄─►169	qwen2.5-plus-1127	1357	±14	1,554	Alibaba	Proprietary
147	122◄─►164	gemini-1.5-pro-002	1356	±7	9,174	Google	Proprietary
148	122◄─►165	qwen2.5-72b-instruct	1355	±7	6,687	Alibaba	Qwen
149	118◄─►172	step-1o-turbo-202506	1354	±15	1,566	StepFun	Proprietary
150	128◄─►165	claude-3-opus-20240229	1353	±6	33,751	Anthropic	Proprietary
151	125◄─►168	mistral-large-2407	1353	±8	7,590	Mistral	Mistral Research
152	122◄─►170	qwen-max-0919	1352	±11	2,756	Alibaba	Qwen
153	124◄─►169	glm-4-plus	1352	±9	4,450	Zhipu AI	Proprietary
154	124◄─►171	athene-70b-0725	1350	±11	3,122	NexusFlow	CC-BY-NC-4.0
155	132◄─►170	gpt-4o-mini-2024-07-18	1349	±6	10,944	OpenAI	Proprietary
156	132◄─►171	gemini-1.5-pro-001	1347	±7	12,749	Google	Proprietary
157	134◄─►171	gpt-4-turbo-2024-04-09	1347	±7	17,110	OpenAI	Proprietary
158	137◄─►172	llama-3.3-70b-instruct	1346	±6	8,851	Meta	Llama-3.3
159	133◄─►174	mistral-large-2411	1345	±9	4,214	Mistral	MRL
160	135◄─►174	gemini-2.0-flash-lite-preview-02-05	1343	±10	3,475	Google	Proprietary
161	139◄─►174	amazon-nova-pro-v1.0	1342	±9	3,854	Amazon	Proprietary
162	134◄─►177	deepseek-coder-v2	1342	±12	2,671	DeepSeek	DeepSeek License
163	126◄─►182	qwen2.5-coder-32b-instruct	1342	±19	873	Alibaba	Apache 2.0
164	144◄─►175	gpt-4-1106-preview	1338	±7	15,608	OpenAI	Proprietary
165	144◄─►177	gemini-advanced-0514	1338	±9	8,138	Google	Proprietary
166	147◄─►177	grok-2-mini-2024-08-13	1335	±7	8,653	xAI	Proprietary
167	154◄─►178	llama-3.1-70b-instruct	1333	±7	9,390	Meta	Llama 3.1 Community
168	132◄─►192	hunyuan-standard-2025-02-10	1331	±24	549	Tencent	Proprietary
169	158◄─►182	gpt-4-0125-preview	1331	±7	15,292	OpenAI	Proprietary
170	140◄─►189	glm-4-plus-0111	1331	±18	894	Zhipu	Proprietary
171	144◄─►190	ibm-granite-h-small	1329	±17	1,272	IBM	Apache 2.0
172	145◄─►189	llama-3.1-nemotron-70b-instruct	1328	±15	1,312	Nvidia	Llama 3.1
173	158◄─►185	gpt-4-0314	1327	±9	8,308	OpenAI	Proprietary
174	151◄─►200	gemma-3-12b-it	1317	±24	543	Google	Gemma
175	167◄─►192	claude-3-sonnet-20240229	1316	±7	18,888	Anthropic	Proprietary
176	167◄─►192	gemini-1.5-flash-002	1316	±8	5,893	Google	Proprietary
177	163◄─►198	reka-core-20240904	1315	±15	1,216	Reka AI	Proprietary
178	169◄─►195	gpt-4-0613	1312	±8	13,720	OpenAI	Proprietary
179	167◄─►198	mistral-small-24b-instruct-2501	1312	±12	2,083	Mistral	Apache 2.0
180	166◄─►200	jamba-1.5-large	1312	±14	1,440	AI21 Labs	Jamba Open
181	169◄─►198	gemma-3n-e4b-it	1310	±10	3,606	Google	Gemma
182	161◄─►204	llama-3.1-nemotron-51b-instruct	1310	±22	665	Nvidia	Llama 3.1
183	170◄─►196	gemini-1.5-flash-001	1310	±8	10,680	Google	Proprietary
184	169◄─►200	glm-4-0520	1307	±14	1,718	Zhipu AI	Proprietary
185	162◄─►207	llama-3.1-tulu-3-70b	1307	±24	450	Ai2	Llama 3.1
186	170◄─►200	nemotron-4-340b-instruct	1307	±11	3,254	Nvidia	NVIDIA Open Model
187	170◄─►200	phi-4	1306	±10	3,304	Microsoft	MIT
188	173◄─►198	gemma-2-27b-it	1305	±6	12,090	Google	Gemma license
189	170◄─►200	amazon-nova-lite-v1.0	1305	±10	3,060	Amazon	Proprietary
190	173◄─►199	llama-3-70b-instruct	1305	±7	28,131	Meta	Llama 3 Community
191	167◄─►216	hunyuan-standard-256k	1300	±25	497	Tencent	Proprietary
192	176◄─►201	claude-3-haiku-20240307	1300	±7	20,901	Anthropic	Proprietary
193	177◄─►206	qwen2-72b-instruct	1295	±9	6,249	Alibaba	Qianwen LICENSE
194	178◄─►206	mistral-large-2402	1293	±8	10,419	Mistral	Proprietary
195	178◄─►207	c4ai-aya-expanse-32b	1292	±9	4,686	Cohere	CC-BY-NC-4.0
196	176◄─►216	reka-flash-20240904	1290	±15	1,207	Reka AI	Proprietary
197	183◄─►214	amazon-nova-micro-v1.0	1288	±10	2,980	Amazon	Proprietary
198	172◄─►224	granite-3.1-8b-instruct	1286	±26	478	IBM	Apache 2.0
199	189◄─►221	command-r-08-2024	1280	±13	1,783	Cohere	CC-BY-NC-4.0
200	176◄─►229	olmo-2-0325-32b-instruct	1279	±27	427	Allen AI	Apache-2.0
201	190◄─►222	command-r-plus-08-2024	1279	±14	1,675	Cohere	CC-BY-NC-4.0
202	191◄─►221	qwen1.5-110b-chat	1278	±10	4,763	Alibaba	Qianwen LICENSE
203	190◄─►223	reka-flash-21b-20240226-online	1276	±13	2,879	Reka AI	Proprietary
204	193◄─►221	mixtral-8x22b-instruct-v0.1	1275	±9	8,781	Mistral	Apache 2.0
205	182◄─►229	gemma-3-4b-it	1275	±24	606	Google	Gemma
206	190◄─►228	ministral-8b-2410	1274	±19	838	Mistral	MRL
207	195◄─►223	qwen1.5-72b-chat	1273	±10	6,366	Alibaba	Qianwen LICENSE
208	195◄─►222	gpt-3.5-turbo-0125	1273	±8	11,127	OpenAI	Proprietary
209	191◄─►226	gemma-2-9b-it-simpo	1272	±15	1,471	Princeton	MIT
210	195◄─►222	gemini-1.5-flash-8b-001	1272	±8	6,067	Google	Proprietary
211	195◄─►223	gemma-2-9b-it	1271	±7	8,923	Google	Gemma license
212	195◄─►223	command-r-plus	1271	±8	13,944	Cohere	CC-BY-NC-4.0
213	196◄─►228	reka-flash-21b-20240226	1265	±11	4,750	Reka AI	Proprietary
214	195◄─►231	jamba-1.5-mini	1265	±15	1,352	AI21 Labs	Jamba Open
215	196◄─►233	gpt-3.5-turbo-1106	1260	±16	2,122	OpenAI	Proprietary
216	198◄─►231	mistral-medium	1260	±10	5,149	Mistral	Proprietary
217	198◄─►231	qwen1.5-32b-chat	1260	±11	3,931	Alibaba	Qianwen LICENSE
218	201◄─►229	llama-3.1-8b-instruct	1259	±7	8,584	Meta	Llama 3.1 Community
219	198◄─►234	c4ai-aya-expanse-8b	1255	±14	1,567	Cohere	CC-BY-NC-4.0
220	195◄─►239	llama-3.1-tulu-3-8b	1253	±25	476	Ai2	Llama 3.1
221	209◄─►233	llama-3-8b-instruct	1252	±8	18,377	Meta	Llama 3 Community
222	209◄─►236	dbrx-instruct-preview	1249	±11	5,501	Databricks	DBRX LICENSE
223	198◄─►241	gemini-pro	1247	±24	678	Google	Proprietary
224	198◄─►241	granite-3.1-2b-instruct	1247	±25	508	IBM	Apache 2.0
225	208◄─►238	internlm2_5-20b-chat	1247	±14	1,684	InternLM	Other
226	210◄─►236	yi-1.5-34b-chat	1247	±10	3,842	01 AI	Apache-2.0
227	204◄─►241	zephyr-orpo-141b-A35b-v0.1	1243	±21	832	HuggingFace	Apache 2.0
228	215◄─►238	command-r	1241	±9	9,648	Cohere	CC-BY-NC-4.0
229	210◄─►242	granite-3.0-8b-instruct	1238	±18	1,109	IBM	Apache 2.0
230	212◄─►241	gemini-pro-dev-api	1238	±14	2,681	Google	Proprietary
231	215◄─►241	qwen1.5-14b-chat	1238	±13	3,208	Alibaba	Qianwen LICENSE
232	218◄─►238	mixtral-8x7b-instruct-v0.1	1237	±8	11,789	Mistral	Apache 2.0
233	218◄─►242	starling-lm-7b-beta	1234	±13	2,948	Nexusflow	Apache-2.0
234	221◄─►244	phi-3-medium-4k-instruct	1229	±10	3,973	Microsoft	MIT
235	220◄─►246	openchat-3.5-0106	1228	±14	2,003	OpenChat	Apache-2.0
236	223◄─►246	snowflake-arctic-instruct	1223	±11	5,737	Snowflake	Apache 2.0
237	227◄─►250	gemma-1.1-7b-it	1217	±10	4,332	Google	Gemma license
238	221◄─►259	deepseek-llm-67b-chat	1216	±24	649	DeepSeek	DeepSeek License
239	223◄─►259	tulu-2-dpo-70b	1213	±21	805	AllenAI/UW	AI2 ImpACT Low-risk
240	226◄─►260	qwen1.5-7b-chat	1208	±21	771	Alibaba	Qianwen LICENSE
241	227◄─►260	granite-3.0-2b-instruct	1208	±18	1,134	IBM	Apache 2.0
242	232◄─►260	starling-lm-7b-alpha	1205	±16	1,397	UC Berkeley	CC-BY-NC-4.0
243	235◄─►260	yi-34b-chat	1204	±13	2,346	01 AI	Yi License
244	235◄─►259	phi-3-small-8k-instruct	1203	±12	3,218	Microsoft	MIT
245	234◄─►263	openchat-3.5	1201	±20	971	OpenChat	Apache-2.0
246	234◄─►268	qwen-14b-chat	1195	±24	599	Alibaba	Qianwen LICENSE
247	237◄─►263	phi-3-mini-4k-instruct-june-2024	1195	±14	1,841	Microsoft	MIT
248	238◄─►262	gemma-2-2b-it	1193	±8	7,299	Google	Gemma license
249	238◄─►263	vicuna-33b	1192	±13	2,866	LMSYS	Non-commercial
250	237◄─►268	wizardlm-70b	1191	±20	988	Microsoft	Llama 2 Community
251	238◄─►265	phi-3-mini-4k-instruct	1186	±12	3,450	Microsoft	MIT
252	237◄─►273	openhermes-2.5-mistral-7b	1185	±23	589	NousResearch	Apache-2.0
253	238◄─►267	mistral-7b-instruct-v0.2	1184	±12	3,113	Mistral	Apache-2.0
254	237◄─►274	solar-10.7b-instruct-v1.0	1182	±27	482	Upstage AI	CC-BY-NC-4.0
255	245◄─►270	llama-2-70b-chat	1177	±10	5,715	Meta	Llama 2 Community
256	241◄─►274	llama-3.2-3b-instruct	1175	±16	1,351	Meta	Llama 3.2
257	238◄─►275	nous-hermes-2-mixtral-8x7b-dpo	1174	±24	575	NousResearch	Apache-2.0
258	238◄─►275	qwq-32b-preview	1172	±24	567	Alibaba	Apache 2.0
259	245◄─►274	gemma-1.1-2b-it	1172	±14	1,963	Google	Gemma license
260	246◄─►275	gemma-7b-it	1168	±17	1,381	Google	Gemma license
261	238◄─►278	mpt-30b-chat	1166	±35	258	MosaicML	CC-BY-NC-SA-4.0
262	238◄─►279	zephyr-7b-alpha	1165	±40	201	HuggingFace	MIT
263	249◄─►277	vicuna-13b	1161	±14	2,389	LMSYS	Llama 2 Community
264	250◄─►277	llama-2-13b-chat	1160	±13	2,624	Meta	Llama 2 Community
265	238◄─►279	smollm2-1.7b-instruct	1160	±33	352	HuggingFace	Apache 2.0
266	249◄─►278	codellama-34b-instruct	1157	±20	853	Meta	Llama 2 Community
267	254◄─►278	phi-3-mini-128k-instruct	1153	±13	3,889	Microsoft	MIT
268	250◄─►278	palm-2	1151	±21	917	Google	Proprietary
269	253◄─►278	zephyr-7b-beta	1151	±18	1,249	HuggingFace	MIT
270	251◄─►278	wizardlm-13b	1150	±22	735	Microsoft	Llama 2 Community
271	254◄─►278	llama-3.2-1b-instruct	1147	±16	1,346	Meta	Llama 3.2
272	253◄─►279	llama2-70b-steerlm-chat	1143	±28	467	Nvidia	Llama 2 Community
273	254◄─►279	mistral-7b-instruct	1142	±20	1,032	Mistral	Apache 2.0
274	255◄─►280	gemma-2b-it	1137	±22	741	Google	Gemma license
275	258◄─►281	vicuna-7b	1130	±23	726	LMSYS	Llama 2 Community
276	263◄─►281	qwen1.5-4b-chat	1129	±17	1,282	Alibaba	Qianwen LICENSE
277	261◄─►281	stripedhyena-nous-7b	1125	±22	704	Together AI	Apache 2.0
278	261◄─►284	guanaco-33b	1112	±36	263	UW	Non-commercial
279	270◄─►284	olmo-7b-instruct	1105	±22	772	Allen AI	Apache-2.0
280	274◄─►283	llama-2-7b-chat	1101	±14	1,956	Meta	Llama 2 Community
281	275◄─►286	chatglm3-6b	1088	±26	535	Tsinghua	Apache-2.0
282	278◄─►288	mpt-7b-chat	1064	±32	397	MosaicML	CC-BY-NC-SA-4.0
283	278◄─►287	koala-13b	1064	±24	747	UC Berkeley	Non-commercial
284	279◄─►288	RWKV-4-Raven-14B	1057	±27	505	RWKV	Apache 2.0
285	281◄─►289	oasst-pythia-12b	1048	±25	714	OpenAssistant	Apache 2.0
286	282◄─►289	chatglm-6b	1033	±27	551	Tsinghua	Non-commercial
287	281◄─►290	chatglm2-6b	1029	±35	293	Tsinghua	Apache-2.0
288	283◄─►290	stablelm-tuned-alpha-7b	1003	±33	363	Stability AI	CC-BY-NC-SA-4.0
289	285◄─►290	alpaca-13b	998	±27	626	Stanford	Non-commercial
290	287◄─►291	dolly-v2-12b	961	±34	396	Databricks	MIT
291	290◄─►292	fastchat-t5-3b	906	±31	428	LMSYS	Apache 2.0
292	291◄─►292	llama-13b	882	±40	304	Meta	Non-commercial

Text Arena

Default Leaderboard Plots

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)

Battle Count for Each Combination of Models (without Ties)