Text Arena

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

Last Updated

Dec 23, 2025

Total Votes

423,561

Total Models

256

/

Style Control

	Rank Spread
1	1◄─►4	gemini-3-pro	1508	±16	1,562	Google	Proprietary
2	1◄─►11	gemini-3-flash	1491	±27	458	Google	Proprietary
3	1◄─►17	gemini-3-flash (thinking-minimal)	1483	±27	480	Google	Proprietary
4	1◄─►31	gpt-5.2	1474	±40	212	OpenAI	Proprietary
5	2◄─►19	grok-4.1-thinking	1470	±15	1,744	xAI	Proprietary
6	2◄─►20	claude-opus-4-5-20251101	1469	±17	1,230	Anthropic	Proprietary
7	2◄─►20	gemini-2.5-pro	1460	±9	4,792	Google	Proprietary
8	2◄─►26	claude-opus-4-5-20251101-thinking-32k	1460	±18	1,144	Anthropic	Proprietary
9	2◄─►28	grok-4.1	1451	±15	1,676	xAI	Proprietary
10	2◄─►31	gpt-5.1	1450	±16	1,447	OpenAI	Proprietary
11	3◄─►26	claude-opus-4-1-20250805	1450	±10	3,554	Anthropic	Proprietary
12	3◄─►34	gpt-5.1-high	1445	±16	1,408	OpenAI	Proprietary
13	2◄─►52	ernie-5.0-preview-1203	1445	±34	285	Baidu	Proprietary
14	4◄─►34	claude-sonnet-4-5-20250929-thinking-32k	1443	±13	2,118	Anthropic	Proprietary
15	3◄─►36	gpt-4.5-preview-2025-02-27	1442	±15	1,457	OpenAI	Proprietary
16	7◄─►34	chatgpt-4o-latest-20250326	1440	±9	4,528	OpenAI	Proprietary
17	5◄─►34	claude-opus-4-1-20250805-thinking-16k	1440	±11	2,810	Anthropic	Proprietary
18	7◄─►44	claude-sonnet-4-5-20250929	1435	±14	1,865	Anthropic	Proprietary
19	7◄─►40	o3-2025-04-16	1434	±10	3,717	OpenAI	Proprietary
20	7◄─►45	claude-opus-4-20250514-thinking-16k	1433	±13	2,073	Anthropic	Proprietary
21	3◄─►57	qwen3-max-2025-09-23	1433	±24	564	Alibaba	Proprietary
22	4◄─►58	ernie-5.0-preview-1103	1431	±25	564	Baidu	Proprietary
23	7◄─►48	gpt-5-high	1431	±15	1,574	OpenAI	Proprietary
24	7◄─►51	gpt-5-chat	1427	±15	1,523	OpenAI	Proprietary
25	3◄─►70	deepseek-v3.1-terminus	1425	±34	250	DeepSeek AI	MIT
26	10◄─►49	claude-opus-4-20250514	1424	±11	2,766	Anthropic	Proprietary
27	3◄─►72	deepseek-v3.1-terminus-thinking	1424	±36	237	DeepSeek AI	MIT
28	10◄─►59	qwen3-max-preview	1419	±16	1,341	Alibaba	Proprietary
29	9◄─►61	deepseek-v3.2	1417	±19	951	DeepSeek AI	MIT
30	17◄─►58	gemini-2.5-flash	1415	±9	5,081	Google	Proprietary
31	12◄─►63	grok-4-1-fast-reasoning	1414	±18	1,149	xAI	Proprietary
32	16◄─►60	grok-4-0709	1414	±13	2,181	xAI	Proprietary
33	18◄─►60	qwen3-235b-a22b-instruct-2507	1413	±10	3,293	Alibaba	Apache 2.0
34	9◄─►72	gpt-5.2-high	1412	±23	653	OpenAI	Proprietary
35	12◄─►72	kimi-k2-0905-preview	1411	±22	670	Moonshot	Modified MIT
36	16◄─►66	deepseek-r1-0528	1411	±16	1,281	DeepSeek	MIT
37	12◄─►73	deepseek-v3.2-exp-thinking	1409	±25	509	DeepSeek AI	MIT
38	19◄─►61	grok-3-preview-02-24	1409	±12	2,536	xAI	Proprietary
39	18◄─►66	glm-4.6	1408	±14	1,737	Z.ai	MIT
40	10◄─►79	qwen3-235b-a22b-thinking-2507	1408	±27	422	Alibaba	Apache 2.0
41	20◄─►63	gpt-4.1-2025-04-14	1407	±11	3,031	OpenAI	Proprietary
42	18◄─►70	kimi-k2-thinking-turbo	1407	±16	1,373	Moonshot	Modified MIT
43	17◄─►73	deepseek-v3.1	1405	±21	750	DeepSeek	MIT
44	20◄─►70	claude-sonnet-4-20250514-thinking-32k	1404	±13	1,930	Anthropic	Proprietary
45	17◄─►75	deepseek-v3.2-exp	1404	±21	751	DeepSeek AI	MIT
46	20◄─►71	kimi-k2-0711-preview	1404	±15	1,477	Moonshot	Modified MIT
47	17◄─►79	deepseek-v3.1-thinking	1402	±23	592	DeepSeek	MIT
48	21◄─►72	gemini-2.5-flash-preview-09-2025	1400	±13	2,131	Google	Proprietary
49	22◄─►72	qwen3-235b-a22b-no-thinking	1400	±12	2,352	Alibaba	Apache 2.0
50	24◄─►72	mistral-medium-2508	1398	±11	2,893	Mistral	Proprietary
51	18◄─►88	grok-4-fast-chat	1395	±28	398	xAI	Proprietary
52	24◄─►82	glm-4.5	1393	±16	1,205	Z.ai	MIT
53	28◄─►78	deepseek-v3-0324	1392	±10	3,076	DeepSeek	MIT
54	24◄─►83	grok-4-fast-reasoning	1392	±19	960	xAI	Proprietary
55	24◄─►87	mistral-large-3	1390	±20	837	Mistral	Apache 2.0
56	25◄─►83	qwen3-next-80b-a3b-instruct	1390	±17	1,142	Alibaba	Apache 2.0
57	23◄─►87	deepseek-v3.2-thinking	1390	±21	818	DeepSeek AI	MIT
58	30◄─►81	claude-sonnet-4-20250514	1389	±12	2,565	Anthropic	Proprietary
59	22◄─►91	qwen3-vl-235b-a22b-instruct	1388	±24	573	Alibaba	Apache 2.0
60	27◄─►90	mai-1-preview	1385	±19	940	Microsoft AI	Proprietary
61	34◄─►82	o1-2024-12-17	1384	±10	3,118	OpenAI	Proprietary
62	32◄─►91	qwen3-coder-480b-a35b-instruct	1381	±16	1,229	Alibaba	Apache 2.0
63	36◄─►91	gemini-2.5-flash-lite-preview-06-17-thinking	1379	±14	1,798	Google	Proprietary
64	34◄─►94	gpt-5-mini-high	1379	±16	1,336	OpenAI	Proprietary
65	36◄─►92	claude-haiku-4-5-20251001	1378	±14	1,814	Anthropic	Proprietary
66	39◄─►91	deepseek-r1	1377	±13	1,932	DeepSeek	MIT
67	40◄─►91	mistral-medium-2505	1377	±12	2,352	Mistral	Proprietary
68	34◄─►97	hunyuan-turbos-20250416	1377	±18	919	Tencent	Proprietary
69	24◄─►117	hunyuan-t1-20250711	1374	±35	250	Tencent	Proprietary
70	48◄─►95	o4-mini-2025-04-16	1373	±11	2,870	OpenAI	Proprietary
71	49◄─►95	claude-3-7-sonnet-20250219	1372	±10	3,220	Anthropic	Proprietary
72	52◄─►91	claude-3-5-sonnet-20241022	1371	±6	9,991	Anthropic	Proprietary
73	49◄─►96	claude-3-7-sonnet-20250219-thinking-32k	1371	±11	3,011	Anthropic	Proprietary
74	32◄─►111	qwen3-vl-235b-a22b-thinking	1371	±26	472	Alibaba	Apache 2.0
75	52◄─►97	gemma-3-27b-it	1369	±10	2,984	Google	Gemma
76	50◄─►98	gemini-2.5-flash-lite-preview-09-2025-no-thinking	1368	±13	2,106	Google	Proprietary
77	48◄─►101	qwen3-30b-a3b-instruct-2507	1367	±17	1,188	Alibaba	Apache 2.0
78	46◄─►114	longcat-flash-chat	1364	±22	667	Meituan	MIT
79	55◄─►99	qwen2.5-max	1364	±10	2,869	Alibaba	Proprietary
80	53◄─►109	glm-4.5-air	1362	±15	1,452	Z.ai	MIT
81	57◄─►100	gemini-2.0-flash-001	1362	±10	3,523	Google	Proprietary
82	36◄─►125	gemma-3-12b-it	1360	±32	289	Google	Gemma
83	59◄─►111	gpt-4.1-mini-2025-04-14	1358	±11	2,584	OpenAI	Proprietary
84	60◄─►108	o1-preview	1357	±9	4,561	OpenAI	Proprietary
85	36◄─►130	mimo-v2-flash (non-thinking)	1356	±36	257	Xiaomi	MIT
86	60◄─►116	qwen3-235b-a22b	1354	±13	1,872	Alibaba	Apache 2.0
87	68◄─►115	deepseek-v3	1353	±11	2,525	DeepSeek	DeepSeek
88	57◄─►122	qwen3-next-80b-a3b-thinking	1352	±21	725	Alibaba	Apache 2.0
89	69◄─►116	gemini-2.0-flash-lite-preview-02-05	1351	±11	2,329	Google	Proprietary
90	57◄─►125	qwen-plus-0125	1350	±22	580	Alibaba	Proprietary
91	74◄─►114	gemini-1.5-pro-002	1350	±7	7,769	Google	Proprietary
92	67◄─►120	grok-3-mini-beta	1349	±15	1,375	xAI	Proprietary
93	61◄─►123	mistral-small-2506	1348	±18	959	Mistral	Apache 2.0
94	49◄─►142	amazon-nova-experimental-chat-11-10	1347	±35	278	Amazon	Proprietary
95	68◄─►125	grok-3-mini-high	1345	±18	988	xAI	Proprietary
96	78◄─►120	claude-3-5-sonnet-20240620	1342	±8	10,021	Anthropic	Proprietary
97	75◄─►125	minimax-m1	1341	±13	1,902	MiniMax	Apache 2.0
98	78◄─►124	command-a-03-2025	1339	±10	3,673	Cohere	CC-BY-NC-4.0
99	72◄─►136	step-2-16k-exp-202412	1339	±22	646	StepFun	Proprietary
100	57◄─►155	hunyuan-turbos-20250226	1336	±35	225	Tencent	Proprietary
101	78◄─►130	gpt-oss-120b	1335	±15	1,556	OpenAI	Apache 2.0
102	88◄─►125	claude-3-opus-20240229	1333	±6	21,274	Anthropic	Proprietary
103	76◄─►143	nova-2-lite	1332	±21	797	Amazon	Proprietary
104	82◄─►129	llama-4-maverick-17b-128e-instruct	1332	±11	2,655	Meta	Llama 4
105	87◄─►133	gemini-advanced-0514	1329	±10	5,925	Google	Proprietary
106	71◄─►158	hunyuan-turbo-0110	1329	±32	270	Tencent	Proprietary
107	78◄─►147	amazon-nova-experimental-chat-10-20	1329	±20	845	Amazon	Proprietary
108	88◄─►128	gpt-4o-2024-05-13	1329	±7	13,959	OpenAI	Proprietary
109	78◄─►149	glm-4-plus-0111	1329	±22	654	Zhipu	Proprietary
110	84◄─►138	o3-mini-high	1329	±13	1,780	OpenAI	Proprietary
111	78◄─►150	step-1o-turbo-202506	1327	±24	543	StepFun	Proprietary
112	90◄─►137	o3-mini	1325	±9	4,468	OpenAI	Proprietary
113	78◄─►158	qwen3-32b	1323	±26	415	Alibaba	Apache 2.0
114	90◄─►139	gemini-1.5-pro-001	1323	±8	9,456	Google	Proprietary
115	91◄─►138	grok-2-2024-08-13	1323	±7	8,776	xAI	Proprietary
116	77◄─►160	step-3	1323	±29	398	StepFun	Apache 2.0
117	92◄─►142	gpt-4o-2024-08-06	1321	±8	5,550	OpenAI	Proprietary
118	88◄─►153	deepseek-v2.5-1210	1319	±17	1,050	DeepSeek	DeepSeek
119	80◄─►164	intellect-3	1318	±29	417	Prime Intellect	MIT
120	82◄─►163	gpt-5-nano-high	1317	±27	487	OpenAI	Proprietary
121	80◄─►171	glm-4.5v	1315	±31	306	Z.ai	MIT
122	99◄─►150	claude-3-5-haiku-20241022	1315	±7	6,209	Anthropic	Proprietary
123	79◄─►172	minimax-m2	1315	±33	308	MiniMax	Apache 2.0
124	82◄─►170	gemma-3-4b-it	1314	±30	311	Google	Gemma
125	100◄─►150	llama-3.1-405b-instruct-fp8	1313	±7	7,753	Meta	Llama 3.1 Community
126	85◄─►172	llama-3.1-nemotron-ultra-253b-v1	1312	±30	305	Nvidia	Nvidia Open Model
127	103◄─►150	gpt-4-turbo-2024-04-09	1311	±8	10,051	OpenAI	Proprietary
128	98◄─►159	llama-4-scout-17b-16e-instruct	1309	±13	1,886	Meta	Llama
129	98◄─►160	gemma-3n-e4b-it	1309	±15	1,390	Google	Gemma
130	102◄─►158	qwen-max-0919	1308	±11	2,447	Alibaba	Qwen
131	105◄─►156	gemini-1.5-flash-002	1308	±8	5,120	Google	Proprietary
132	108◄─►156	o1-mini	1307	±7	7,456	OpenAI	Proprietary
133	102◄─►160	qwen3-30b-a3b	1307	±13	1,899	Alibaba	Apache 2.0
134	108◄─►158	llama-3.1-405b-instruct-bf16	1305	±8	4,951	Meta	Llama 3.1 Community
135	110◄─►157	gpt-4o-mini-2024-07-18	1305	±7	8,341	OpenAI	Proprietary
136	108◄─►159	glm-4-plus	1305	±10	3,925	Zhipu AI	Proprietary
137	103◄─►162	qwq-32b	1304	±13	1,943	Alibaba	Apache 2.0
138	98◄─►172	gpt-oss-20b	1302	±24	593	OpenAI	Apache 2.0
139	111◄─►162	athene-v2-chat	1302	±10	3,457	NexusFlow	NexusFlow
140	111◄─►161	mistral-large-2407	1301	±8	5,811	Mistral	Mistral Research
141	93◄─►179	hunyuan-large-2025-02-10	1300	±29	374	Tencent	Proprietary
142	102◄─►172	gpt-4.1-nano-2025-04-14	1299	±21	704	OpenAI	Proprietary
143	113◄─►163	gpt-4-1106-preview	1299	±9	7,182	OpenAI	Proprietary
144	111◄─►172	qwen2.5-plus-1127	1295	±15	1,400	Alibaba	Proprietary
145	112◄─►172	mistral-small-3.1-24b-instruct-2503	1295	±13	1,977	Mistral	Apache 2.0
146	117◄─►165	grok-2-mini-2024-08-13	1295	±7	7,224	xAI	Proprietary
147	118◄─►168	gpt-4-0125-preview	1293	±8	8,528	OpenAI	Proprietary
148	118◄─►167	qwen2.5-72b-instruct	1293	±8	5,798	Alibaba	Qwen
149	117◄─►172	mistral-large-2411	1293	±10	3,296	Mistral	MRL
150	111◄─►174	reka-core-20240904	1293	±18	986	Reka AI	Proprietary
151	103◄─►183	hunyuan-standard-2025-02-10	1292	±27	383	Tencent	Proprietary
152	121◄─►172	llama-3.3-70b-instruct	1291	±8	5,486	Meta	Llama-3.3
153	131◄─►172	gemma-2-27b-it	1287	±7	9,716	Google	Gemma license
154	126◄─►173	deepseek-v2.5	1286	±10	3,552	DeepSeek	DeepSeek
155	122◄─►177	athene-70b-0725	1285	±13	1,944	NexusFlow	CC-BY-NC-4.0
156	107◄─►191	ling-flash-2.0	1285	±30	372	Ant Group	MIT
157	128◄─►174	yi-lightning	1284	±10	4,220	01 AI	Proprietary
158	132◄─►174	claude-3-sonnet-20240229	1284	±9	10,894	Anthropic	Proprietary
159	104◄─►193	llama-3.3-nemotron-49b-super-v1	1283	±34	274	Nvidia	Nvidia
160	134◄─►174	gemini-1.5-flash-001	1283	±9	7,495	Google	Proprietary
161	112◄─►193	hunyuan-large-vision	1278	±30	359	Tencent	Proprietary
162	117◄─►193	llama-3.1-tulu-3-70b	1276	±27	371	Ai2	Llama 3.1
163	139◄─►183	amazon-nova-pro-v1.0	1275	±10	3,052	Amazon	Proprietary
164	119◄─►197	nvidia-nemotron-3-nano-30b-a3b-bf16	1271	±28	424	Nvidia	NVIDIA Open Model
165	142◄─►189	nemotron-4-340b-instruct	1271	±12	2,521	Nvidia	NVIDIA Open Model
166	140◄─►191	command-r-plus-08-2024	1270	±15	1,367	Cohere	CC-BY-NC-4.0
167	138◄─►192	gemma-2-9b-it-simpo	1269	±17	1,125	Princeton	MIT
168	152◄─►187	llama-3.1-70b-instruct	1269	±8	7,414	Meta	Llama 3.1 Community
169	138◄─►193	qwen2.5-coder-32b-instruct	1267	±18	825	Alibaba	Apache 2.0
170	137◄─►196	magistral-medium-2506	1267	±21	751	Mistral	Proprietary
171	141◄─►193	reka-flash-20240904	1267	±17	1,021	Reka AI	Proprietary
172	151◄─►192	gpt-4-0314	1266	±12	3,657	OpenAI	Proprietary
173	156◄─►190	claude-3-haiku-20240307	1266	±8	12,084	Anthropic	Proprietary
174	140◄─►197	gemini-pro-dev-api	1265	±20	956	Google	Proprietary
175	157◄─►191	gemini-1.5-flash-8b-001	1264	±8	5,333	Google	Proprietary
176	157◄─►192	c4ai-aya-expanse-32b	1263	±9	3,910	Cohere	CC-BY-NC-4.0
177	136◄─►202	olmo-3-32b-think	1261	±29	462	Allen AI	Apache 2.0
178	156◄─►197	mistral-small-24b-instruct-2501	1258	±14	1,447	Mistral	Apache 2.0
179	156◄─►199	glm-4-0520	1258	±16	1,265	Zhipu AI	Proprietary
180	158◄─►193	command-r-plus	1257	±9	7,939	Cohere	CC-BY-NC-4.0
181	158◄─►199	deepseek-coder-v2	1256	±14	1,835	DeepSeek AI	DeepSeek License
182	160◄─►193	gemma-2-9b-it	1255	±8	6,717	Google	Gemma license
183	160◄─►197	gpt-4-0613	1254	±10	6,070	OpenAI	Proprietary
184	158◄─►207	llama-3.1-nemotron-51b-instruct	1248	±22	610	Nvidia	Llama 3.1
185	162◄─►199	amazon-nova-lite-v1.0	1247	±11	2,502	Amazon	Proprietary
186	160◄─►205	jamba-1.5-large	1247	±18	1,013	AI21 Labs	Jamba Open
187	166◄─►202	phi-4	1243	±11	2,619	Microsoft	MIT
188	160◄─►208	ministral-8b-2410	1242	±20	765	Mistral	MRL
189	163◄─►208	llama-3.1-nemotron-70b-instruct	1239	±17	1,084	Nvidia	Llama 3.1
190	176◄─►207	qwen2-72b-instruct	1236	±10	4,595	Alibaba	Qianwen LICENSE
191	176◄─►207	mistral-large-2402	1236	±10	5,591	Mistral	Proprietary
192	158◄─►212	ibm-granite-h-small	1235	±34	324	IBM	Apache 2.0
193	161◄─►212	ring-flash-2.0	1231	±30	382	Ant Group	MIT
194	177◄─►209	command-r-08-2024	1230	±15	1,366	Cohere	CC-BY-NC-4.0
195	181◄─►209	c4ai-aya-expanse-8b	1228	±14	1,484	Cohere	CC-BY-NC-4.0
196	161◄─►213	olmo-2-0325-32b-instruct	1226	±33	307	Allen AI	Apache-2.0
197	181◄─►209	reka-flash-21b-20240226-online	1226	±16	1,350	Reka AI	Proprietary
198	184◄─►209	mixtral-8x22b-instruct-v0.1	1223	±10	5,068	Mistral	Apache 2.0
199	184◄─►209	reka-flash-21b-20240226	1223	±13	2,347	Reka AI	Proprietary
200	176◄─►212	llama-3.1-tulu-3-8b	1222	±24	425	Ai2	Llama 3.1
201	186◄─►209	amazon-nova-micro-v1.0	1220	±11	2,509	Amazon	Proprietary
202	187◄─►209	llama-3-70b-instruct	1220	±8	15,231	Meta	Llama 3 Community
203	186◄─►212	mistral-medium	1217	±15	1,793	Mistral	Proprietary
204	187◄─►210	gpt-3.5-turbo-0125	1217	±10	5,578	OpenAI	Proprietary
205	184◄─►212	jamba-1.5-mini	1216	±18	1,012	AI21 Labs	Jamba Open
206	190◄─►212	command-r	1214	±10	5,355	Cohere	CC-BY-NC-4.0
207	169◄─►228	wizardlm-70b	1205	±44	185	Microsoft	Llama 2 Community
208	200◄─►215	phi-3-medium-4k-instruct	1194	±11	2,986	Microsoft	MIT
209	192◄─►226	hunyuan-standard-256k	1192	±26	448	Tencent	Proprietary
210	186◄─►234	openchat-3.5	1190	±41	191	OpenChat	Apache-2.0
211	206◄─►216	llama-3.1-8b-instruct	1189	±8	6,698	Meta	Llama 3.1 Community
212	199◄─►230	zephyr-orpo-141b-A35b-v0.1	1182	±27	418	HuggingFace	Apache 2.0
213	200◄─►234	gpt-3.5-turbo-1106	1176	±28	410	OpenAI	Proprietary
214	207◄─►227	qwen1.5-110b-chat	1175	±12	2,964	Alibaba	Qianwen LICENSE
215	209◄─►227	llama-3-8b-instruct	1172	±9	10,288	Meta	Llama 3 Community
216	208◄─►228	qwen1.5-72b-chat	1170	±12	2,726	Alibaba	Qianwen LICENSE
217	209◄─►230	phi-3-small-8k-instruct	1168	±13	2,225	Microsoft	MIT
218	209◄─►230	snowflake-arctic-instruct	1168	±13	2,871	Snowflake	Apache 2.0
219	209◄─►228	gemma-2-2b-it	1167	±8	5,996	Google	Gemma license
220	209◄─►234	mixtral-8x7b-instruct-v0.1	1158	±10	5,347	Mistral	Apache 2.0
221	209◄─►235	dbrx-instruct-preview	1158	±13	3,129	Databricks	DBRX LICENSE
222	209◄─►241	starling-lm-7b-alpha	1153	±27	413	UC Berkeley	CC-BY-NC-4.0
223	209◄─►242	granite-3.1-8b-instruct	1151	±28	472	IBM	Apache 2.0
224	209◄─►239	openchat-3.5-0106	1151	±21	797	OpenChat	Apache-2.0
225	207◄─►244	codellama-34b-instruct	1148	±44	157	Meta	Llama 2 Community
226	212◄─►240	internlm2_5-20b-chat	1145	±16	1,446	InternLM	Other
227	210◄─►242	vicuna-33b	1142	±21	721	LMSYS	Non-commercial
228	218◄─►241	qwen1.5-32b-chat	1140	±13	2,233	Alibaba	Qianwen LICENSE
229	215◄─►242	starling-lm-7b-beta	1139	±16	1,414	Nexusflow	Apache-2.0
230	218◄─►240	yi-1.5-34b-chat	1139	±12	3,267	01 AI	Apache-2.0
231	215◄─►242	granite-3.0-8b-instruct	1137	±20	969	IBM	Apache 2.0
232	218◄─►242	llama-2-70b-chat	1137	±14	2,026	Meta	Llama 2 Community
233	221◄─►242	gemma-1.1-7b-it	1133	±12	2,782	Google	Gemma license
234	209◄─►246	zephyr-7b-beta	1132	±38	208	HuggingFace	MIT
235	218◄─►245	vicuna-13b	1125	±26	470	LMSYS	Llama 2 Community
236	222◄─►248	qwq-32b-preview	1116	±26	530	Alibaba	Apache 2.0
237	222◄─►246	llama-2-13b-chat	1112	±21	815	Meta	Llama 2 Community
238	222◄─►248	granite-3.1-2b-instruct	1112	±28	467	IBM	Apache 2.0
239	223◄─►246	granite-3.0-2b-instruct	1111	±19	1,074	IBM	Apache 2.0
240	222◄─►248	yi-34b-chat	1111	±21	806	01 AI	Yi License
241	227◄─►246	qwen1.5-14b-chat	1108	±15	1,778	Alibaba	Qianwen LICENSE
242	233◄─►251	mistral-7b-instruct-v0.2	1089	±17	1,244	Mistral	Apache-2.0
243	225◄─►253	mistral-7b-instruct	1086	±41	183	Mistral	Apache 2.0
244	234◄─►251	gemma-1.1-2b-it	1085	±18	1,197	Google	Gemma license
245	239◄─►253	phi-3-mini-4k-instruct-june-2024	1075	±16	1,432	Microsoft	MIT
246	235◄─►253	gemma-7b-it	1074	±23	640	Google	Gemma license
247	233◄─►253	qwen1.5-7b-chat	1072	±34	303	Alibaba	Qianwen LICENSE
248	242◄─►253	phi-3-mini-4k-instruct	1069	±13	2,817	Microsoft	MIT
249	242◄─►253	phi-3-mini-128k-instruct	1066	±16	1,856	Microsoft	MIT
250	239◄─►254	smollm2-1.7b-instruct	1060	±31	417	HuggingFace	Apache 2.0
251	242◄─►254	llama-2-7b-chat	1055	±23	593	Meta	Llama 2 Community
252	244◄─►254	qwen1.5-4b-chat	1041	±25	568	Alibaba	Qianwen LICENSE
253	244◄─►256	gemma-2b-it	1027	±36	302	Google	Gemma license
254	250◄─►256	llama-3.2-3b-instruct	1009	±23	954	Meta	Llama 3.2
255	253◄─►256	llama-3.2-1b-instruct	991	±23	980	Meta	Llama 3.2
256	253◄─►256	olmo-7b-instruct	983	±28	504	Allen AI	Apache-2.0

Text Arena

Default Leaderboard Plots

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)

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