Text Arena

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

Last Updated

Oct 16, 2025

Total Votes

45,352

Total Models

150

/


1	o3-2025-04-16	1495	±27	635	OpenAI	Proprietary
1	claude-opus-4-1-20250805-thinking-16k	1482	±37	297	Anthropic	Proprietary
1	chatgpt-4o-latest-20250326	1476	±29	488	OpenAI	Proprietary
1	qwen3-235b-a22b-instruct-2507	1474	±33	410	Alibaba	Apache 2.0
1	claude-opus-4-1-20250805	1465	±31	471	Anthropic	Proprietary
1	gemini-2.5-pro	1460	±26	691	Google	Proprietary
1	qwen3-max-preview	1459	±40	245	Alibaba	Proprietary
1	mistral-medium-2508	1456	±37	319	Mistral	Proprietary
1	claude-opus-4-20250514-thinking-16k	1454	±31	428	Anthropic	Proprietary
1	grok-3-preview-02-24	1451	±34	365	xAI	Proprietary
1	deepseek-v3.1	1451	±40	243	DeepSeek	MIT
1	gpt-4.5-preview-2025-02-27	1447	±57	121	OpenAI	Proprietary
1	gpt-5-chat	1445	±38	264	OpenAI	Proprietary
1	qwen3-coder-480b-a35b-instruct	1442	±37	272	Alibaba	Apache 2.0
1	longcat-flash-chat	1424	±50	152	Meituan	MIT
2	gpt-4.1-2025-04-14	1437	±29	517	OpenAI	Proprietary
2	claude-sonnet-4-20250514	1436	±29	499	Anthropic	Proprietary
2	glm-4.5	1428	±37	280	Z.ai	MIT
2	kimi-k2-0711-preview	1428	±33	368	Moonshot	Modified MIT
2	gpt-5-high	1425	±38	302	OpenAI	Proprietary
2	deepseek-r1-0528	1425	±41	220	DeepSeek	MIT
2	claude-sonnet-4-20250514-thinking-32k	1425	±31	394	Anthropic	Proprietary
2	grok-4-0709	1424	±35	342	xAI	Proprietary
2	deepseek-v3-0324	1420	±28	517	DeepSeek	MIT
2	mai-1-preview	1420	±40	254	Microsoft AI	Proprietary
2	gpt-5-mini-high	1420	±42	237	OpenAI	Proprietary
3	claude-opus-4-20250514	1419	±28	545	Anthropic	Proprietary
3	qwen2.5-max	1412	±33	329	Alibaba	Proprietary
4	minimax-m1	1411	±33	368	MiniMax	Apache 2.0
5	o4-mini-2025-04-16	1411	±29	492	OpenAI	Proprietary
5	gemini-2.5-flash-lite-preview-06-17-thinking	1403	±33	369	Google	Proprietary
5	glm-4.5-air	1401	±36	316	Z.ai	MIT
5	qwen3-30b-a3b-instruct-2507	1398	±38	253	Alibaba	Apache 2.0
5	qwen3-next-80b-a3b-instruct	1395	±44	202	Alibaba	Apache 2.0
5	deepseek-r1	1394	±42	188	DeepSeek	MIT
5	hunyuan-turbos-20250416	1389	±50	148	Tencent	Proprietary
7	gpt-4.1-mini-2025-04-14	1402	±28	535	OpenAI	Proprietary
7	gemma-3-27b-it	1399	±27	583	Google	Gemma
7	o1-preview	1398	±34	291	OpenAI	Proprietary
7	qwen3-235b-a22b-no-thinking	1394	±29	477	Alibaba	Apache 2.0
7	mistral-medium-2505	1394	±30	454	Mistral	Proprietary
7	o1-2024-12-17	1392	±36	253	OpenAI	Proprietary
7	deepseek-v3.1-thinking	1385	±47	170	DeepSeek	MIT
7	qwen-max-0919	1382	±41	183	Alibaba	Qwen
7	qwen3-next-80b-a3b-thinking	1381	±45	170	Alibaba	Apache 2.0
8	gemini-2.0-flash-lite-preview-02-05	1385	±38	256	Google	Proprietary
8	mistral-large-2411	1380	±40	204	Mistral	MRL
8	o3-mini-high	1378	±44	204	OpenAI	Proprietary
10	Claude 3.5 Sonnet (10/22)	1396	±21	813	Anthropic	Proprietary
11	deepseek-v3	1376	±36	243	DeepSeek	DeepSeek
14	qwen3-30b-a3b	1373	±34	322	Alibaba	Apache 2.0
15	claude-3-7-sonnet-20250219-thinking-32k	1375	±30	477	Anthropic	Proprietary
16	command-a-03-2025	1375	±28	534	Cohere	CC-BY-NC-4.0
16	gemini-advanced-0514	1375	±24	757	Google	Proprietary
16	qwen3-235b-a22b	1369	±34	324	Alibaba	Apache 2.0
16	athene-v2-chat	1362	±36	228	NexusFlow	NexusFlow
16	grok-3-mini-beta	1359	±38	273	xAI	Proprietary
16	mistral-small-2506	1358	±42	215	Mistral	Apache 2.0
18	Claude 3.5 Sonnet (06/20)	1371	±21	938	Anthropic	Proprietary
18	o3-mini	1370	±24	649	OpenAI	Proprietary
18	gpt-oss-120b	1356	±38	258	OpenAI	Apache 2.0
23	gemma-3n-e4b-it	1353	±35	306	Google	Gemma
24	gpt-4o-2024-05-13	1368	±18	1,356	OpenAI	Proprietary
24	glm-4-plus	1351	±35	286	Zhipu AI	Proprietary
24	grok-3-mini-high	1341	±45	163	xAI	Proprietary
25	qwq-32b	1348	±35	288	Alibaba	Apache 2.0
26	grok-2-2024-08-13	1357	±24	605	xAI	Proprietary
26	yi-lightning	1345	±36	272	01 AI	Proprietary
28	Gemini-1.5-Pro-002	1352	±27	460	Google	Proprietary
28	llama-3.1-405b-instruct-bf16	1349	±30	365	Meta	Llama 3.1 Community
30	athene-70b-0725	1335	±41	206	NexusFlow	CC-BY-NC-4.0
33	magistral-medium-2506	1320	±52	158	Mistral	Proprietary
34	claude-3-5-haiku-20241022	1346	±24	779	Anthropic	Propretary
34	llama-4-scout-17b-16e-instruct	1338	±32	388	Meta	Llama
35	gpt-4-1106-preview	1350	±18	1,737	OpenAI	Proprietary
35	gpt-4-0125-preview	1348	±19	1,522	OpenAI	Proprietary
35	llama-3.1-405b-instruct-fp8	1340	±26	549	Meta	Llama 3.1 Community
36	deepseek-v2.5	1329	±37	223	DeepSeek	DeepSeek
37	GPT-4o-mini (07/18)	1342	±22	654	OpenAI	Proprietary
38	claude-3-opus-20240229	1348	±16	2,850	Anthropic	Proprietary
39	gpt-4-turbo-2024-04-09	1344	±19	1,402	OpenAI	Proprietary
39	llama-3.3-70b-instruct	1337	±26	535	Meta	Llama-3.3
39	GPT-4o (08/06)	1336	±27	459	OpenAI	Proprietary
39	mistral-large-2407	1334	±28	443	Mistral	Mistral Research
40	gemini-1.5-pro-001	1339	±20	1,081	Google	Proprietary
40	o1-mini	1329	±28	424	OpenAI	Proprietary
40	amazon-nova-pro-v1.0	1322	±38	224	Amazon	Proprietary
41	grok-2-mini-2024-08-13	1326	±27	472	xAI	Proprietary
41	qwen2.5-72b-instruct	1323	±32	343	Alibaba	Qwen
50	gpt-4-0314	1318	±24	843	OpenAI	Proprietary
54	gemma-2-27b-it	1319	±21	795	Google	Gemma license
56	Meta-Llama-3.1-70B-Instruct	1309	±27	501	Meta	Llama 3.1 Community
57	mistral-small-3.1-24b-instruct-2503	1302	±34	384	Mistral	Apache 2.0
57	c4ai-aya-expanse-32b	1301	±34	274	Cohere	CC-BY-NC-4.0
62	claude-3-sonnet-20240229	1311	±18	1,826	Anthropic	Proprietary
63	llama-4-maverick-17b-128e-instruct	1299	±28	558	Meta	Llama 4
63	Gemini-1.5-Flash-002	1294	±33	297	Google	Proprietary
63	amazon-nova-micro-v1.0	1283	±44	164	Amazon	Proprietary
65	gemini-1.5-flash-001	1304	±22	922	Google	Proprietary
69	amazon-nova-lite-v1.0	1274	±45	171	Amazon	Proprietary
71	mistral-large-2402	1297	±21	1,055	Mistral	Proprietary
73	llama-3-70b-instruct	1301	±16	2,514	Meta	Llama 3 Community
73	gemini-1.5-flash-8b-001	1285	±32	334	Google	Proprietary
76	phi-4	1273	±40	206	Microsoft	MIT
79	mistral-small-24b-instruct-2501	1259	±50	142	Mistral	Apache 2.0
80	command-r-plus	1287	±20	1,234	Cohere	CC-BY-NC-4.0
80	nemotron-4-340b-instruct	1275	±33	356	Nvidia	NVIDIA Open Model
80	deepseek-coder-v2	1266	±41	207	DeepSeek AI	DeepSeek License
82	claude-3-haiku-20240307	1285	±18	1,777	Anthropic	Proprietary
82	gpt-4-0613	1282	±19	1,551	OpenAI	Proprietary
91	gemma-2-9b-it	1267	±25	592	Google	Gemma license
91	mixtral-8x22b-instruct-v0.1	1265	±24	775	Mistral	Apache 2.0
91	qwen2-72b-instruct	1263	±24	597	Alibaba	Qianwen LICENSE
91	gemini-pro-dev-api	1256	±31	462	Google	Proprietary
91	reka-flash-21b-20240226	1255	±30	432	Reka AI	Proprietary
92	mistral-medium	1259	±25	723	Mistral	Proprietary
95	reka-flash-21b-20240226-online	1241	±40	231	Reka AI	Proprietary
97	mixtral-8x7b-instruct-v0.1	1251	±20	1,258	Mistral	Apache 2.0
97	qwen1.5-72b-chat	1248	±23	862	Alibaba	Qianwen LICENSE
97	qwen1.5-110b-chat	1238	±31	378	Alibaba	Qianwen LICENSE
98	command-r	1245	±23	841	Cohere	CC-BY-NC-4.0
102	gpt-3.5-turbo-0125	1243	±20	1,293	OpenAI	Proprietary
104	snowflake-arctic-instruct	1228	±29	529	Snowflake	Apache 2.0
104	phi-3-small-8k-instruct	1222	±35	271	Microsoft	MIT
105	llama-3-8b-instruct	1233	±19	1,640	Meta	Llama 3 Community
105	yi-1.5-34b-chat	1217	±31	403	01 AI	Apache-2.0
105	gemma-2-2b-it	1215	±29	469	Google	Gemma license
105	llama-3.1-8b-instruct	1214	±28	482	Meta	Llama 3.1 Community
107	qwen1.5-14b-chat	1204	±38	278	Alibaba	Qianwen LICENSE
110	gpt-3.5-turbo-1106	1200	±38	310	OpenAI	Proprietary
110	openchat-3.5-0106	1193	±43	212	OpenChat	Apache-2.0
112	phi-3-medium-4k-instruct	1199	±32	352	Microsoft	MIT
114	dbrx-instruct-preview	1198	±28	544	Databricks	DBRX LICENSE
119	qwen1.5-32b-chat	1188	±34	310	Alibaba	Qianwen LICENSE
120	starling-lm-7b-alpha	1173	±43	211	UC Berkeley	CC-BY-NC-4.0
121	gemma-1.1-7b-it	1183	±31	407	Google	Gemma license
121	vicuna-33b	1175	±36	295	LMSYS	Non-commercial
121	starling-lm-7b-beta	1171	±38	248	Nexusflow	Apache-2.0
123	yi-34b-chat	1165	±40	236	01 AI	Yi License
125	llama-2-70b-chat	1162	±26	683	Meta	Llama 2 Community
125	phi-3-mini-4k-instruct	1160	±35	310	Microsoft	MIT
129	phi-3-mini-128k-instruct	1142	±34	372	Microsoft	MIT
129	gemma-7b-it	1135	±46	201	Google	Gemma license
129	stripedhyena-nous-7b	1131	±48	170	Together AI	Apache 2.0
129	vicuna-13b	1125	±45	200	LMSYS	Llama 2 Community
133	mistral-7b-instruct-v0.2	1125	±31	479	Mistral	Apache-2.0
133	llama-2-13b-chat	1119	±38	265	Meta	Llama 2 Community
133	zephyr-7b-beta	1112	±49	154	HuggingFace	MIT
142	mistral-7b-instruct	1067	±47	175	Mistral	Apache 2.0
145	llama-2-7b-chat	1048	±41	257	Meta	Llama 2 Community

Take your chats anywhere

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)