Text Arena🇯🇵Japanese

View overall rankings across various AI models in text-to-text tasks across math, coding, creative writing, and other open-ended domains.

Mar 31, 2026

85,513 votes

196 models

	Rank Spread
1	19	gemini-3.1-pro-preview Google · Proprietary	1540±63	116	$2 / $12	1M
2	118	claude-opus-4-6-thinking Anthropic · Proprietary	1512±64	90	$5 / $25	1M
3	113	gemini-3-pro Google · Proprietary	1497±33	400	$2 / $12	1M
4	125	claude-opus-4-6 Anthropic · Proprietary	1487±65	85	$5 / $25	1M
5	118	gemini-3-flash Google · Proprietary	1486±39	270	$0.50 / $3	1M
6	125	gpt-5.1-high OpenAI · Proprietary	1455±33	356	$1.25 / $10	400K
7	128	claude-opus-4-5-20251101-thinking-32k Anthropic · Proprietary	1454±37	284	$5 / $25	200K
8	137	gemini-3-flash (thinking-minimal) Google · Proprietary	1454±46	188	$0.50 / $3	1M
9	220	gemini-2.5-pro Google · Proprietary	1453±17	1,650	$1.25 / $10	1M
10	233	grok-4.1 xAI · Proprietary	1440±29	449	N/A	N/A
11	244	gpt-4.5-preview-2025-02-27 OpenAI · Proprietary	1438±38	271	$75 / $150	128K
12	247	claude-opus-4-5-20251101 Anthropic · Proprietary	1433±34	343	$5 / $25	200K
13	336	gpt-5-high OpenAI · Proprietary	1432±23	834	$1.25 / $10	400K
14	164	kimi-k2.5-thinking Moonshot · Modified MIT	1430±64	94	$0.60 / $3	N/A
15	536	o3-2025-04-16 OpenAI · Proprietary	1427±18	1,286	$2 / $8	200K
16	350	grok-4.1-thinking xAI · Proprietary	1426±32	370	N/A	N/A
17	352	gpt-5.1 OpenAI · Proprietary	1424±33	366	$1.25 / $10	400K
18	350	gpt-5-chat OpenAI · Proprietary	1422±29	472	$1.25 / $10	128K
19	359	gpt-5.2-high OpenAI · Proprietary	1415±45	196	$1.75 / $14	400K
20	655	claude-opus-4-1-20250805-thinking-16k Anthropic · Proprietary	1408±25	571	$15 / $75	200K
21	652	chatgpt-4o-latest-20250326 OpenAI · Proprietary	1408±19	1,178	$5 / $15	128K
22	855	claude-opus-4-1-20250805 Anthropic · Proprietary	1402±20	1,045	$15 / $75	200K
23	665	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1399±35	312	$0.30 / $2.50	1M
24	573	gpt-5.2 OpenAI · Proprietary	1396±50	160	$1.75 / $14	400K
25	865	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1393±29	455	$3 / $15	200K
26	1055	gemini-2.5-flash Google · Proprietary	1393±16	1,668	$0.30 / $2.50	1M
27	865	claude-sonnet-4-5-20250929-thinking-32k Anthropic · Proprietary	1391±29	445	$3 / $15	200K
28	963	glm-4.5 Z.ai · MIT	1391±24	716	$0.60 / $2.20	131.1K
29	1265	claude-opus-4-20250514-thinking-16k Anthropic · Proprietary	1386±23	765	$15 / $75	200K
30	1366	grok-4-0709 xAI · Proprietary	1382±21	879	$3 / $15	256K
31	680	deepseek-v3.2-thinking DeepSeek · MIT	1382±41	212	$0.26 / $0.38	163.8K
32	681	ernie-5.0-0110 Baidu · Proprietary	1381±42	210	N/A	N/A
33	972	qwen3-max-preview Alibaba · Proprietary	1381±31	378	$0.78 / $3.90	262.1K
34	1468	claude-opus-4-20250514 Anthropic · Proprietary	1380±20	992	$15 / $75	200K
35	1372	deepseek-r1-0528 DeepSeek · MIT	1379±26	563	$0.45 / $2.15	163.8K
36	1568	qwen3-235b-a22b-instruct-2507 Alibaba · Apache 2.0	1378±19	1,118	$0.26 / $1.06	N/A
37	1074	deepseek-v3.1 DeepSeek · MIT	1377±32	311	$1.23 / $4.94	N/A
38	1570	grok-3-preview-02-24 xAI · Proprietary	1376±22	784	$3 / $15	131.1K
39	983	deepseek-v3.1-thinking DeepSeek · MIT	1374±38	235	$1.23 / $4.94	N/A
40	1376	qwen3-235b-a22b-thinking-2507 Alibaba · Apache 2.0	1374±31	412	$0.15 / $1.50	131.1K
41	1081	qwen3-next-80b-a3b-instruct Alibaba · Apache 2.0	1374±36	272	$0.09 / $1.10	262.1K
42	1472	o1-2024-12-17 OpenAI · Proprietary	1374±26	581	$15 / $60	200K
43	988	kimi-k2-0905-preview Moonshot · Modified MIT	1374±44	181	$0.60 / $2.50	262.1K
44	1382	glm-4.6 Z.ai · MIT	1370±34	318	$0.39 / $1.90	204.8K
45	1481	gpt-5-mini-high OpenAI · Proprietary	1369±31	413	$0.25 / $2	400K
46	1388	grok-4-1-fast-reasoning xAI · Proprietary	1369±39	250	$0.20 / $0.50	2M
47	990	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1368±46	154	$0.20 / $0.88	262.1K
48	1388	deepseek-v3.2 DeepSeek · MIT	1366±36	303	$0.26 / $0.38	163.8K
49	1975	qwen3-235b-a22b-no-thinking Alibaba · Apache 2.0	1366±22	801	$0.46 / $1.82	131.1K
50	1975	kimi-k2-0711-preview Moonshot · Modified MIT	1365±21	851	$0.60 / $2.50	131.1K
51	1589	kimi-k2-thinking-turbo Moonshot · Modified MIT	1362±35	319	$1.15 / $8	262.1K
52	1398	grok-4-fast-reasoning xAI · Proprietary	1356±45	182	$0.20 / $0.50	2M
53	1989	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1356±29	418	$0.10 / $0.40	1M
54	2286	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1354±22	733	$0.10 / $0.40	1M
55	2286	mistral-medium-2508 Mistral · Proprietary	1354±22	817	$2.70 / $8.10	32K
56	1798	mistral-large-3 Mistral · Apache 2.0	1353±40	227	$0.50 / $1.50	N/A
57	2389	claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary	1348±20	946	$3 / $15	200K
58	2390	o1-preview OpenAI · Proprietary	1346±23	674	$15 / $60	N/A
59	2490	claude-sonnet-4-20250514 Anthropic · Proprietary	1346±21	894	$3 / $15	1M
60	2390	claude-sonnet-4-20250514-thinking-32k Anthropic · Proprietary	1345±23	753	$3 / $15	1M
61	22101	mai-1-preview Microsoft AI · Proprietary	1341±35	293	N/A	N/A
62	3090	gpt-4.1-2025-04-14 OpenAI · Proprietary	1341±19	1,038	$2 / $8	1M
63	3091	o4-mini-2025-04-16 OpenAI · Proprietary	1341±20	1,003	$1.10 / $4.40	200K
64	17107	deepseek-v3.2-exp DeepSeek · MIT	1339±54	124	$0.27 / $0.41	163.8K
65	3293	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1338±20	936	$3 / $15	200K
66	2998	deepseek-r1 DeepSeek · MIT	1336±26	468	$0.70 / $2.50	64K
67	3295	deepseek-v3-0324 DeepSeek · MIT	1335±20	970	$3 / $4.50	32.8K
68	25101	claude-haiku-4-5-20251001 Anthropic · Proprietary	1335±31	438	$1 / $5	200K
69	23101	hunyuan-turbos-20250416 Tencent · Proprietary	1334±34	325	N/A	N/A
70	33101	grok-3-mini-beta xAI · Proprietary	1329±25	605	$0.30 / $0.50	131.1K
71	36101	qwen3-30b-a3b-instruct-2507 Alibaba · Apache 2.0	1324±23	717	$0.09 / $0.30	262.1K
72	38101	glm-4.5-air Z.ai · MIT	1323±22	800	$0.13 / $0.85	131.1K
73	41101	gpt-4.1-mini-2025-04-14 OpenAI · Proprietary	1322±20	923	$0.40 / $1.60	1M
74	41104	mistral-medium-2505 Mistral · Proprietary	1320±21	822	$0.40 / $2	131.1K
75	41104	gemini-2.0-flash-lite-preview-02-05 Google · Proprietary	1318±25	542	$0.07 / $0.30	1M
76	22125	step-3.5-flash StepFun · Apache 2.0	1318±56	127	$0.10 / $0.30	262.1K
77	40107	gpt-oss-120b OpenAI · Apache 2.0	1317±27	510	$0.04 / $0.19	131.1K
78	45104	qwen3-coder-480b-a35b-instruct Alibaba · Apache 2.0	1316±21	869	$0.40 / $1.60	262.1K
79	47104	gemini-1.5-pro-002 Google · Proprietary	1316±17	1,210	$3.50 / $10.50	2.1M
80	37107	o3-mini-high OpenAI · Proprietary	1315±30	374	$1.10 / $4.40	200K
81	41108	grok-3-mini-high xAI · Proprietary	1312±29	427	$0.30 / $0.50	131.1K
82	52107	command-a-03-2025 Cohere · CC-BY-NC-4.0	1310±19	1,122	$2.50 / $10	256K
83	49107	qwen2.5-max Alibaba · Proprietary	1309±22	698	N/A	N/A
84	33125	mimo-v2-flash (non-thinking) Xiaomi · MIT	1308±46	199	$0.09 / $0.29	262.1K
85	61104	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1307±14	1,977	$6 / $30	200K
86	49108	qwen3-235b-a22b Alibaba · Apache 2.0	1306±24	661	$0.46 / $1.82	131.1K
87	55107	gemma-3-27b-it Google · Gemma	1306±20	964	$0.08 / $0.16	131.1K
88	62107	gpt-4o-2024-05-13 OpenAI · Proprietary	1304±14	2,674	$5 / $15	128K
89	62110	gemini-2.0-flash-001 Google · Proprietary	1298±19	977	$0.10 / $0.40	1M
90	63109	o3-mini OpenAI · Proprietary	1297±17	1,335	$1.10 / $4.40	200K
91	61122	mistral-small-2506 Mistral · Apache 2.0	1292±27	470	$0.10 / $0.30	32K
92	46135	qwen3-next-80b-a3b-thinking Alibaba · Apache 2.0	1291±45	184	$0.10 / $0.78	131.1K
93	66117	gpt-4o-2024-08-06 OpenAI · Proprietary	1291±18	1,104	$2.50 / $10	128K
94	63120	gemma-3n-e4b-it Google · Gemma	1290±23	684	$0.02 / $0.04	32.8K
95	60125	nvidia-llama-3.3-nemotron-super-49b-v1.5 Nvidia · Nvidia Open	1290±31	386	$0.10 / $0.40	131.1K
96	66119	gemini-advanced-0514 Google · Proprietary	1290±20	1,212	N/A	N/A
97	47136	longcat-flash-chat Meituan · MIT	1289±44	165	$0.20 / $0.80	131.1K
98	42141	amazon-nova-experimental-chat-11-10 Amazon · Proprietary	1288±51	143	N/A	N/A
99	66124	deepseek-v3 DeepSeek · DeepSeek	1286±23	534	$1.14 / $4.56	N/A
100	73119	claude-3-5-sonnet-20240620 Anthropic · Proprietary	1285±15	2,127	$6 / $30	200K
101	73120	gemini-1.5-pro-001 Google · Proprietary	1284±16	1,935	$3.50 / $10.50	2.1M
102	47144	minimax-m2.1-preview MiniMax · MIT	1281±54	143	$0.27 / $0.95	196.6K
103	63140	qwen-plus-0125 Alibaba · Proprietary	1277±38	206	$0.40 / $1.20	131.1K
104	78126	o1-mini OpenAI · Proprietary	1275±18	1,093	$1.10 / $4.40	N/A
105	78128	llama-3.1-405b-instruct-bf16 Meta · Llama 3.1 Community	1273±20	846	$4 / $4	32.8K
106	85130	grok-2-2024-08-13 xAI · Proprietary	1268±16	1,478	$2 / $10	131.1K
107	88136	gpt-4-1106-preview OpenAI · Proprietary	1262±17	1,422	$10 / $30	128K
108	89135	claude-3-opus-20240229 Anthropic · Proprietary	1261±13	3,650	$15 / $75	200K
109	73149	gpt-oss-20b OpenAI · Apache 2.0	1259±40	235	$0.03 / $0.11	131.1K
110	87141	llama-4-scout-17b-16e-instruct Meta · Llama	1259±23	729	$0.40 / $0.70	8.2K
111	89141	gemini-1.5-flash-002 Google · Proprietary	1257±21	753	$0.07 / $0.30	1M
112	89144	yi-lightning 01 AI · Proprietary	1253±24	565	N/A	N/A
113	89143	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1253±22	866	$0.63 / $1.80	131.1K
114	92142	gpt-4-0125-preview OpenAI · Proprietary	1251±18	1,474	$10 / $30	128K
115	78154	deepseek-v2.5-1210 DeepSeek · DeepSeek	1251±42	161	N/A	N/A
116	94142	gpt-4-turbo-2024-04-09 OpenAI · Proprietary	1250±15	2,112	$10 / $30	128K
117	96142	gpt-4o-mini-2024-07-18 OpenAI · Proprietary	1249±14	1,791	$0.15 / $0.60	128K
118	90145	qwen3-30b-a3b Alibaba · Apache 2.0	1248±23	675	$0.08 / $0.28	41K
119	90146	qwq-32b Alibaba · Apache 2.0	1246±26	580	$0.15 / $0.58	131.1K
120	95149	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1242±23	723	$0.10 / $0.30	32K
121	99145	claude-3-5-haiku-20241022 Anthropic · Proprietary	1241±16	1,463	$0.80 / $4	200K
122	89154	qwen-max-0919 Alibaba · Qwen	1241±32	312	$1.60 / $6.40	32.8K
123	101146	llama-3.1-405b-instruct-fp8 Meta · Llama 3.1 Community	1237±16	1,606	$4 / $4	32.8K
124	102149	grok-2-mini-2024-08-13 xAI · Proprietary	1234±17	1,225	$2 / $10	131.1K
125	102149	mistral-large-2407 Mistral · Mistral Research	1232±17	1,249	$2 / $6	131.1K
126	95156	qwen2.5-plus-1127 Alibaba · Proprietary	1232±32	300	N/A	N/A
127	89161	gpt-4.1-nano-2025-04-14 OpenAI · Proprietary	1231±45	160	$0.10 / $0.40	1M
128	100156	glm-4-plus Zhipu AI · Proprietary	1231±26	485	$0.44 / $1.76	204.8K
129	101155	athene-v2-chat NexusFlow · NexusFlow	1230±23	584	N/A	N/A
130	94157	magistral-medium-2506 Mistral · Proprietary	1229±37	305	$2 / $5	40K
131	106151	gemma-2-27b-it Google · Gemma license	1227±15	1,808	$0.65 / $0.65	8.2K
132	102156	amazon-nova-pro-v1.0 Amazon · Proprietary	1226±26	511	$0.80 / $3.20	300K
133	102156	deepseek-v2.5 DeepSeek · DeepSeek	1226±26	479	N/A	N/A
134	104156	minimax-m1 MiniMax · Apache 2.0	1222±23	793	$0.40 / $2.20	1M
135	106156	gemini-1.5-flash-001 Google · Proprietary	1222±17	1,522	$0.07 / $0.30	1M
136	89164	nvidia-nemotron-3-nano-30b-a3b-bf16 Nvidia · NVIDIA Open Model	1222±56	128	$0.06 / $0.24	262.1K
137	100163	glm-4-plus-0111 Zhipu · Proprietary	1219±38	201	N/A	N/A
138	107156	command-r-plus Cohere · CC-BY-NC-4.0	1218±18	1,487	$2.50 / $10	128K
139	106158	gpt-4-0314 OpenAI · Proprietary	1217±25	619	$30 / $60	8.2K
140	102163	command-r-plus-08-2024 Cohere · CC-BY-NC-4.0	1214±38	210	$2.50 / $10	128K
141	113157	llama-3.3-70b-instruct Meta · Llama-3.3	1213±18	1,132	$0.10 / $0.32	131.1K
142	110158	mistral-large-2411 Mistral · MRL	1213±22	629	$2 / $6	131.1K
143	106163	command-r-08-2024 Cohere · CC-BY-NC-4.0	1211±33	254	$0.15 / $0.60	128K
144	114160	qwen2.5-72b-instruct Alibaba · Qwen	1209±20	788	$1.20 / $1.20	N/A
145	116163	c4ai-aya-expanse-32b Cohere · CC-BY-NC-4.0	1204±22	670	N/A	N/A
146	120163	gpt-4-0613 OpenAI · Proprietary	1201±19	1,241	$30 / $60	8.2K
147	124163	claude-3-sonnet-20240229 Anthropic · Proprietary	1195±17	1,753	$3 / $15	200K
148	120164	phi-4 Microsoft · MIT	1194±26	500	$0.07 / $0.14	16.4K
149	125163	gemma-2-9b-it Google · Gemma license	1193±17	1,301	$0.03 / $0.09	8.2K
150	118166	deepseek-coder-v2 DeepSeek · DeepSeek License	1193±31	345	$0.14 / $0.28	128K
151	120167	gemma-2-9b-it-simpo Princeton · MIT	1187±32	291	$0.03 / $0.09	8.2K
152	128166	athene-70b-0725 NexusFlow · CC-BY-NC-4.0	1185±22	676	N/A	N/A
153	125167	amazon-nova-micro-v1.0 Amazon · Proprietary	1183±27	443	$0.04 / $0.14	128K
154	125167	amazon-nova-lite-v1.0 Amazon · Proprietary	1183±28	403	$0.06 / $0.24	300K
155	127167	nemotron-4-340b-instruct Nvidia · NVIDIA Open Model	1179±28	434	N/A	N/A
156	124170	jamba-1.5-large AI21 Labs · Jamba Open	1176±37	242	$2 / $8	256K
157	135167	qwen2-72b-instruct Alibaba · Qianwen LICENSE	1175±20	901	$0.90 / $0.90	32.8K
158	139167	llama-3.1-70b-instruct Meta · Llama 3.1 Community	1174±16	1,428	$0.40 / $0.40	131.1K
159	140167	claude-3-haiku-20240307 Anthropic · Proprietary	1171±16	2,063	$0.25 / $1.25	200K
160	137168	gemini-1.5-flash-8b-001 Google · Proprietary	1170±22	691	$0.07 / $0.30	1M
161	141169	command-r Cohere · CC-BY-NC-4.0	1163±22	856	$0.15 / $0.60	128K
162	139174	c4ai-aya-expanse-8b Cohere · CC-BY-NC-4.0	1153±36	231	N/A	N/A
163	141174	mistral-small-24b-instruct-2501 Mistral · Apache 2.0	1149±37	269	$0.05 / $0.08	32.8K
164	150174	gpt-3.5-turbo-0125 OpenAI · Proprietary	1141±21	965	$0.50 / $1.50	16.4K
165	148178	reka-flash-21b-20240226-online Reka AI · Proprietary	1139±35	274	N/A	N/A
166	150175	qwen1.5-110b-chat Alibaba · Qianwen LICENSE	1137±26	599	N/A	N/A
167	152176	qwen1.5-72b-chat Alibaba · Qianwen LICENSE	1133±27	495	N/A	N/A
168	162180	gemma-2-2b-it Google · Gemma license	1118±18	1,228	N/A	N/A
169	160182	reka-flash-21b-20240226 Reka AI · Proprietary	1116±29	440	N/A	N/A
170	161182	phi-3-medium-4k-instruct Microsoft · MIT	1116±24	683	$0.17 / $0.68	N/A
171	162182	mixtral-8x22b-instruct-v0.1 Mistral · Apache 2.0	1109±21	972	$0.90 / $0.90	65.5K
172	159187	gemini-pro-dev-api Google · Proprietary	1104±45	173	$0.35 / $1.05	32.8K
173	162185	qwen1.5-32b-chat Alibaba · Qianwen LICENSE	1099±33	324	N/A	N/A
174	167184	llama-3.1-8b-instruct Meta · Llama 3.1 Community	1086±18	1,234	$0.02 / $0.05	16.4K
175	162190	qwen1.5-14b-chat Alibaba · Qianwen LICENSE	1082±40	217	$0.30 / $0.30	N/A
176	169185	llama-3-70b-instruct Meta · Llama 3 Community	1081±15	3,276	$0.51 / $0.74	8.2K
177	168187	mistral-large-2402 Mistral · Proprietary	1079±22	945	$4 / $12	32K
178	166190	dbrx-instruct-preview Databricks · DBRX LICENSE	1078±30	426	$0.60 / $0.60	32.8K
179	168190	yi-1.5-34b-chat 01 AI · Apache-2.0	1076±27	506	N/A	N/A
180	165190	jamba-1.5-mini AI21 Labs · Jamba Open	1075±36	270	$0.20 / $0.40	256K
181	167190	mistral-medium Mistral · Proprietary	1070±34	337	$2.70 / $8.10	32K
182	172193	gemma-1.1-7b-it Google · Gemma license	1050±30	449	$0.03 / $0.09	8.2K
183	169195	yi-34b-chat 01 AI · Yi License	1050±44	197	$0.90 / $0.90	4.1K
184	173193	snowflake-arctic-instruct Snowflake · Apache 2.0	1042±25	667	N/A	N/A
185	172195	starling-lm-7b-beta Nexusflow · Apache-2.0	1042±44	181	N/A	N/A
186	177193	llama-3-8b-instruct Meta · Llama 3 Community	1035±17	1,992	$0.03 / $0.04	8.2K
187	175195	phi-3-small-8k-instruct Microsoft · MIT	1033±31	390	$0.15 / $0.60	N/A
188	175196	vicuna-33b LMSYS · Non-commercial	1024±41	195	$0 / $0	2K
189	177195	phi-3-mini-4k-instruct-june-2024 Microsoft · MIT	1023±33	354	$0.13 / $0.52	4.1K
190	182196	mixtral-8x7b-instruct-v0.1 Mistral · Apache 2.0	1002±22	960	$0.63 / $0.63	32K
191	177196	vicuna-13b LMSYS · Llama 2 Community	1001±53	125	$0.30 / $0.30	N/A
192	182196	phi-3-mini-4k-instruct Microsoft · MIT	1000±34	384	$0.13 / $0.52	N/A
193	182196	llama-2-70b-chat Meta · Llama 2 Community	988±33	341	$0.70 / $2.80	4.1K
194	185196	phi-3-mini-128k-instruct Microsoft · MIT	981±32	385	$0.13 / $0.52	N/A
195	185196	llama-2-13b-chat Meta · Llama 2 Community	960±49	175	$0.25 / $0.25	4.1K
196	189196	mistral-7b-instruct-v0.2 Mistral · Apache-2.0	943±47	167	$0.20 / $0.20	32.8K

Text Arena🇯🇵Japanese

Default Leaderboard Plots

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

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

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