Text Arena🤓Expert

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

May 17, 2026

336,354 votes

162 open source models

Rank by

				Rank Spread
1	7	mimo-v2.5-pro Xiaomi · MIT	1522±20	132	857	$1 / $3	1M
2	11	kimi-k2.6 Moonshot · Modified MIT	1507±19	344	857	$0.95 / $4	262.1K
3	22	glm-5.1 Z.ai · MIT	1497±18	555	1,066	$1.40 / $4.40	202.8K
4	29	kimi-k2.5-thinking Moonshot · Modified MIT	1488±13	958	2,238	$0.60 / $3	N/A
5	30	glm-5 Z.ai · MIT	1487±14	961	1,628	$1 / $3.20	202.8K
6	31	deepseek-v4-pro-thinking DeepSeek · MIT	1485±20	770	901	$0.43 / $0.87	1M
7	34	gemma-4-31b Google · Apache 2.0	1482±26	684	435	$0.14 / $0.40	262.1K
8	39	gemma-4-26b-a4b Google · Apache 2.0	1479±27	790	406	N/A	N/A
9	45	qwen3.5-397b-a17b Alibaba · Apache 2.0	1473±13	1876	2,142	$0.39 / $2.34	262.1K
10	46	deepseek-v4-pro DeepSeek · MIT	1471±19	1390	977	$0.43 / $0.87	1M
11	50	deepseek-v4-flash-thinking DeepSeek · MIT	1468±19	1893	931	$0.11 / $0.22	1M
12	51	mimo-v2.5 Xiaomi · MIT	1467±19	1894	927	$0.40 / $2	1M
13	54	qwen3-235b-a22b-thinking-2507 Alibaba · Apache 2.0	1464±28	11110	412	$0.15 / $1.50	262.1K
14	58	hunyuan-hy3-preview Tencent · tencent-hunyuan-community	1459±24	19111	504	$0.29 / $1.17	262.1K
15	59	kimi-k2-thinking-turbo Moonshot · Modified MIT	1458±10	3394	3,773	$1.15 / $8	262.1K
16	61	kimi-k2.5-instant Moonshot · Modified MIT	1457±24	20111	565	$0.40 / $1.90	262.1K
17	63	deepseek-v3.2-thinking DeepSeek · MIT	1454±12	35102	2,450	$0.25 / $0.38	131.1K
18	65	qwen3-vl-235b-a22b-instruct Alibaba · Apache 2.0	1450±25	27117	564	$0.20 / $0.88	262.1K
19	69	qwen3-235b-a22b-instruct-2507 Alibaba · Apache 2.0	1449±8	44102	5,395	$0.26 / $1.06	N/A
20	70	deepseek-v3.2 DeepSeek · MIT	1448±11	41108	2,917	$0.25 / $0.38	131.1K
21	72	deepseek-v4-flash DeepSeek · MIT	1448±19	34115	919	$0.11 / $0.22	1M
22	73	deepseek-v3.2-exp-thinking DeepSeek · MIT	1447±29	26126	396	$0.27 / $0.41	163.8K
23	74	glm-4.7 Z.ai · MIT	1447±22	33117	718	$0.40 / $1.75	202.8K
24	76	qwen3.5-122b-a10b Alibaba · Apache 2.0	1447±13	41111	1,949	$0.26 / $2.08	262.1K
25	80	glm-4.6 Z.ai · MIT	1442±14	46116	1,856	$0.43 / $1.74	202.8K
26	83	glm-4.5 Z.ai · MIT	1439±18	44120	1,107	$0.60 / $2.20	131.1K
27	84	minimax-m2.7 MiniMax · Modified MIT	1438±16	48118	1,368	$0.28 / $1.20	204.8K
28	85	qwen3.5-27b Alibaba · Apache 2.0	1438±14	53118	1,866	$0.20 / $1.56	262.1K
29	87	minimax-m2.5 MiniMax · Modified MIT	1435±13	55118	2,287	$0.15 / $1.15	204.8K
30	89	minimax-m2.1-preview MiniMax · MIT	1434±18	49129	1,056	$0.29 / $0.95	204.8K
31	92	qwen3-vl-235b-a22b-thinking Alibaba · Apache 2.0	1432±30	36139	378	$0.26 / $2.60	131.1K
32	93	step-3.5-flash StepFun · Apache 2.0	1432±13	58124	2,185	$0.10 / $0.30	262.1K
33	95	deepseek-v3.1-thinking DeepSeek · MIT	1430±25	47137	531	$1.23 / $4.94	N/A
34	97	deepseek-v3.1 DeepSeek · MIT	1428±22	53137	726	$1.23 / $4.94	N/A
35	99	longcat-flash-chat Meituan · MIT	1425±26	53143	519	$0.20 / $0.80	131.1K
36	100	qwen3.5-35b-a3b Alibaba · Apache 2.0	1423±13	66134	1,963	$0.14 / $1	262.1K
37	102	deepseek-v3.2-exp DeepSeek · MIT	1422±23	58143	607	$0.27 / $0.41	163.8K
38	104	mistral-large-3 Mistral · Apache 2.0	1421±11	74135	2,871	$0.50 / $1.50	N/A
39	105	deepseek-r1-0528 DeepSeek · MIT	1421±20	63140	881	$0.50 / $2.15	163.8K
40	108	mimo-v2-flash (thinking) Xiaomi · MIT	1418±22	63143	710	$0.10 / $0.30	262.1K
41	109	kimi-k2-0905-preview Moonshot · Modified MIT	1418±25	59148	555	$0.60 / $2.50	262.1K
42	110	mimo-v2-flash (non-thinking) Xiaomi · MIT	1417±11	76137	3,019	$0.10 / $0.30	262.1K
43	112	kimi-k2-0711-preview Moonshot · Modified MIT	1414±16	75143	1,460	$0.60 / $2.50	131.1K
44	120	trinity-large-preview Arcee AI · Apache 2.0	1404±14	93152	2,089	$0.15 / $0.45	131K
45	124	glm-4.5v Z.ai · MIT	1402±41	59170	196	$0.60 / $1.80	65.5K
46	126	nvidia-nemotron-3-super-120b-a12b Nvidia · NVIDIA Open Model	1400±24	81163	588	N/A	N/A
47	128	deepseek-r1 DeepSeek · MIT	1399±20	88158	848	$0.70 / $2.50	163.8K
48	129	trinity-large-thinking Arcee AI · Apache 2.0	1399±16	94157	1,440	$0.22 / $0.85	262.1K
49	130	qwen3-32b Alibaba · Apache 2.0	1398±38	67170	236	$0.08 / $0.28	131.1K
50	131	deepseek-v3-0324 DeepSeek · MIT	1398±12	95156	2,294	$3 / $4.50	32.8K
51	133	qwen3-next-80b-a3b-instruct Alibaba · Apache 2.0	1396±18	94160	1,005	$0.09 / $1.10	262.1K
52	134	qwen3-235b-a22b-no-thinking Alibaba · Apache 2.0	1396±14	96157	1,878	$0.46 / $1.82	131.1K
53	135	qwen3-30b-a3b-instruct-2507 Alibaba · Apache 2.0	1394±17	94162	1,145	$0.09 / $0.30	262.1K
54	136	glm-4.7-flash Z.ai · MIT	1390±20	94165	801	$0.06 / $0.40	202.8K
55	137	glm-4.5-air Z.ai · MIT	1389±16	101165	1,390	$0.13 / $0.85	131.1K
56	140	qwen3-235b-a22b Alibaba · Apache 2.0	1385±16	104165	1,320	$0.46 / $1.82	131.1K
57	141	qwen3-next-80b-a3b-thinking Alibaba · Apache 2.0	1385±23	96169	620	$0.10 / $0.78	262.1K
58	145	qwen3-coder-480b-a35b-instruct Alibaba · Apache 2.0	1379±17	111168	1,319	$0.40 / $1.60	262.1K
59	154	minimax-m1 MiniMax · Apache 2.0	1364±15	128179	1,594	$0.40 / $2.20	1M
60	155	qwq-32b Alibaba · Apache 2.0	1362±17	128182	1,199	$0.50 / $1	16.4K
61	156	nvidia-llama-3.3-nemotron-super-49b-v1.5 Nvidia · Nvidia Open	1361±42	102205	180	$0.10 / $0.40	131.1K
62	157	ling-flash-2.0 Ant Group · MIT	1361±30	116192	341	N/A	N/A
63	158	step-3 StepFun · Apache 2.0	1361±35	111195	259	$0.57 / $1.42	65.5K
64	159	gpt-oss-120b OpenAI · Apache 2.0	1361±16	130184	1,318	$0.04 / $0.18	131.1K
65	160	ring-flash-2.0 Ant Group · MIT	1360±33	115194	332	N/A	N/A
66	161	intellect-3 Prime Intellect · MIT	1354±34	119202	309	$0.20 / $1.10	131.1K
67	167	deepseek-v3 DeepSeek · DeepSeek	1347±17	142192	1,236	$1.14 / $4.56	N/A
68	168	nvidia-nemotron-3-nano-30b-a3b-bf16 Nvidia · NVIDIA Open Model	1346±20	140194	945	$0.06 / $0.24	262.1K
69	169	qwen3-30b-a3b Alibaba · Apache 2.0	1344±17	144193	1,316	$0.09 / $0.45	131.1K
70	171	minimax-m2 MiniMax · Apache 2.0	1339±35	133220	258	$0.26 / $1	204.8K
71	172	command-a-03-2025 Cohere · CC-BY-NC-4.0	1339±11	151193	2,783	$2.50 / $10	256K
72	173	mistral-small-2506 Mistral · Apache 2.0	1336±20	148207	840	$0.10 / $0.30	32K
73	175	gemma-3-27b-it Google · Gemma	1335±13	152200	2,225	$0.08 / $0.16	131.1K
74	176	olmo-3.1-32b-instruct Ai2 · Apache 2.0	1332±22	149214	753	$0.20 / $0.60	65.5K
75	180	llama-4-maverick-17b-128e-instruct Meta · Llama 4	1325±13	159213	1,994	$0.63 / $1.80	131.1K
76	181	granite-4.1-8b IBM · Apache 2.0	1325±34	146226	323	$0.05 / $0.10	131.1K
77	182	olmo-3.1-32b-think Ai2 · Apache 2.0	1323±27	151222	503	$0.15 / $0.50	65.5K
78	185	llama-3.1-405b-instruct-fp8 Meta · Llama 3.1 Community	1321±11	159214	3,123	$4 / $4	32.8K
79	186	gpt-oss-20b OpenAI · Apache 2.0	1318±28	153226	489	$0.03 / $0.14	131.1K
80	187	olmo-3-32b-think Ai2 · Apache 2.0	1316±38	151235	275	$0.15 / $0.50	65.5K
81	193	athene-v2-chat NexusFlow · NexusFlow	1311±15	167223	1,469	N/A	N/A
82	197	llama-4-scout-17b-16e-instruct Meta · Llama	1308±16	169226	1,503	$0.40 / $0.70	8.2K
83	198	llama-3.1-405b-instruct-bf16 Meta · Llama 3.1 Community	1308±13	170224	2,128	$4 / $4	32.8K
84	199	ibm-granite-h-small IBM · Apache 2.0	1306±37	155243	283	N/A	N/A
85	200	deepseek-v2.5-1210 DeepSeek · DeepSeek	1306±26	159234	441	N/A	N/A
86	201	mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0	1304±15	172227	1,644	$0.10 / $0.30	32K
87	204	mistral-large-2407 Mistral · Mistral Research	1299±13	177228	2,505	$2 / $6	131.1K
88	205	qwen-max-0919 Alibaba · Qwen	1299±18	173233	1,011	$1.60 / $6.40	32.8K
89	206	athene-70b-0725 NexusFlow · CC-BY-NC-4.0	1296±19	175235	867	N/A	N/A
90	207	deepseek-v2.5 DeepSeek · DeepSeek	1295±15	178234	1,523	N/A	N/A
91	209	llama-3.3-70b-instruct Meta · Llama-3.3	1294±11	180230	2,894	$0.10 / $0.32	131.1K
92	210	qwen2.5-72b-instruct Alibaba · Qwen	1294±12	180233	2,397	$1.20 / $1.20	N/A
93	212	llama-3.1-nemotron-70b-instruct Nvidia · Llama 3.1	1293±27	171244	453	$1.20 / $1.20	131.1K
94	220	jamba-1.5-large AI21 Labs · Jamba Open	1283±29	177250	331	$2 / $8	256K
95	222	gemma-3n-e4b-it Google · Gemma	1278±18	188247	1,071	$0.06 / $0.12	32.8K
96	224	qwen2.5-coder-32b-instruct Alibaba · Apache 2.0	1275±33	180259	267	$0.87 / $0.87	32K
97	227	llama-3.1-70b-instruct Meta · Llama 3.1 Community	1272±12	201247	2,924	$0.40 / $0.40	131.1K
98	228	gemma-3-12b-it Google · Gemma	1271±42	177268	186	$0.04 / $0.13	131.1K
99	229	mistral-large-2411 Mistral · MRL	1269±15	199250	1,510	$2 / $6	131.1K
100	231	phi-4 Microsoft · MIT	1266±17	201255	1,124	$0.07 / $0.14	16.4K
101	233	deepseek-coder-v2 DeepSeek · DeepSeek License	1263±21	199259	769	$0.14 / $0.28	128K
102	234	c4ai-aya-expanse-32b Cohere · CC-BY-NC-4.0	1262±14	211256	1,764	N/A	N/A
103	237	mistral-small-24b-instruct-2501 Mistral · Apache 2.0	1257±21	209266	754	$0.05 / $0.08	32.8K
104	238	qwen2-72b-instruct Alibaba · Qianwen LICENSE	1257±15	213259	1,763	$0.90 / $0.90	32.8K
105	239	gemma-3-4b-it Google · Gemma	1257±41	187273	208	$0.04 / $0.08	131.1K
106	240	nemotron-4-340b-instruct Nvidia · NVIDIA Open Model	1256±19	211264	1,027	N/A	N/A
107	241	gemma-2-27b-it Google · Gemma license	1255±11	218257	4,025	$0.65 / $0.65	8.2K
108	243	llama-3.1-nemotron-51b-instruct Nvidia · Llama 3.1	1249±33	201273	265	N/A	N/A
109	246	command-r-plus-08-2024 Cohere · CC-BY-NC-4.0	1246±25	213271	524	$2.50 / $10	128K
110	248	llama-3-70b-instruct Meta · Llama 3 Community	1240±11	228268	7,958	$0.51 / $0.74	8.2K
111	250	command-r-plus Cohere · CC-BY-NC-4.0	1238±12	229270	4,031	$2.50 / $10	128K
112	251	ministral-8b-2410 Mistral · MRL	1235±30	217277	332	$0.10 / $0.10	131.1K
113	252	gemma-2-9b-it Google · Gemma license	1232±12	233271	2,847	$0.03 / $0.09	8.2K
114	253	granite-3.1-8b-instruct IBM · Apache 2.0	1231±35	215283	237	N/A	N/A
115	254	qwen1.5-72b-chat Alibaba · Qianwen LICENSE	1231±15	232273	1,846	N/A	N/A
116	255	gemma-2-9b-it-simpo Princeton · MIT	1230±30	223280	369	$0.03 / $0.09	8.2K
117	256	c4ai-aya-expanse-8b Cohere · CC-BY-NC-4.0	1228±24	228278	600	N/A	N/A
118	257	command-r-08-2024 Cohere · CC-BY-NC-4.0	1227±22	231278	604	$0.15 / $0.60	128K
119	258	qwen1.5-110b-chat Alibaba · Qianwen LICENSE	1225±17	238274	1,411	N/A	N/A
120	262	qwen1.5-32b-chat Alibaba · Qianwen LICENSE	1219±18	240280	1,176	N/A	N/A
121	263	yi-1.5-34b-chat 01 AI · Apache-2.0	1217±19	241282	1,049	N/A	N/A
122	264	internlm2_5-20b-chat InternLM · Other	1217±22	238283	604	$0 / $0	32.8K
123	265	granite-3.1-2b-instruct IBM · Apache 2.0	1214±36	229290	225	N/A	N/A
124	266	mixtral-8x22b-instruct-v0.1 Mistral · Apache 2.0	1214±14	244281	2,582	$0.90 / $0.90	65.5K
125	268	command-r Cohere · CC-BY-NC-4.0	1210±14	248283	2,830	$0.15 / $0.60	128K
126	269	jamba-1.5-mini AI21 Labs · Jamba Open	1210±31	238290	332	$0.20 / $0.40	256K
127	271	llama-3-8b-instruct Meta · Llama 3 Community	1206±12	250283	5,360	$0.04 / $0.04	8.2K
128	272	phi-3-medium-4k-instruct Microsoft · MIT	1201±18	250286	1,091	$0.17 / $0.68	N/A
129	273	granite-3.0-8b-instruct IBM · Apache 2.0	1200±31	242293	345	N/A	N/A
130	274	llama-3.1-8b-instruct Meta · Llama 3.1 Community	1195±12	255286	2,589	$0.02 / $0.05	131.1K
131	275	mixtral-8x7b-instruct-v0.1 Mistral · Apache 2.0	1192±13	255290	3,240	$0.63 / $0.63	32K
132	277	qwen1.5-14b-chat Alibaba · Qianwen LICENSE	1190±20	254293	944	$0.30 / $0.30	N/A
133	278	dbrx-instruct-preview Databricks · DBRX LICENSE	1186±16	259293	1,678	$0.60 / $0.60	32.8K
134	279	llama-3.2-3b-instruct Meta · Llama 3.2	1175±25	263300	499	$0.05 / $0.34	131.1K
135	281	granite-3.0-2b-instruct IBM · Apache 2.0	1173±29	259302	407	N/A	N/A
136	282	starling-lm-7b-beta Nexusflow · Apache-2.0	1170±20	269300	952	N/A	N/A
137	283	gemma-1.1-7b-it Google · Gemma license	1168±18	269300	1,247	$0.03 / $0.09	8.2K
138	284	zephyr-orpo-141b-A35b-v0.1 HuggingFace · Apache 2.0	1168±40	255305	219	N/A	N/A
139	285	gemma-2-2b-it Google · Gemma license	1167±13	272298	2,525	N/A	N/A
140	286	phi-3-small-8k-instruct Microsoft · MIT	1162±19	271302	895	$0.15 / $0.60	N/A
141	287	snowflake-arctic-instruct Snowflake · Apache 2.0	1159±17	276303	1,722	N/A	N/A
142	288	openchat-3.5-0106 OpenChat · Apache-2.0	1159±23	271303	611	N/A	N/A
143	289	openchat-3.5 OpenChat · Apache-2.0	1159±42	261306	194	$0.20 / $0.20	N/A
144	290	qwq-32b-preview Alibaba · Apache 2.0	1153±36	269306	232	$0.50 / $1	16.4K
145	291	yi-34b-chat 01 AI · Yi License	1152±25	276305	559	$0.90 / $0.90	4.1K
146	292	phi-3-mini-4k-instruct-june-2024 Microsoft · MIT	1145±26	276305	486	$0.13 / $0.52	4.1K
147	293	qwen1.5-7b-chat Alibaba · Qianwen LICENSE	1144±37	272308	231	$0.20 / $0.20	N/A
148	294	vicuna-33b LMSYS · Non-commercial	1141±27	279306	484	$0 / $0	2K
149	295	phi-3-mini-4k-instruct Microsoft · MIT	1136±20	279306	936	$0.13 / $0.52	N/A
150	296	mistral-7b-instruct-v0.2 Mistral · Apache-2.0	1136±21	279306	798	$0.20 / $0.20	32.8K
151	297	starling-lm-7b-alpha UC Berkeley · CC-BY-NC-4.0	1134±31	279308	318	N/A	N/A
152	298	llama-2-70b-chat Meta · Llama 2 Community	1133±17	280306	1,356	$0.70 / $2.80	4.1K
153	299	llama-2-7b-chat Meta · Llama 2 Community	1130±28	279308	411	$0.15 / $0.15	4.1K
154	300	llama-2-13b-chat Meta · Llama 2 Community	1125±25	280308	539	$0.25 / $0.25	4.1K
155	301	gemma-7b-it Google · Gemma license	1116±31	284308	340	$0.05 / $0.08	8.2K
156	302	vicuna-13b LMSYS · Llama 2 Community	1112±31	286308	321	$0.30 / $0.30	N/A
157	303	gemma-1.1-2b-it Google · Gemma license	1110±26	288308	578	N/A	N/A
158	304	zephyr-7b-beta HuggingFace · MIT	1109±38	284308	201	$0.15 / $0.15	16.4K
159	305	qwen1.5-4b-chat Alibaba · Qianwen LICENSE	1103±31	288308	356	$0.10 / $0.10	N/A
160	306	phi-3-mini-128k-instruct Microsoft · MIT	1093±20	297308	1,095	$0.13 / $0.52	N/A
161	307	llama-3.2-1b-instruct Meta · Llama 3.2	1080±28	297308	487	$0.03 / $0.20	131.1K
162	308	mistral-7b-instruct Mistral · Apache 2.0	1079±40	291308	183	$0.07 / $0.28	4.1K

Text Arena🤓Expert

Default Leaderboard Plots

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

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)