• New Chat
  • Leaderboard
  • Search
Terms of UsePrivacy Policy
Start Voting
Overview
Agent
Start Voting
Agent

Learn more

Min
Max

Min
Max

Min
Max

Min
Max

Text Arena🇷🇺Russian

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

Jul 21, 2026
704,112 votes
178 open source models
Rank Spread
1
30
glm-5.1
Z.ai · MIT
1470±11
1156
3,192$1.40 / $4.40202.8K
2
33
gemma-4-31b
Google · Apache 2.0
1467±23
779
649$0.14 / $0.40262.1K
3
38
glm-5.2 (max)
Z.ai · MIT
1463±14
1374
1,738$1.40 / $4.401M
4
40
deepseek-v4-pro-thinking
DeepSeek · MIT
1461±9
1970
4,670$0.43 / $0.871M
5
43
deepseek-v4-pro
DeepSeek · MIT
1458±9
2173
4,784$0.43 / $0.871M
6
44
mimo-v2.5-pro
Xiaomi · MIT
1458±10
2174
4,606$0.43 / $0.871.1M
7
51
kimi-k2.6
Moonshot · Modified MIT
1453±10
2782
3,867$0.95 / $4262.1K
8
57
gemma-4-26b-a4b
Google · Apache 2.0
1448±21
2097
680N/AN/A
9
58
glm-5
Z.ai · MIT
1448±11
3088
2,860$1 / $3.20202.8K
10
65
kimi-k2.5-thinking
Moonshot · Modified MIT
1444±8
3688
6,739$0.60 / $3N/A
11
68
minimax-m3
MiniMax · MiniMax Community License
1440±11
3797
3,013$0.60 / $2.40N/A
12
70
qwen3.5-397b-a17b
Alibaba · Apache 2.0
1438±8
4496
5,984$0.39 / $2.34262.1K
13
71
deepseek-v4-flash-thinking
DeepSeek · MIT
1438±9
4397
4,847$0.25 / $1.75200K
14
72
Thinking Machines
inkling
Thinky · Apache 2.0
1438±25
27121
564$1 / $4.051M
15
74
deepseek-v4-flash
DeepSeek · MIT
1437±9
4597
4,835$0.09 / $0.191M
16
77
glm-4.7
Z.ai · MIT
1433±15
40116
1,353$0.40 / $1.75204.8K
17
81
deepseek-v3.1-terminus-thinking
DeepSeek · MIT
1427±36
26143
235$0.27 / $1163.8K
18
84
kimi-k2.5-instant
Moonshot · Modified MIT
1426±19
49128
858$0.57 / $2.85262.1K
19
85
deepseek-v3.1-terminus
DeepSeek · MIT
1425±33
30143
261$0.27 / $1163.8K
20
86
deepseek-v3.2
DeepSeek · MIT
1424±9
61119
4,931$0.27 / $0.40163.8K
21
88
mistral-medium-3.5
Mistral · Modified MIT
1418±18
59135
1,155$1.50 / $7.50262.1K
22
90
Tencent
hunyuan-hy3-preview
Tencent · tencent-hunyuan-community
1418±23
54141
666$0.29 / $1.17262.1K
23
92
qwen3-235b-a22b-instruct-2507
Alibaba · Apache 2.0
1417±7
75125
8,427$0.26 / $1.06N/A
24
94
deepseek-r1-0528
DeepSeek · MIT
1415±16
63137
1,251$0.50 / $2.15163.8K
25
97
kimi-k2-thinking-turbo
Moonshot · Modified MIT
1412±8
77130
6,272$1.15 / $8262.1K
26
98
kimi-k2-0905-preview
Moonshot · Modified MIT
1411±22
61145
698$0.60 / $2.50262.1K
27
101
glm-4.6
Z.ai · MIT
1410±11
76137
2,754$0.50 / $2204.8K
28
103
mistral-large-3
Mistral · Apache 2.0
1408±8
78135
5,154$0.50 / $1.50N/A
29
105
qwen3-235b-a22b-no-thinking
Alibaba · Apache 2.0
1407±12
77139
2,401$0.46 / $1.82131.1K
30
108
deepseek-v3.2-exp-thinking
DeepSeek · MIT
1406±24
64153
504$0.27 / $0.41163.8K
31
110
mimo-v2.5
Xiaomi · MIT
1405±10
81140
4,651$0.14 / $0.281.1M
32
111
deepseek-v3.2-exp
DeepSeek · MIT
1404±20
75151
846$0.27 / $0.41163.8K
33
112
deepseek-v3.1-thinking
DeepSeek · MIT
1403±22
74154
603$1.23 / $4.94N/A
34
113
kimi-k2-0711-preview
Moonshot · Modified MIT
1403±15
78147
1,485$0.60 / $2.50131.1K
35
114
qwen3-235b-a22b-thinking-2507
Alibaba · Apache 2.0
1403±26
66161
436$0.30 / $3262.1K
36
115
deepseek-v3.2-thinking
DeepSeek · MIT
1402±9
83142
4,500$0.27 / $0.40163.8K
37
116
nvidia-nemotron-3-ultra-550b-a55b-nvfp4
Nvidia · OpenMDW-1.1
1402±19
76151
1,080N/AN/A
38
117
minimax-m2.7
MiniMax · Modified MIT
1402±9
83142
5,516$0.25 / $1204.8K
39
118
deepseek-v3.1
DeepSeek · MIT
1402±20
75153
789$1.23 / $4.94N/A
40
119
qwen3-vl-235b-a22b-instruct
Alibaba · Apache 2.0
1401±23
75158
715$0.21 / $1.90262.1K
41
122
deepseek-v3-0324
DeepSeek · MIT
1399±10
85146
3,098$3 / $4.5032.8K
42
125
qwen3.5-122b-a10b
Alibaba · Apache 2.0
1397±11
85147
2,994$0.26 / $2.08262.1K
43
126
glm-4.5
Z.ai · MIT
1396±16
83156
1,247$0.60 / $2.20131.1K
44
131
qwen3.5-27b
Alibaba · Apache 2.0
1391±11
90156
2,834$0.20 / $1.56262.1K
45
132
minimax-m2.5
MiniMax · Modified MIT
1390±9
96155
4,504$0.15 / $0.90204.8K
46
133
qwen3-coder-480b-a35b-instruct
Alibaba · Apache 2.0
1388±15
90164
1,424$0.40 / $1.60262.1K
47
134
qwen3-next-80b-a3b-instruct
Alibaba · Apache 2.0
1387±17
88169
1,190$0.10 / $1.10262.1K
48
138
minimax-m2.1-preview
MiniMax · MIT
1383±13
99169
1,912$0.30 / $1.20204.8K
49
139
deepseek-r1
DeepSeek · MIT
1381±13
104169
1,904$0.70 / $2.50163.8K
50
141
qwen3.5-35b-a3b
Alibaba · Apache 2.0
1378±11
111172
3,139$0.14 / $1262.1K
51
142
qwen3-vl-235b-a22b-thinking
Alibaba · Apache 2.0
1378±26
90185
481$0.26 / $2.60131.1K
52
143
Stepfun
step-3.5-flash
StepFun · Apache 2.0
1377±8
115169
6,334$0.10 / $0.30262.1K
53
149
longcat-flash-chat
Meituan · MIT
1373±21
102185
691$0.20 / $0.80131.1K
54
153
mimo-v2-flash (non-thinking)
Xiaomi · MIT
1370±9
129180
5,213$0.10 / $0.30262.1K
55
154
gemma-3-27b-it
Google · Gemma
1368±10
128181
2,986$0.08 / $0.45262.1K
56
156
trinity-large-preview
Apache 2.0
1366±11
129182
3,261$0.15 / $0.45131K
57
157
qwen3-30b-a3b-instruct-2507
Alibaba · Apache 2.0
1366±16
120189
1,227$0.10 / $0.30262.1K
58
158
mimo-v2-flash (thinking)
Xiaomi · MIT
1365±16
122192
1,279$0.10 / $0.30262.1K
59
161
trinity-large-thinking
Apache 2.0
1360±11
134191
3,115$0.25 / $0.80262.1K
60
163
gemma-3-12b-it
Google · Gemma
1358±32
110209
285$0.05 / $0.15131.1K
61
164
glm-4.5-air
Z.ai · MIT
1358±15
133195
1,485$0.13 / $0.85131.1K
62
165
mistral-small-2506
Mistral · Apache 2.0
1356±18
132199
985$0.10 / $0.3032K
63
166
deepseek-v3
DeepSeek · DeepSeek
1356±11
139193
2,512$1.14 / $4.56N/A
64
167
qwen3-235b-a22b
Alibaba · Apache 2.0
1355±13
139195
1,856$0.46 / $1.82131.1K
65
168
qwen3-next-80b-a3b-thinking
Alibaba · Apache 2.0
1353±21
132206
747$0.10 / $0.78262.1K
66
173
glm-4.7-flash
Z.ai · MIT
1351±15
141202
1,389$0.06 / $0.40202.8K
67
176
minimax-m1
MiniMax · Apache 2.0
1349±13
148202
1,924$0.55 / $2.201M
68
177
glm-4.6v
Z.ai · MIT
1347±33
123227
286$0.30 / $0.90131.1K
69
178
Cohere
command-a-03-2025
Cohere · CC-BY-NC-4.0
1343±9
154205
3,718$2.50 / $10256K
70
182
gpt-oss-120b
OpenAI · Apache 2.0
1335±14
159218
1,607$0.04 / $0.17131.1K
71
183
minimax-m2
MiniMax · Apache 2.0
1335±32
141238
323$0.26 / $1.02204.8K
72
187
intellect-3
MIT
1332±28
149237
449$0.20 / $1.10131.1K
73
191
nvidia-nemotron-3-super-120b-a12b
Nvidia · NVIDIA Open Model
1329±21
159234
815N/AN/A
74
192
qwen3-32b
Alibaba · Apache 2.0
1328±26
154238
412$0.08 / $0.28131.1K
75
194
Meta
llama-4-maverick-17b-128e-instruct
Meta · Llama 4
1327±11
170223
2,653$0.63 / $1.80131.1K
76
197
Stepfun
step-3
StepFun · Apache 2.0
1326±28
154245
404$0.57 / $1.4265.5K
77
201
deepseek-v2.5-1210
DeepSeek · DeepSeek
1322±17
169235
1,034N/AN/A
78
202
glm-4.5v
Z.ai · MIT
1319±31
158252
318$0.60 / $1.8065.5K
79
205
gemma-3-4b-it
Google · Gemma
1315±30
162254
307$0.05 / $0.10131.1K
80
206
llama-3.1-nemotron-ultra-253b-v1
Nvidia · Nvidia Open Model
1313±30
163254
303$0.60 / $1.80131.1K
81
207
Meta
llama-3.1-405b-instruct-fp8
Meta · Llama 3.1 Community
1313±8
182235
7,673$4 / $432.8K
82
208
gemma-3n-e4b-it
Google · Gemma
1312±15
178246
1,393$0.06 / $0.1232.8K
83
211
qwen-max-0919
Alibaba · Qwen
1311±12
181244
2,432$1.60 / $6.4032.8K
84
213
Meta
llama-4-scout-17b-16e-instruct
Meta · Llama
1310±13
181246
1,915$0.40 / $0.708.2K
85
215
qwen3-30b-a3b
Alibaba · Apache 2.0
1307±13
183248
1,906$0.13 / $0.52131.1K
86
219
qwq-32b
Alibaba · Apache 2.0
1306±13
184249
1,914$0.50 / $116.4K
87
220
Meta
llama-3.1-405b-instruct-bf16
Meta · Llama 3.1 Community
1305±9
191246
4,863$4 / $432.8K
88
221
athene-v2-chat
NexusFlow
1305±10
189248
3,448N/AN/A
89
223
mistral-large-2407
Mistral · Mistral Research
1303±9
191248
5,748$2 / $6131.1K
90
224
gpt-oss-20b
OpenAI · Apache 2.0
1302±24
179257
606$0.03 / $0.13131.1K
91
226
olmo-3.1-32b-instruct
Ai2 · Apache 2.0
1300±16
188254
1,392$0.20 / $0.6065.5K
92
227
mistral-small-3.1-24b-instruct-2503
Mistral · Apache 2.0
1299±13
192254
2,010$0.10 / $0.3032K
93
231
qwen2.5-72b-instruct
Alibaba · Qwen
1296±9
198253
5,776$1.20 / $1.20N/A
94
233
mistral-large-2411
Mistral · MRL
1294±10
198254
3,258$2 / $6128K
95
236
Meta
llama-3.3-70b-instruct
Meta · Llama-3.3
1292±8
207254
5,440$0.13 / $0.40131.1K
96
237
ling-flash-2.0
Ant Group · MIT
1291±30
182272
374N/AN/A
97
238
deepseek-v2.5
DeepSeek · DeepSeek
1290±10
207257
3,519N/AN/A
98
239
gemma-2-27b-it
Google · Gemma license
1290±7
210255
9,678$0.65 / $0.658.2K
99
240
llama-3.3-nemotron-49b-super-v1
Nvidia · Nvidia
1289±35
180278
263N/AN/A
100
241
athene-70b-0725
CC-BY-NC-4.0
1288±13
204261
1,934N/AN/A
101
246
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia · NVIDIA Open Model
1278±14
217271
1,690$0.06 / $0.24262.1K
102
249
llama-3.1-tulu-3-70b
Ai2 · Llama 3.1
1276±27
200278
366N/AN/A
103
250
olmo-3-32b-think
Ai2 · Apache 2.0
1272±27
207281
498$0.15 / $0.5065.5K
104
251
gemma-2-9b-it-simpo
MIT
1271±17
220278
1,119$0.03 / $0.098.2K
105
252
qwen2.5-coder-32b-instruct
Alibaba · Apache 2.0
1270±19
220278
822$0.87 / $0.8732K
106
253
granite-4.1-8b
IBM · Apache 2.0
1270±30
207285
447$0.05 / $0.10131.1K
107
254
Meta
llama-3.1-70b-instruct
Meta · Llama 3.1 Community
1269±8
235272
7,285$0.40 / $0.40131.1K
108
255
nemotron-4-340b-instruct
Nvidia · NVIDIA Open Model
1269±13
232278
2,494N/AN/A
109
256
Cohere
command-r-plus-08-2024
Cohere · CC-BY-NC-4.0
1268±15
230278
1,354$2.50 / $10128K
110
261
Cohere
c4ai-aya-expanse-32b
Cohere · CC-BY-NC-4.0
1264±10
242278
3,891N/AN/A
111
263
mistral-small-24b-instruct-2501
Mistral · Apache 2.0
1260±15
239281
1,418$0.05 / $0.0832.8K
112
265
gemma-2-9b-it
Google · Gemma license
1259±8
243278
6,684$0.03 / $0.098.2K
113
266
deepseek-coder-v2
DeepSeek · DeepSeek License
1257±14
242284
1,823$0.14 / $0.28128K
114
267
Cohere
command-r-plus
Cohere · CC-BY-NC-4.0
1256±10
244279
7,778$2.50 / $10128K
115
269
jamba-1.5-large
Jamba Open
1251±18
242288
998$2 / $8256K
116
271
llama-3.1-nemotron-51b-instruct
Nvidia · Llama 3.1
1247±22
242293
605N/AN/A
117
272
phi-4
Microsoft · MIT
1245±11
248287
2,576$0.07 / $0.1416.4K
118
273
ministral-8b-2410
Mistral · MRL
1244±20
245293
760$0.10 / $0.10131.1K
119
274
llama-3.1-nemotron-70b-instruct
Nvidia · Llama 3.1
1241±18
247293
1,069$1.20 / $1.20131.1K
120
275
qwen2-72b-instruct
Alibaba · Qianwen LICENSE
1236±11
262293
4,555$0.90 / $0.9032.8K
121
276
ibm-granite-h-small
IBM · Apache 2.0
1236±33
242298
322N/AN/A
122
278
Cohere
c4ai-aya-expanse-8b
Cohere · CC-BY-NC-4.0
1229±15
267295
1,474N/AN/A
123
279
ring-flash-2.0
Ant Group · MIT
1228±30
247298
381N/AN/A
124
280
Cohere
command-r-08-2024
Cohere · CC-BY-NC-4.0
1227±16
267295
1,350$0.15 / $0.60128K
125
282
olmo-2-0325-32b-instruct
Ai2 · Apache-2.0
1225±33
247299
304$0.05 / $0.20128K
126
283
llama-3.1-tulu-3-8b
Ai2 · Llama 3.1
1223±25
260298
418N/AN/A
127
284
olmo-3.1-32b-think
Ai2 · Apache 2.0
1223±21
266298
903$0.15 / $0.5065.5K
128
286
mixtral-8x22b-instruct-v0.1
Mistral · Apache 2.0
1223±10
271295
4,914$0.90 / $0.9065.5K
129
288
Meta
llama-3-70b-instruct
Meta · Llama 3 Community
1220±8
272295
14,995$0.51 / $0.748.2K
130
290
jamba-1.5-mini
Jamba Open
1217±18
270298
998$0.20 / $0.40256K
131
292
wizardlm-70b
Microsoft · Llama 2 Community
1213±46
247311
172N/AN/A
132
293
Cohere
command-r
Cohere · CC-BY-NC-4.0
1212±11
277298
5,283$0.15 / $0.60128K
133
295
phi-3-medium-4k-instruct
Microsoft · MIT
1192±12
285300
2,964$0.17 / $0.68N/A
134
296
Meta
llama-3.1-8b-instruct
Meta · Llama 3.1 Community
1189±9
292302
6,589$0.05 / $0.08131.1K
135
297
openchat-3.5
Apache-2.0
1185±41
272320
187$0.20 / $0.20N/A
136
298
zephyr-orpo-141b-A35b-v0.1
Apache 2.0
1184±27
281313
407N/AN/A
137
300
qwen1.5-110b-chat
Alibaba · Qianwen LICENSE
1173±12
293312
2,898N/AN/A
138
301
gemma-2-2b-it
Google · Gemma license
1171±9
295312
5,974N/AN/A
139
302
Meta
llama-3-8b-instruct
Meta · Llama 3 Community
1171±9
295312
10,009$0.14 / $0.148.2K
140
303
qwen1.5-72b-chat
Alibaba · Qianwen LICENSE
1168±13
294314
2,666N/AN/A
141
304
snowflake-arctic-instruct
Apache 2.0
1167±13
294315
2,784N/AN/A
142
305
phi-3-small-8k-instruct
Microsoft · MIT
1167±13
295315
2,195$0.15 / $0.60N/A
143
306
mixtral-8x7b-instruct-v0.1
Mistral · Apache 2.0
1158±11
295320
5,239$0.63 / $0.6332K
144
307
dbrx-instruct-preview
DBRX LICENSE
1158±13
295320
3,044$0.60 / $0.6032.8K
145
308
starling-lm-7b-alpha
CC-BY-NC-4.0
1152±27
295326
410N/AN/A
146
309
granite-3.1-8b-instruct
IBM · Apache 2.0
1149±29
295326
467N/AN/A
147
310
openchat-3.5-0106
Apache-2.0
1148±21
295325
790N/AN/A
148
311
internlm2_5-20b-chat
Other
1145±16
300324
1,425$0 / $032.8K
149
312
vicuna-33b
Non-commercial
1142±22
297326
703$0 / $02K
150
313
qwen1.5-32b-chat
Alibaba · Qianwen LICENSE
1138±14
304326
2,175N/AN/A
151
314
gemma-1.1-7b-it
Google · Gemma license
1137±13
304326
2,709$0.03 / $0.098.2K
152
315
yi-1.5-34b-chat
Apache-2.0
1137±12
305326
3,231N/AN/A
153
316
starling-lm-7b-beta
Apache-2.0
1137±17
304326
1,405N/AN/A
154
317
granite-3.0-8b-instruct
IBM · Apache 2.0
1136±20
301327
954N/AN/A
155
318
Meta
llama-2-70b-chat
Meta · Llama 2 Community
1135±14
304327
1,981$0.70 / $2.804.1K
156
319
zephyr-7b-beta
MIT
1130±38
295331
202$0.15 / $0.1516.4K
157
320
vicuna-13b
Llama 2 Community
1127±27
302331
448$0.30 / $0.30N/A
158
321
Meta
llama-2-13b-chat
Meta · Llama 2 Community
1113±21
308331
783$0.25 / $0.254.1K
159
322
qwq-32b-preview
Alibaba · Apache 2.0
1111±26
308333
527$0.50 / $116.4K
160
323
yi-34b-chat
Yi License
1110±21
308332
789$0.90 / $0.904.1K
161
324
granite-3.1-2b-instruct
IBM · Apache 2.0
1109±28
308333
464N/AN/A
162
325
granite-3.0-2b-instruct
IBM · Apache 2.0
1107±20
310332
1,056N/AN/A
163
326
qwen1.5-14b-chat
Alibaba · Qianwen LICENSE
1104±16
317332
1,741$0.30 / $0.30N/A
164
327
gemma-1.1-2b-it
Google · Gemma license
1089±19
319336
1,166N/AN/A
165
328
mistral-7b-instruct-v0.2
Mistral · Apache-2.0
1086±17
319336
1,203$0.20 / $0.2032.8K
166
329
mistral-7b-instruct
Mistral · Apache 2.0
1086±42
309338
175$0.07 / $0.284.1K
167
330
gemma-7b-it
Google · Gemma license
1078±23
319338
629$0.05 / $0.088.2K
168
331
phi-3-mini-4k-instruct-june-2024
Microsoft · MIT
1073±17
322338
1,415$0.13 / $0.524.1K
169
332
qwen1.5-7b-chat
Alibaba · Qianwen LICENSE
1067±35
319338
296$0.20 / $0.20N/A
170
333
phi-3-mini-4k-instruct
Microsoft · MIT
1066±13
327338
2,751$0.13 / $0.52N/A
171
334
phi-3-mini-128k-instruct
Microsoft · MIT
1062±16
327338
1,800$0.13 / $0.52N/A
172
335
Meta
llama-2-7b-chat
Meta · Llama 2 Community
1054±23
327338
580$0.15 / $0.154.1K
173
336
smollm2-1.7b-instruct
Apache 2.0
1054±32
325339
410N/AN/A
174
337
qwen1.5-4b-chat
Alibaba · Qianwen LICENSE
1039±25
329339
564$0.10 / $0.10N/A
175
338
gemma-2b-it
Google · Gemma license
1029±36
329341
300$0.10 / $0.10N/A
176
339
Meta
llama-3.2-3b-instruct
Meta · Llama 3.2
1004±24
336341
933$0.05 / $0.33131.1K
177
340
Meta
llama-3.2-1b-instruct
Meta · Llama 3.2
987±24
338341
953$0.03 / $0.2060K
178
341
olmo-7b-instruct
Ai2 · Apache-2.0
978±28
338341
497$0.20 / $0.20N/A

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)

USE CASES

  • Chat with AI
  • Build Apps & Websites
  • Write & Edit Text
  • Search the Web
  • Generate Images
  • Generate Videos
  • Chose any model
  • Compare Models Side by Side

LEADERBOARD RANKINGS

  • Overall
  • Agent
  • Text
  • WebDev
  • Image-to-WebDev
  • Text to Image
  • Image Edit
  • Text to Video
  • Image to Video
  • Video Edit
  • Vision
  • Document
  • Search

COMPANY

  • About Us
  • How It Works
  • Blog
  • Careers
  • Changelog
  • Help Center
  • FAQ

LEGAL

  • Terms
  • Privacy
  • Cookies

FOLLOW

  • X
  • LinkedIn
  • YouTube
  • Discord

© Arena Intelligence 2026