Text Arena📊Longer Query

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

May 28, 2026
1,276,419 votes
338 models
Rank Spread
1
13
Anthropic
Anthropic · Proprietary
1526±7
11,853$5 / $251M
2
14
Anthropic
Anthropic · Proprietary
1517±6
13,077$5 / $251M
3
15
Anthropic
Anthropic · Proprietary
1515±8
8,256$5 / $251M
4
29
Anthropic
Anthropic · Proprietary
1508±8
8,671$5 / $251M
5
414
Google · Proprietary
1499±6
15,876$2 / $121M
6
328
Alibaba · Proprietary
1495±16
1,625$1.25 / $3.751M
7
420
Anthropic
Anthropic · Proprietary
1495±7
9,992$3 / $151M
8
420
Anthropic
1495±7
9,258$5 / $25200K
9
521
Google · Proprietary
1492±7
10,496$2 / $121M
10
422
OpenAI · Proprietary
1492±8
6,782$5 / $301.1M
11
521
Anthropic
Anthropic · Proprietary
1492±5
20,053$5 / $25200K
12
524
Z.ai · MIT
1491±9
5,378$1.40 / $4.40202.8K
13
527
Xiaomi · MIT
1488±8
6,318$0.43 / $0.871M
14
527
OpenAI · Proprietary
1488±7
10,627$2.50 / $151.1M
15
628
Anthropic
1485±6
11,148$15 / $75200K
16
627
Anthropic
1485±5
22,126$3 / $15200K
17
628
Anthropic
Anthropic · Proprietary
1484±5
22,429$3 / $15200K
18
632
OpenAI · Proprietary
1483±7
11,342$2.50 / $151.1M
19
633
Alibaba · Proprietary
1481±8
7,372N/AN/A
20
638
Google · Proprietary
1480±11
3,663$1.50 / $91M
21
836
OpenAI · Proprietary
1480±8
7,030$5 / $301.1M
22
1138
Moonshot · Modified MIT
1475±8
6,089$0.95 / $4262.1K
23
1138
Google · Proprietary
1475±7
7,878$0.50 / $31M
24
1241
1474±8
6,400$0.43 / $0.871M
25
1541
OpenAI · Proprietary
1473±7
11,142$5 / $301.1M
26
1838
Anthropic
Anthropic · Proprietary
1472±5
17,745$15 / $75200K
27
1841
OpenAI · Proprietary
1472±7
11,474$1.75 / $14128K
28
1244
Meta
Meta · Proprietary
1472±9
4,355N/AN/A
29
1843
Z.ai · MIT
1470±7
7,224$1 / $3.20202.8K
30
1054
Alibaba · Proprietary
1470±14
1,760$1.04 / $6.24262.1K
31
1949
DeepSeek · MIT
1469±8
6,777$0.43 / $0.871M
32
1849
Baidu · Proprietary
1468±9
5,528N/AN/A
33
1258
Google · Apache 2.0
1467±14
1,637$0.14 / $0.40262.1K
34
2049
xAI · Proprietary
1466±7
8,173N/AN/A
35
2052
Xiaomi · Proprietary
1465±7
8,191$1 / $31M
36
2052
Anthropic
Anthropic · Proprietary
1465±8
6,931$15 / $75200K
37
2152
1464±7
10,946$2 / $62M
38
2149
1464±6
17,413$0.50 / $31M
39
2561
1459±7
10,714$2 / $62M
40
2561
OpenAI · Proprietary
1459±7
10,271$1.25 / $10400K
41
3061
Google · Proprietary
1457±4
31,190$1.25 / $101M
42
3064
Moonshot · Modified MIT
1456±6
12,008$0.60 / $3N/A
43
3065
OpenAI · Proprietary
1455±7
11,016$1.75 / $14128K
44
3065
Alibaba · Apache 2.0
1454±6
11,640$0.39 / $2.34262.1K
45
2970
Xiaomi · MIT
1454±8
6,653$0.14 / $0.281M
46
3072
Alibaba · Proprietary
1453±8
7,213$0.33 / $1.951M
47
2878
Z.ai · MIT
1453±11
3,103$0.40 / $1.75202.8K
48
3472
Bytedance
Bytedance · Proprietary
1452±6
13,121N/AN/A
49
2891
Google · Apache 2.0
1449±15
1,547N/AN/A
50
3874
xAI · Proprietary
1449±5
18,583N/AN/A
51
3880
OpenAI · Proprietary
1448±7
10,171$0.75 / $4.50400K
52
3781
1448±8
6,767$0.10 / $0.201M
53
3976
xAI · Proprietary
1448±5
18,634N/AN/A
54
3881
Anthropic
Anthropic · Proprietary
1447±7
8,361$15 / $75200K
55
3491
DeepSeek · MIT
1446±12
2,362$1.23 / $4.94N/A
56
3885
xAI · Proprietary
1446±8
6,584$1.25 / $2.501M
57
3492
Moonshot · Modified MIT
1446±12
2,215$0.40 / $1.90262.1K
58
3988
DeepSeek · MIT
1445±8
6,890$0.10 / $0.201M
59
25103
1444±22
680$0.27 / $0.95163.8K
60
4290
Alibaba · Proprietary
1444±8
6,037$0.78 / $3.90262.1K
61
4286
OpenAI · Proprietary
1444±6
11,470$1.25 / $10400K
62
3794
OpenAI · Proprietary
1443±14
1,796$75 / $150128K
63
3993
DeepSeek · MIT
1442±11
2,939$0.27 / $0.41163.8K
64
4590
Baidu · Proprietary
1441±6
10,316N/AN/A
65
4392
Anthropic
1441±8
6,725$3 / $151M
66
4590
OpenAI · Proprietary
1441±6
15,663$1.75 / $14400K
67
4591
DeepSeek · MIT
1441±6
10,364$0.25 / $0.38131.1K
68
4690
OpenAI · Proprietary
1441±5
17,318$5 / $15128K
69
4691
DeepSeek · MIT
1440±6
12,217$0.25 / $0.38131.1K
70
4992
Anthropic
Anthropic · Proprietary
1438±5
22,921$1 / $5200K
71
4896
OpenAI · Proprietary
1436±8
6,738$1.25 / $10128K
72
5194
OpenAI · Proprietary
1435±6
14,850$1.75 / $14400K
73
42110
Xiaomi · Proprietary
1435±17
1,255$0.40 / $2262.1K
74
5096
Meituan · Proprietary
1435±7
8,548N/AN/A
75
45101
Baidu · Proprietary
1435±12
2,456N/AN/A
76
5494
Alibaba · Apache 2.0
1435±4
24,643$0.26 / $1.06N/A
77
5296
Z.ai · MIT
1433±7
8,751$0.43 / $1.74202.8K
78
5496
Moonshot · Modified MIT
1433±5
17,498$1.15 / $8262.1K
79
48106
Alibaba · Proprietary
1432±13
2,065$0.78 / $3.90262.1K
80
49110
1431±13
2,070$0.27 / $0.41163.8K
81
5799
Google · Proprietary
1430±6
12,714$0.25 / $1.501M
82
50112
Tencent
Tencent · tencent-hunyuan-community
1430±13
2,294$0.29 / $1.17262.1K
83
57103
MiniMax · Modified MIT
1429±7
8,393$0.28 / $1.20204.8K
84
55106
xAI · Proprietary
1429±9
4,878$3 / $15131.1K
85
45124
1428±19
947N/AN/A
86
60107
Anthropic
1427±8
6,155$3 / $15200K
87
65107
Anthropic
Anthropic · Proprietary
1426±7
7,690$3 / $151M
88
54118
Alibaba · Apache 2.0
1425±13
2,204$0.20 / $0.88262.1K
89
69110
OpenAI · Proprietary
1424±6
9,833$2 / $81M
90
72110
xAI · Proprietary
1423±5
16,033$0.20 / $0.502M
91
51128
1422±19
886N/AN/A
92
72114
Alibaba · Apache 2.0
1422±7
9,157$0.20 / $1.56262.1K
93
56125
xAI · Proprietary
1422±15
1,457$3 / $15256K
94
68119
DeepSeek · MIT
1421±11
3,221$1.23 / $4.94N/A
95
56127
Baidu · Proprietary
1420±17
1,152N/AN/A
96
77114
Google · Proprietary
1419±4
30,538$0.30 / $2.501M
97
54133
DeepSeek · MIT
1418±20
846$0.27 / $0.95163.8K
98
76119
1418±7
7,928$0.30 / $2.501M
99
77120
xAI · Proprietary
1417±7
8,841$3 / $15256K
100
78119
Mistral · Apache 2.0
1417±6
11,900$0.50 / $1.50N/A
101
76124
Z.ai · MIT
1417±9
5,017$0.60 / $2.20131.1K
102
78124
Alibaba · Apache 2.0
1416±7
9,621$0.26 / $2.08262.1K
103
89125
Mistral · Proprietary
1412±4
25,190$2.70 / $8.1032K
104
80128
OpenAI · Proprietary
1412±10
3,571$15 / $60200K
105
80128
xAI · Proprietary
1412±9
4,451$0.20 / $0.502M
106
84127
Alibaba · Apache 2.0
1411±8
7,146$0.46 / $1.82131.1K
107
84128
OpenAI · Proprietary
1411±8
6,805$1.25 / $10400K
108
82129
MiniMax · MIT
1410±9
4,255$0.29 / $0.95204.8K
109
88128
Anthropic
Anthropic · Proprietary
1410±7
6,679$3 / $15200K
110
88130
Alibaba · Apache 2.0
1409±9
4,883$0.40 / $1.60262.1K
111
91128
OpenAI · Proprietary
1408±6
11,463$2 / $8200K
112
84135
DeepSeek · MIT
1408±11
3,138$0.50 / $2.15163.8K
113
91129
Stepfun
StepFun · Apache 2.0
1407±6
11,283$0.09 / $0.30262.1K
114
80136
Alibaba · Apache 2.0
1407±14
1,730$0.26 / $2.60131.1K
115
96134
1404±6
14,001$0.10 / $0.30262.1K
116
95135
Alibaba · Apache 2.0
1404±7
9,872$0.14 / $1262.1K
117
96135
MiniMax · Modified MIT
1403±6
12,634$0.15 / $1.15204.8K
118
91138
1403±11
2,814$0.10 / $0.30262.1K
119
96136
OpenAI · Proprietary
1402±7
10,020$0.20 / $1.25400K
120
91140
Moonshot · Modified MIT
1402±12
2,544$0.60 / $2.50262.1K
121
89144
Alibaba · Apache 2.0
1401±14
1,624$0.15 / $1.50262.1K
122
76154
Tencent
Tencent · Proprietary
1401±25
506N/AN/A
123
99136
Alibaba · Proprietary
1401±7
10,528N/AN/A
124
92144
DeepSeek · MIT
1399±12
2,303$0.70 / $2.50163.8K
125
111144
DeepSeek · MIT
1393±7
8,461$3 / $4.5032.8K
126
112142
Anthropic
Anthropic · Proprietary
1393±6
13,789$3 / $15200K
127
109148
Moonshot · Modified MIT
1393±8
5,501$0.60 / $2.50131.1K
128
112150
Alibaba · Apache 2.0
1391±8
5,217$0.09 / $1.10262.1K
129
114148
Arcee AI · Apache 2.0
1391±7
9,676$0.15 / $0.45131K
130
112150
Mistral · Proprietary
1391±8
5,905$0.40 / $2131.1K
131
96166
Tencent
Tencent · Proprietary
1390±20
889N/AN/A
132
117150
OpenAI · Proprietary
1389±8
7,047$0.40 / $1.601M
133
113159
Meituan · MIT
1386±12
2,343$0.20 / $0.80131.1K
134
120153
1386±6
11,479$0.10 / $0.401M
135
101169
1386±20
760N/AN/A
136
120154
Alibaba · Proprietary
1384±9
4,516N/AN/A
137
121159
Alibaba · Apache 2.0
1382±9
4,882$0.09 / $0.30262.1K
138
121162
OpenAI · Proprietary
1381±10
4,578$15 / $60N/A
139
103183
Z.ai · MIT
1380±23
663$0.30 / $0.90131.1K
140
123161
Z.ai · MIT
1380±8
6,632$0.13 / $0.85131.1K
141
126166
1378±8
6,300$0.10 / $0.401M
142
123166
Alibaba · Apache 2.0
1378±9
4,584$0.46 / $1.82131.1K
143
122168
xAI · Proprietary
1378±10
3,303$0.25 / $1.27N/A
144
101187
Tencent
Tencent · Proprietary
1376±28
371N/AN/A
145
122176
Tencent
Tencent · Proprietary
1375±15
1,530N/AN/A
146
126171
DeepSeek · DeepSeek
1375±11
3,123$1.14 / $4.56N/A
147
131168
1373±8
6,119N/AN/A
148
128174
Z.ai · MIT
1373±11
3,169$0.06 / $0.40202.8K
149
126175
OpenAI · Proprietary
1372±12
2,160$1.10 / $4.40200K
150
131180
Alibaba · Apache 2.0
1370±11
2,831$0.10 / $0.78262.1K
151
132174
OpenAI · Proprietary
1369±8
5,775$0.25 / $2400K
152
134173
Cohere
Cohere · CC-BY-NC-4.0
1369±6
10,525$2.50 / $10256K
153
134175
OpenAI · Proprietary
1368±7
8,549$1.10 / $4.40200K
154
133183
xAI · Proprietary
1366±9
4,149$0.30 / $0.50131.1K
155
136180
Arcee AI · Apache 2.0
1366±7
9,511$0.22 / $0.85262.1K
156
137183
MiniMax · Apache 2.0
1365±7
6,963$0.40 / $2.201M
157
138183
Google · Gemma
1364±7
6,645$0.08 / $0.16131.1K
158
138183
Google · Proprietary
1363±8
6,497$0.10 / $0.401M
159
128199
Alibaba · Proprietary
1362±21
690$0.40 / $1.20131.1K
160
134187
Nvidia · NVIDIA Open Model
1361±13
2,013N/AN/A
161
138185
Mistral · Apache 2.0
1361±10
3,404$0.10 / $0.3032K
162
144185
OpenAI · Proprietary
1358±6
9,223$1.10 / $4.40200K
163
145185
Google · Proprietary
1356±7
8,372$3.50 / $10.502.1M
164
131212
Alibaba · Apache 2.0
1355±25
504$0.08 / $0.28131.1K
165
126222
Tencent
Tencent · Proprietary
1355±32
287N/AN/A
166
144198
1354±12
2,582N/AN/A
167
141206
Prime Intellect · MIT
1352±17
1,262$0.20 / $1.10131.1K
168
151195
Anthropic
Anthropic · Proprietary
1351±8
10,574$3 / $15200K
169
153199
Google · Proprietary
1350±8
9,750$3.50 / $10.502.1M
170
153202
1347±10
2,940$0.07 / $0.301M
171
145212
Stepfun
StepFun · Apache 2.0
1347±16
1,258$0.57 / $1.4265.5K
172
134225
Google · Gemma
1346±29
371$0.04 / $0.13131.1K
173
158202
OpenAI · Proprietary
1345±8
7,913$1.10 / $4.40N/A
174
148215
Stepfun
StepFun · Proprietary
1344±17
1,265N/AN/A
175
143224
1344±22
642$0.10 / $0.40131.1K
176
153215
MiniMax · Apache 2.0
1343±15
1,588$0.26 / $1204.8K
177
161202
Anthropic
Anthropic · Proprietary
1343±6
10,987$0.80 / $4200K
178
136229
Tencent
Tencent · Proprietary
1343±30
313N/AN/A
179
150221
Z.ai · MIT
1342±18
1,070$0.60 / $1.8065.5K
180
146224
Stepfun
StepFun · Proprietary
1342±21
693N/AN/A
181
138230
Nvidia · Nvidia Open Model
1341±30
321$0.60 / $1.80131.1K
182
161212
Alibaba · Apache 2.0
1340±9
4,460$0.09 / $0.45131.1K
183
151224
Z.ai · Proprietary
1339±20
765N/AN/A
184
163215
OpenAI · Proprietary
1338±8
6,160$2.50 / $10128K
185
141234
1338±30
317N/AN/A
186
158224
DeepSeek · DeepSeek
1337±17
1,037N/AN/A
187
163217
Ai2 · Apache 2.0
1337±11
2,874$0.20 / $0.6065.5K
188
163217
Amazon · Proprietary
1336±11
2,920$0.30 / $2.501M
189
163215
Alibaba · Apache 2.0
1336±9
4,025$0.50 / $116.4K
190
151230
1335±24
575N/AN/A
191
163222
Mistral · Proprietary
1335±12
2,386$2 / $540K
192
165215
xAI · Proprietary
1335±7
8,902$2 / $10131.1K
193
164215
1335±7
7,067$0.63 / $1.80131.1K
194
151235
Tencent
Tencent · Proprietary
1333±27
432N/AN/A
195
167220
OpenAI · Proprietary
1331±7
14,922$5 / $15128K
196
163228
Ant Group · MIT
1330±16
1,333N/AN/A
197
164228
OpenAI · Proprietary
1329±15
1,620$0.05 / $0.40400K
198
170224
1327±8
5,759$0.40 / $0.708.2K
199
164230
Ant Group · MIT
1327±16
1,254N/AN/A
200
171224
Anthropic
Anthropic · Proprietary
1327±6
23,374$15 / $75200K
201
171225
Meta
Meta · Llama 3.1 Community
1326±8
5,486$4 / $432.8K
202
171224
OpenAI · Proprietary
1326±7
8,980$0.15 / $0.60128K
203
167229
Alibaba · Qwen
1326±12
2,440$1.60 / $6.4032.8K
204
170225
Z.ai · Proprietary
1325±10
3,992$0.44 / $1.76204.8K
205
170227
01.AI
01 AI · Proprietary
1325±11
3,634N/AN/A
206
171225
OpenAI · Apache 2.0
1325±8
6,453$0.04 / $0.18131.1K
207
163237
OpenAI · Proprietary
1325±20
730$0.10 / $0.401M
208
163238
Inception AI · Proprietary
1324±20
844$0.25 / $0.75128K
209
171229
Google · Proprietary
1323±10
5,486N/AN/A
210
174228
1322±8
6,301$0.10 / $0.3032K
211
173229
Google · Proprietary
1322±8
5,463$0.07 / $0.301M
212
174230
NexusFlow · NexusFlow
1321±10
3,663N/AN/A
213
170238
Ai2 · Apache 2.0
1320±17
1,344$0.15 / $0.5065.5K
214
180230
Meta
Meta · Llama 3.1 Community
1318±8
8,047$4 / $432.8K
215
182231
Alibaba · Qwen
1317±8
6,008$1.20 / $1.20N/A
216
182231
xAI · Proprietary
1317±8
7,048$2 / $10131.1K
217
184233
OpenAI · Proprietary
1316±8
11,559$10 / $30128K
218
171248
Tencent
Tencent · Proprietary
1314±20
877N/AN/A
219
183238
DeepSeek · DeepSeek
1314±10
3,499N/AN/A
220
193237
Meta
Meta · Llama-3.3
1312±7
8,307$0.10 / $0.32131.1K
221
186241
Google · Gemma
1311±11
2,853$0.06 / $0.1232.8K
222
167255
Google · Gemma
1311±27
444$0.04 / $0.08131.1K
223
180251
IBM · Apache 2.0
1308±18
1,280$0.05 / $0.10131.1K
224
186248
Alibaba · Proprietary
1308±14
1,586N/AN/A
225
197244
OpenAI · Proprietary
1306±9
9,653$10 / $30128K
226
201248
Mistral · MRL
1304±10
3,607$2 / $6131.1K
227
205248
Mistral · Mistral Research
1303±9
5,885$2 / $6131.1K
228
197251
Ai2 · Apache 2.0
1301±14
1,970$0.15 / $0.5065.5K
229
198251
OpenAI · Apache 2.0
1301±13
2,093$0.03 / $0.14131.1K
230
212251
OpenAI · Proprietary
1300±9
9,140$10 / $30128K
231
212251
Google · Proprietary
1300±9
7,837$0.07 / $0.301M
232
210251
Amazon · Proprietary
1300±10
3,398$0.80 / $3.20300K
233
215251
Google · Gemma license
1299±7
9,918$0.65 / $0.658.2K
234
182264
Inception AI · Proprietary
1297±27
493$0.25 / $0.75128K
235
220253
Meta
Meta · Llama 3.1 Community
1293±8
7,622$0.40 / $0.40131.1K
236
217256
NexusFlow · CC-BY-NC-4.0
1292±12
2,123N/AN/A
237
220255
Nvidia · NVIDIA Open Model
1292±10
3,851$0.06 / $0.24262.1K
238
213262
IBM · Apache 2.0
1290±17
1,280N/AN/A
239
221256
Cohere
Cohere · CC-BY-NC-4.0
1289±9
4,165N/AN/A
240
214266
Princeton · MIT
1288±19
841$0.03 / $0.098.2K
241
220262
Nvidia · NVIDIA Open Model
1287±13
2,130N/AN/A
242
215266
Alibaba · Apache 2.0
1286±19
804$0.87 / $0.8732K
243
220264
DeepSeek · DeepSeek License
1286±14
1,842$0.14 / $0.28128K
244
226261
Anthropic
Anthropic · Proprietary
1284±9
11,870$3 / $15200K
245
221266
1280±18
1,049$1.20 / $1.20131.1K
246
222266
Cohere
Cohere · CC-BY-NC-4.0
1280±15
1,369$2.50 / $10128K
247
226266
Mistral · Apache 2.0
1279±14
1,767$0.05 / $0.0832.8K
248
222267
Reka AI · Proprietary
1279±18
951N/AN/A
249
233266
OpenAI · Proprietary
1276±9
7,523$30 / $608.2K
250
233266
OpenAI · Proprietary
1275±12
4,251$30 / $608.2K
251
234266
Amazon · Proprietary
1274±11
2,784$0.06 / $0.24300K
252
222273
Ai2 · Llama 3.1
1272±25
463N/AN/A
253
222274
Tencent
Tencent · Proprietary
1270±27
414N/AN/A
254
226273
1269±23
587N/AN/A
255
234272
Z.ai · Proprietary
1267±17
1,174N/AN/A
256
238270
Microsoft · MIT
1266±11
2,896$0.07 / $0.1416.4K
257
239269
Google · Proprietary
1266±8
5,573$0.07 / $0.301M
258
241270
Anthropic
Anthropic · Proprietary
1264±8
13,976$0.25 / $1.25200K
259
241270
Google · Gemma license
1264±8
6,877$0.03 / $0.098.2K
260
236274
Reka AI · Proprietary
1263±18
992N/AN/A
261
238273
Cohere
Cohere · CC-BY-NC-4.0
1261±15
1,421$0.15 / $0.60128K
262
238274
AI21 Labs · Jamba Open
1260±17
1,024$2 / $8256K
263
243272
Cohere
Cohere · CC-BY-NC-4.0
1260±9
9,149$2.50 / $10128K
264
243272
Alibaba · Qianwen LICENSE
1259±10
4,614$0.90 / $0.9032.8K
265
238277
Mistral · MRL
1258±20
720$0.10 / $0.10131.1K
266
252274
Meta
Meta · Llama 3 Community
1251±8
17,500$0.51 / $0.748.2K
267
252277
Amazon · Proprietary
1248±11
2,625$0.04 / $0.14128K
268
251279
Cohere
Cohere · CC-BY-NC-4.0
1247±15
1,483N/AN/A
269
256278
Mistral · Proprietary
1245±10
6,217$4 / $1232K
270
238294
Ai2 · Apache-2.0
1243±34
261$0.05 / $0.20128K
271
262286
Alibaba · Qianwen LICENSE
1234±12
3,483N/AN/A
272
266286
Cohere
Cohere · CC-BY-NC-4.0
1231±10
6,160$0.15 / $0.60128K
273
253297
IBM · Apache 2.0
1230±27
461N/AN/A
274
266289
Alibaba · Qianwen LICENSE
1227±12
3,345N/AN/A
275
256298
Ai2 · Llama 3.1
1226±26
454N/AN/A
276
266294
Google · Proprietary
1223±18
1,351$0.35 / $1.0532.8K
277
270290
Meta
Meta · Llama 3.1 Community
1223±8
6,736$0.02 / $0.05131.1K
278
268292
Alibaba · Qianwen LICENSE
1222±13
2,574N/AN/A
279
259299
IBM · Apache 2.0
1221±26
489N/AN/A
280
270292
OpenAI · Proprietary
1218±9
6,707$0.50 / $1.5016.4K
281
270297
Mistral · Proprietary
1217±13
2,718$2.70 / $8.1032K
282
269298
AI21 Labs · Jamba Open
1216±18
1,023$0.20 / $0.40256K
283
270294
Mistral · Apache 2.0
1216±10
5,865$0.90 / $0.9065.5K
284
270298
Reka AI · Proprietary
1215±16
1,650N/AN/A
285
270297
Reka AI · Proprietary
1215±13
2,719N/AN/A
286
273299
Meta
Meta · Llama 3 Community
1206±9
11,165$0.04 / $0.048.2K
287
272302
01.AI
01 AI · Apache-2.0
1202±13
2,098N/AN/A
288
270308
IBM · Apache 2.0
1201±24
603N/AN/A
289
272306
InternLM · Other
1199±16
1,266$0 / $032.8K
290
279309
Alibaba · Qianwen LICENSE
1190±15
2,102$0.30 / $0.30N/A
291
282309
Microsoft · MIT
1189±13
2,150$0.17 / $0.68N/A
292
285310
Databricks · DBRX LICENSE
1186±13
3,489$0.60 / $0.6032.8K
293
287308
Google · Gemma license
1185±9
5,866N/AN/A
294
279314
OpenAI · Proprietary
1184±20
933$1 / $216.4K
295
272322
DeepSeek · DeepSeek License
1181±37
243N/AN/A
296
274318
HuggingFace · Apache 2.0
1181±28
448N/AN/A
297
276318
OpenChat · Apache-2.0
1181±28
414$0.20 / $0.20N/A
298
287312
Mistral · Apache 2.0
1180±10
6,572$0.63 / $0.6332K
299
274321
Microsoft · Llama 2 Community
1180±32
355N/AN/A
300
279318
Alibaba · Apache 2.0
1178±26
475$0.50 / $116.4K
301
276322
AllenAI/UW · AI2 ImpACT Low-risk
1176±33
280N/AN/A
302
288319
01.AI
01 AI · Yi License
1169±18
1,106$0.90 / $0.904.1K
303
288319
OpenChat · Apache-2.0
1168±19
1,097N/AN/A
304
289318
Google · Gemma license
1165±13
2,649$0.03 / $0.098.2K
305
289321
Nexusflow · Apache-2.0
1164±16
1,676N/AN/A
306
287325
Alibaba · Qianwen LICENSE
1162±30
372$0.20 / $0.20N/A
307
294322
Microsoft · MIT
1160±13
2,238$0.15 / $0.60N/A
308
291323
Meta
Meta · Llama 3.2
1157±18
1,046$0.05 / $0.34131.1K
309
294327
UC Berkeley · CC-BY-NC-4.0
1149±23
666N/AN/A
310
288332
Microsoft · Llama 2 Community
1148±40
203$0.30 / $0.30N/A
311
295330
IBM · Apache 2.0
1146±25
647N/AN/A
312
296330
LMSYS · Llama 2 Community
1142±22
756$0.30 / $0.30N/A
313
288335
LMSYS · Llama 2 Community
1140±44
162$0.20 / $0.20N/A
314
296330
Meta
Meta · Llama 2 Community
1138±18
1,193$0.25 / $0.254.1K
315
293333
Google · Proprietary
1137±37
251$0.50 / $0.5025.8K
316
295332
NousResearch · Apache-2.0
1137±33
270$0.17 / $0.17N/A
317
302328
Meta
Meta · Llama 2 Community
1136±13
2,813$0.70 / $2.804.1K
318
300332
LMSYS · Non-commercial
1132±19
1,047$0 / $02K
319
304331
Mistral · Apache-2.0
1132±15
1,592$0.20 / $0.2032.8K
320
296335
HuggingFace · Apache 2.0
1130±33
328N/AN/A
321
307332
Snowflake · Apache 2.0
1127±14
2,793N/AN/A
322
296336
Alibaba · Qianwen LICENSE
1125±38
214N/AN/A
323
308335
Google · Gemma license
1115±18
1,179N/AN/A
324
302338
NousResearch · Apache-2.0
1114±35
230$0.90 / $0.90N/A
325
308336
Google · Gemma license
1110±23
676$0.05 / $0.088.2K
326
311336
Microsoft · MIT
1106±15
1,706$0.13 / $0.52N/A
327
310337
1105±19
1,035$0.13 / $0.524.1K
328
309338
HuggingFace · MIT
1104±28
461$0.15 / $0.1516.4K
329
314337
Meta
Meta · Llama 3.2
1100±19
1,057$0.03 / $0.20131.1K
330
309338
Meta
Meta · Llama 2 Community
1096±33
320$0.35 / $1.4016.4K
331
311338
Mistral · Apache 2.0
1096±27
448$0.07 / $0.284.1K
332
315338
Google · Gemma license
1082±31
377$0.10 / $0.10N/A
333
320338
Alibaba · Qianwen LICENSE
1076±24
692$0.10 / $0.10N/A
334
323338
Meta
Meta · Llama 2 Community
1074±20
835$0.15 / $0.154.1K
335
319338
Together AI · Apache 2.0
1070±32
334$0.20 / $0.20N/A
336
326338
Microsoft · MIT
1070±16
2,074$0.13 / $0.52N/A
337
320338
Nvidia · Llama 2 Community
1055±43
208N/AN/A
338
328338
Tsinghua · Apache-2.0
1040±40
205N/AN/A

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)

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)