Text Arena🧮Math

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

May 14, 2026
584,633 votes
347 models
Rank Spread
1
111
Anthropic
Anthropic · Proprietary
1513±15
1,553$5 / $251M
2
115
OpenAI · Proprietary
1509±17
1,198$2.50 / $151.1M
3
115
Anthropic
Anthropic · Proprietary
1508±14
1,753$5 / $251M
4
120
Google · Proprietary
1500±13
2,023$2 / $121M
5
126
Baidu · Proprietary
1497±26
460N/AN/A
6
123
Anthropic
Anthropic · Proprietary
1497±22
695$5 / $251M
7
124
Anthropic
Anthropic · Proprietary
1494±21
720$5 / $251M
8
137
OpenAI · Proprietary
1486±26
520$5 / $301.1M
9
137
OpenAI · Proprietary
1484±24
548$5 / $301.1M
10
141
Xiaomi · MIT
1483±25
494$1 / $31M
11
234
Alibaba · Proprietary
1480±18
1,021N/AN/A
12
431
Google · Proprietary
1477±11
2,651$2 / $121M
13
437
Google · Proprietary
1474±13
2,009$0.50 / $31M
14
253
Moonshot · Modified MIT
1473±24
526$0.95 / $4262.1K
15
537
Moonshot · Modified MIT
1473±13
1,883$0.60 / $3N/A
16
262
1470±25
535$0.43 / $0.871M
17
176
Alibaba · Proprietary
1470±31
297$1.04 / $6.24262.1K
18
453
Z.ai · MIT
1469±21
760$1.40 / $4.40202.8K
19
276
Google · Apache 2.0
1467±29
365N/AN/A
20
462
Alibaba · Proprietary
1467±21
687$0.33 / $1.951M
21
557
Anthropic
Anthropic · Proprietary
1463±16
1,275$3 / $151M
22
482
Google · Apache 2.0
1463±28
400$0.14 / $0.40262.1K
23
853
Anthropic
Anthropic · Proprietary
1459±10
3,599$5 / $25200K
24
758
Anthropic
1459±12
2,271$5 / $25200K
25
671
1457±17
1,236$2 / $62M
26
971
1452±11
2,674$0.50 / $31M
27
880
OpenAI · Proprietary
1452±16
1,290$2.50 / $151.1M
28
686
Meta
Meta · Proprietary
1452±21
719N/AN/A
29
1466
Google · Proprietary
1451±7
7,220$1.25 / $101M
30
883
Xiaomi · Proprietary
1450±17
1,231$1 / $31M
31
982
Alibaba · Proprietary
1450±15
1,526$0.78 / $3.90262.1K
32
1576
Anthropic
1448±9
4,206$3 / $15200K
33
1086
Alibaba · Apache 2.0
1447±14
1,634$0.39 / $2.34262.1K
34
8103
DeepSeek · MIT
1445±25
499$0.11 / $0.221M
35
1092
1445±16
1,259$2 / $62M
36
1586
OpenAI · Proprietary
1442±12
2,502$1.25 / $10400K
37
1586
OpenAI · Proprietary
1442±12
2,565$1.75 / $14400K
38
1494
xAI · Proprietary
1442±16
1,325N/AN/A
39
1591
Baidu · Proprietary
1442±13
1,891N/AN/A
40
1496
Alibaba · Apache 2.0
1441±17
1,211$0.09 / $1.10262.1K
41
8108
Moonshot · Modified MIT
1441±25
515$0.40 / $1.90262.1K
42
9105
Meituan · MIT
1441±22
688$0.20 / $0.80131.1K
43
5126
1441±39
207N/AN/A
44
1597
Z.ai · MIT
1439±16
1,283$1 / $3.20202.8K
45
1596
Bytedance
Bytedance · Proprietary
1438±14
1,791N/AN/A
46
1597
OpenAI · Proprietary
1438±15
1,664$1.75 / $14128K
47
10110
Alibaba · Proprietary
1438±24
586$0.78 / $3.90262.1K
48
15105
Meituan · Proprietary
1436±18
998N/AN/A
49
1896
DeepSeek · MIT
1436±11
2,901$0.25 / $0.38131.1K
50
14114
DeepSeek · MIT
1435±23
622$0.43 / $0.871M
51
20103
Z.ai · MIT
1433±13
2,112$0.43 / $1.74202.8K
52
2597
Alibaba · Apache 2.0
1432±8
5,554$0.26 / $1.06N/A
53
20108
1431±14
1,588N/AN/A
54
22108
Google · Proprietary
1431±14
1,652$0.25 / $1.501M
55
20110
Alibaba · Apache 2.0
1430±16
1,318$0.20 / $1.56262.1K
56
25103
Anthropic
1430±11
3,025$15 / $75200K
57
25105
Moonshot · Modified MIT
1429±10
3,420$1.15 / $8262.1K
58
23111
Alibaba · Apache 2.0
1428±15
1,402$0.26 / $2.08262.1K
59
23115
Z.ai · MIT
1427±16
1,428$0.60 / $2.20131.1K
60
19121
1427±20
805N/AN/A
61
15129
1426±27
482$0.27 / $0.41163.8K
62
15133
Tencent
Tencent · tencent-hunyuan-community
1426±29
333$0.29 / $1.17262.1K
63
18124
Alibaba · Apache 2.0
1425±23
703$0.20 / $0.88262.1K
64
31109
OpenAI · Proprietary
1425±10
3,730$2 / $8200K
65
28115
xAI · Proprietary
1424±12
2,266$3 / $15256K
66
22123
Z.ai · MIT
1423±21
712$0.40 / $1.75202.8K
67
32114
xAI · Proprietary
1423±10
3,411N/AN/A
68
23124
DeepSeek · MIT
1422±20
773$0.27 / $0.41163.8K
69
36111
Anthropic
Anthropic · Proprietary
1422±9
4,731$15 / $75200K
70
25123
OpenAI · Proprietary
1421±18
1,006$0.20 / $1.25400K
71
28126
DeepSeek · MIT
1420±18
992$1.23 / $4.94N/A
72
15144
1420±37
234N/AN/A
73
37117
xAI · Proprietary
1419±10
3,937N/AN/A
74
15139
OpenAI · Proprietary
1418±31
340$5 / $301.1M
75
23135
1418±25
529$0.11 / $0.221M
76
36122
OpenAI · Proprietary
1418±12
2,292$1.75 / $14400K
77
20138
xAI · Proprietary
1417±29
399$3 / $15256K
78
36122
DeepSeek · MIT
1417±12
2,408$0.25 / $0.38131.1K
79
39120
Anthropic
Anthropic · Proprietary
1417±9
4,225$3 / $15200K
80
36123
1416±13
1,941$0.30 / $2.501M
81
22138
xAI · Proprietary
1416±28
419$1.25 / $2.501M
82
32132
OpenAI · Proprietary
1415±18
1,047$0.75 / $4.50400K
83
23140
Alibaba · Apache 2.0
1415±28
428$0.26 / $2.60131.1K
84
25137
Xiaomi · MIT
1415±25
497$0.40 / $21M
85
39123
Mistral · Apache 2.0
1414±11
2,691$0.50 / $1.50N/A
86
29136
DeepSeek · MIT
1414±22
664$1.23 / $4.94N/A
87
28139
Alibaba · Apache 2.0
1412±24
491$0.15 / $1.50262.1K
88
38133
OpenAI · Proprietary
1412±15
1,393$75 / $150128K
89
51123
Google · Proprietary
1410±7
7,483$0.30 / $2.501M
90
22154
Baidu · Proprietary
1410±34
268N/AN/A
91
51124
Mistral · Proprietary
1410±8
5,421$2.70 / $8.1032K
92
45130
OpenAI · Proprietary
1410±11
2,873$1.25 / $10400K
93
18158
Tencent
Tencent · Proprietary
1409±38
236N/AN/A
94
42135
Alibaba · Proprietary
1409±15
1,426N/AN/A
95
48130
xAI · Proprietary
1409±11
3,268$0.20 / $0.502M
96
45135
OpenAI · Proprietary
1409±14
1,785$1.25 / $10128K
97
36143
Baidu · Proprietary
1407±23
622N/AN/A
98
18161
1407±41
200$0.27 / $0.95163.8K
99
57131
OpenAI · Proprietary
1406±8
5,721$5 / $15128K
100
45137
Alibaba · Apache 2.0
1405±15
1,382$0.14 / $1262.1K
101
45140
xAI · Proprietary
1403±18
1,084$0.20 / $0.502M
102
45145
DeepSeek · MIT
1403±20
869$0.50 / $2.15163.8K
103
45143
MiniMax · Modified MIT
1403±19
950$0.28 / $1.20204.8K
104
29159
1402±33
263N/AN/A
105
48148
Microsoft AI · Proprietary
1400±19
891N/AN/A
106
59140
Stepfun
StepFun · Apache 2.0
1399±14
1,758$0.10 / $0.30262.1K
107
28163
DeepSeek · MIT
1399±38
219$0.27 / $0.95163.8K
108
63140
Alibaba · Apache 2.0
1398±12
2,393$0.46 / $1.82131.1K
109
61140
OpenAI · Proprietary
1398±14
1,888$1.25 / $10400K
110
38159
Alibaba · Apache 2.0
1398±30
316$0.08 / $0.28131.1K
111
59145
Z.ai · MIT
1398±15
1,539$0.13 / $0.85131.1K
112
51154
Moonshot · Modified MIT
1397±21
760$0.60 / $2.50262.1K
113
65144
1396±12
2,452$0.10 / $0.30262.1K
114
64146
OpenAI · Proprietary
1395±13
1,909$1.10 / $4.40200K
115
64147
Alibaba · Apache 2.0
1395±14
1,604$0.46 / $1.82131.1K
116
55155
Alibaba · Apache 2.0
1395±20
830$0.10 / $0.78262.1K
117
63150
Alibaba · Apache 2.0
1395±15
1,428$0.09 / $0.30262.1K
118
59154
MiniMax · MIT
1394±18
1,017$0.29 / $0.95204.8K
119
32164
1394±39
194$0.10 / $0.40131.1K
120
66152
DeepSeek · MIT
1392±14
1,606$0.70 / $2.50163.8K
121
73152
Anthropic
Anthropic · Proprietary
1390±12
2,243$15 / $75200K
122
78150
xAI · Proprietary
1390±11
2,677$3 / $15131.1K
123
68154
MiniMax · Modified MIT
1390±14
1,753$0.15 / $1.15204.8K
124
79154
OpenAI · Proprietary
1388±11
2,986$15 / $60200K
125
76157
OpenAI · Apache 2.0
1388±14
1,796$0.04 / $0.18131.1K
126
82154
OpenAI · Proprietary
1387±11
2,938$1.10 / $4.40200K
127
85154
Anthropic
Anthropic · Proprietary
1386±9
4,253$1 / $5200K
128
54165
Prime Intellect · MIT
1385±31
332$0.20 / $1.10131.1K
129
78158
OpenAI · Proprietary
1385±15
1,605$1.75 / $14128K
130
64163
Nvidia · NVIDIA Open Model
1384±25
507N/AN/A
131
76161
xAI · Proprietary
1384±18
976$0.25 / $1.27N/A
132
78164
1379±22
633$0.10 / $0.30262.1K
133
88162
OpenAI · Proprietary
1377±15
1,457$0.25 / $2400K
134
93162
Anthropic
1375±13
2,026$3 / $151M
135
100162
DeepSeek · MIT
1374±10
3,192$3 / $4.5032.8K
136
107161
OpenAI · Proprietary
1373±8
4,722$1.10 / $4.40200K
137
100162
Anthropic
Anthropic · Proprietary
1373±11
2,773$15 / $75200K
138
102162
1373±11
2,883$0.10 / $0.401M
139
89164
Nvidia · NVIDIA Open Model
1373±18
993$0.06 / $0.24262.1K
140
106162
OpenAI · Proprietary
1373±10
4,569$15 / $60N/A
141
83169
Ant Group · MIT
1371±26
462N/AN/A
142
100164
xAI · Proprietary
1370±14
1,531$0.30 / $0.50131.1K
143
91165
Arcee AI · Apache 2.0
1370±20
868$0.22 / $0.85262.1K
144
111163
Alibaba · Proprietary
1369±10
3,306N/AN/A
145
113164
OpenAI · Proprietary
1368±10
3,230$2 / $81M
146
108165
Moonshot · Modified MIT
1367±14
1,697$0.60 / $2.50131.1K
147
81172
Stepfun
StepFun · Apache 2.0
1367±31
352$0.57 / $1.4265.5K
148
109165
Alibaba · Apache 2.0
1366±15
1,628$0.40 / $1.60262.1K
149
120165
1363±12
2,099$0.10 / $0.401M
150
121165
MiniMax · Apache 2.0
1362±13
1,798$0.40 / $2.201M
151
85178
Nvidia · Nvidia Open Model
1359±37
209$0.60 / $1.80131.1K
152
122167
Alibaba · Apache 2.0
1359±14
1,719$0.50 / $116.4K
153
111172
Amazon · Proprietary
1359±20
833$0.30 / $2.501M
154
113172
Tencent
Tencent · Proprietary
1359±19
845N/AN/A
155
109172
Z.ai · MIT
1358±21
716$0.06 / $0.40202.8K
156
126165
OpenAI · Proprietary
1358±8
7,499$1.10 / $4.40N/A
157
124167
Anthropic
Anthropic · Proprietary
1358±12
2,478$3 / $151M
158
126171
Alibaba · Apache 2.0
1354±14
1,709$0.09 / $0.45131.1K
159
95181
MiniMax · Apache 2.0
1354±33
317$0.26 / $1204.8K
160
129171
Mistral · Proprietary
1352±12
2,231$0.40 / $2131.1K
161
135169
Google · Proprietary
1352±9
4,067$0.10 / $0.401M
162
103182
Z.ai · MIT
1349±34
277$0.60 / $1.8065.5K
163
121180
Ant Group · MIT
1348±27
454N/AN/A
164
143174
OpenAI · Proprietary
1343±11
2,694$0.40 / $1.601M
165
138177
Mistral · Apache 2.0
1341±18
1,042$0.10 / $0.3032K
166
150175
Anthropic
1337±11
2,794$3 / $15200K
167
152182
Arcee AI · Apache 2.0
1330±15
1,516$0.15 / $0.45131K
168
152189
Alibaba · Proprietary
1326±19
732$0.40 / $1.20131.1K
169
161188
Anthropic
Anthropic · Proprietary
1318±10
3,358$3 / $15200K
170
154197
Stepfun
StepFun · Proprietary
1318±24
564N/AN/A
171
156197
OpenAI · Apache 2.0
1318±22
680$0.03 / $0.14131.1K
172
154201
OpenAI · Proprietary
1316±27
494$0.05 / $0.40400K
173
150207
Ai2 · Apache 2.0
1315±32
314$0.15 / $0.5065.5K
174
164189
Google · Proprietary
1315±7
7,610$3.50 / $10.502.1M
175
165193
Google · Gemma
1311±9
3,578$0.08 / $0.16131.1K
176
160202
Ai2 · Apache 2.0
1311±23
695$0.20 / $0.6065.5K
177
164193
DeepSeek · DeepSeek
1311±11
2,721$1.14 / $4.56N/A
178
166194
1309±10
2,814$0.07 / $0.301M
179
160209
Google · Gemma
1307±27
389$0.04 / $0.13131.1K
180
168193
Anthropic
Anthropic · Proprietary
1306±6
10,020$3 / $15200K
181
162206
Stepfun
StepFun · Proprietary
1304±20
642N/AN/A
182
168197
Anthropic
Anthropic · Proprietary
1303±7
11,359$3 / $15200K
183
168199
NexusFlow · NexusFlow
1300±9
3,412N/AN/A
184
168201
1300±11
2,839$0.63 / $1.80131.1K
185
168201
01.AI
01 AI · Proprietary
1300±10
3,921N/AN/A
186
169201
Cohere
Cohere · CC-BY-NC-4.0
1299±9
3,995$2.50 / $10256K
187
168206
Alibaba · Proprietary
1297±14
1,404N/AN/A
188
163220
Ai2 · Apache 2.0
1297±26
473$0.15 / $0.5065.5K
189
162227
Tencent
Tencent · Proprietary
1294±31
238N/AN/A
190
171220
DeepSeek · DeepSeek
1288±17
1,031N/AN/A
191
171223
Z.ai · Proprietary
1287±19
721N/AN/A
192
174219
1286±13
1,943$0.40 / $0.708.2K
193
178212
OpenAI · Proprietary
1285±8
6,826$2.50 / $10128K
194
178211
OpenAI · Proprietary
1284±7
15,103$5 / $15128K
195
179214
xAI · Proprietary
1283±7
8,950$2 / $10131.1K
196
179217
Alibaba · Qwen
1282±8
5,415$1.20 / $1.20N/A
197
183219
Meta
Meta · Llama 3.1 Community
1281±7
8,482$4 / $432.8K
198
171229
Tencent
Tencent · Proprietary
1281±24
497N/AN/A
199
184220
Meta
Meta · Llama 3.1 Community
1278±8
5,215$4 / $432.8K
200
184226
Alibaba · Qwen
1275±12
2,249$1.60 / $6.4032.8K
201
184226
Z.ai · Proprietary
1275±10
3,599$0.44 / $1.76204.8K
202
175234
OpenAI · Proprietary
1274±23
582$0.10 / $0.401M
203
175234
Tencent
Tencent · Proprietary
1274±24
499N/AN/A
204
171235
Tencent
Tencent · Proprietary
1273±31
243N/AN/A
205
188225
Anthropic
Anthropic · Proprietary
1272±6
25,769$15 / $75200K
206
187227
Google · Proprietary
1271±9
6,395N/AN/A
207
188226
OpenAI · Proprietary
1271±7
13,217$10 / $30128K
208
184231
1271±17
1,041$1.20 / $1.20131.1K
209
187228
DeepSeek · DeepSeek
1271±10
3,649N/AN/A
210
190227
Google · Proprietary
1269±8
10,492$3.50 / $10.502.1M
211
190227
OpenAI · Proprietary
1269±8
13,306$10 / $30128K
212
189228
Google · Proprietary
1269±9
4,789$0.07 / $0.301M
213
175238
Tencent
Tencent · Proprietary
1268±30
351N/AN/A
214
191228
OpenAI · Proprietary
1268±8
12,374$10 / $30128K
215
192228
OpenAI · Proprietary
1267±7
9,322$0.15 / $0.60128K
216
191228
Meta
Meta · Llama-3.3
1267±8
5,778$0.10 / $0.32131.1K
217
194229
xAI · Proprietary
1265±8
7,261$2 / $10131.1K
218
197231
Mistral · Mistral Research
1261±8
6,664$2 / $6131.1K
219
191234
1261±13
2,131$0.10 / $0.3032K
220
197233
Mistral · MRL
1261±9
3,574$2 / $6131.1K
221
186248
IBM · Apache 2.0
1252±32
358N/AN/A
222
211234
Meta
Meta · Llama 3.1 Community
1252±7
7,677$0.40 / $0.40131.1K
223
206236
Amazon · Proprietary
1251±10
2,978$0.80 / $3.20300K
224
199242
Google · Gemma
1251±15
1,573$0.06 / $0.1232.8K
225
197244
Alibaba · Apache 2.0
1250±19
725$0.87 / $0.8732K
226
191247
Mistral · Proprietary
1249±26
553$2 / $540K
227
213243
Microsoft · MIT
1246±10
2,764$0.07 / $0.1416.4K
228
216239
Anthropic
Anthropic · Proprietary
1244±7
6,366$0.80 / $4200K
229
198250
Ai2 · Llama 3.1
1242±24
397N/AN/A
230
213245
DeepSeek · DeepSeek License
1241±13
1,858$0.14 / $0.28128K
231
215245
Mistral · Apache 2.0
1240±13
1,683$0.05 / $0.0832.8K
232
198252
Google · Gemma
1239±28
423$0.04 / $0.08131.1K
233
220245
Alibaba · Qianwen LICENSE
1235±9
4,835$0.90 / $0.9032.8K
234
202256
Tencent
Tencent · Proprietary
1235±28
361N/AN/A
235
221248
NexusFlow · CC-BY-NC-4.0
1231±10
2,921N/AN/A
236
222248
OpenAI · Proprietary
1230±10
7,052$30 / $608.2K
237
215256
1230±22
507N/AN/A
238
224248
Google · Proprietary
1229±8
8,392$0.07 / $0.301M
239
223251
Amazon · Proprietary
1226±11
2,511$0.06 / $0.24300K
240
224256
Reka AI · Proprietary
1222±14
1,207N/AN/A
241
224256
AI21 Labs · Jamba Open
1221±15
1,147$2 / $8256K
242
226256
Z.ai · Proprietary
1218±15
1,191N/AN/A
243
230252
Meta
Meta · Llama 3 Community
1218±7
20,941$0.51 / $0.748.2K
244
230255
OpenAI · Proprietary
1217±8
11,181$30 / $608.2K
245
227256
Nvidia · NVIDIA Open Model
1216±12
2,352N/AN/A
246
222264
Alibaba · Apache 2.0
1213±24
480$0.50 / $116.4K
247
231256
Anthropic
Anthropic · Proprietary
1213±8
13,766$3 / $15200K
248
235256
Google · Gemma license
1212±7
10,170$0.65 / $0.658.2K
249
225271
Ai2 · Apache-2.0
1207±28
375$0.05 / $0.20128K
250
237257
Google · Proprietary
1207±8
5,036$0.07 / $0.301M
251
236259
Amazon · Proprietary
1206±11
2,455$0.04 / $0.14128K
252
239262
Mistral · Proprietary
1200±9
7,987$4 / $1232K
253
239264
Cohere
Cohere · CC-BY-NC-4.0
1200±10
3,854N/AN/A
254
239270
Reka AI · Proprietary
1195±14
1,284N/AN/A
255
235275
Ai2 · Llama 3.1
1195±25
363N/AN/A
256
240275
Mistral · MRL
1188±20
683$0.10 / $0.10131.1K
257
249270
Anthropic
Anthropic · Proprietary
1188±7
14,983$0.25 / $1.25200K
258
248272
Cohere
Cohere · CC-BY-NC-4.0
1188±14
1,467$2.50 / $10128K
259
249272
Alibaba · Qianwen LICENSE
1185±11
3,188N/AN/A
260
250272
Mistral · Apache 2.0
1184±9
6,778$0.90 / $0.9065.5K
261
251272
Google · Gemma license
1183±8
7,110$0.03 / $0.098.2K
262
250274
01.AI
01 AI · Apache-2.0
1182±11
2,985N/AN/A
263
251275
Mistral · Proprietary
1180±11
4,406$2.70 / $8.1032K
264
250279
InternLM · Other
1180±15
1,387$0 / $032.8K
265
253274
Meta
Meta · Llama 3.1 Community
1179±8
7,135$0.02 / $0.05131.1K
266
253280
Microsoft · MIT
1173±10
3,238$0.17 / $0.68N/A
267
253282
Princeton · MIT
1173±15
1,285$0.03 / $0.098.2K
268
253285
Cohere
Cohere · CC-BY-NC-4.0
1168±15
1,307N/AN/A
269
253285
Reka AI · Proprietary
1168±14
2,028N/AN/A
270
260284
Cohere
Cohere · CC-BY-NC-4.0
1164±8
9,769$2.50 / $10128K
271
260285
Alibaba · Qianwen LICENSE
1164±10
5,327N/AN/A
272
256288
AI21 Labs · Jamba Open
1160±16
1,094$0.20 / $0.40256K
273
253295
IBM · Apache 2.0
1159±26
391N/AN/A
274
265288
Reka AI · Proprietary
1155±11
3,363N/AN/A
275
265288
Alibaba · Qianwen LICENSE
1155±12
2,649N/AN/A
276
265290
Cohere
Cohere · CC-BY-NC-4.0
1155±14
1,601$0.15 / $0.60128K
277
265291
1152±14
1,568$0.13 / $0.524.1K
278
255300
IBM · Apache 2.0
1151±28
382N/AN/A
279
267288
Meta
Meta · Llama 3 Community
1151±8
14,252$0.04 / $0.048.2K
280
266292
Microsoft · MIT
1151±13
2,092$0.15 / $0.60N/A
281
262299
HuggingFace · Apache 2.0
1148±22
589N/AN/A
282
269291
Mistral · Apache 2.0
1147±8
9,663$0.63 / $0.6332K
283
268295
Databricks · DBRX LICENSE
1145±11
4,001$0.60 / $0.6032.8K
284
267299
IBM · Apache 2.0
1143±19
873N/AN/A
285
272295
OpenAI · Proprietary
1142±8
8,626$0.50 / $1.5016.4K
286
268298
OpenAI · Proprietary
1141±15
2,134$1 / $216.4K
287
276298
Google · Gemma license
1134±8
6,599N/AN/A
288
272302
Google · Proprietary
1132±14
2,274$0.35 / $1.0532.8K
289
272304
Google · Proprietary
1129±19
993$0.35 / $1.0532.8K
290
276304
Meta
Meta · Llama 3.2
1126±16
1,136$0.05 / $0.34131.1K
291
277304
Alibaba · Qianwen LICENSE
1125±13
2,184$0.30 / $0.30N/A
292
279304
Nexusflow · Apache-2.0
1124±14
1,973N/AN/A
293
283304
Cohere
Cohere · CC-BY-NC-4.0
1120±9
6,682$0.15 / $0.60128K
294
280310
IBM · Apache 2.0
1117±19
908N/AN/A
295
280312
Microsoft · Llama 2 Community
1116±19
903N/AN/A
296
283308
01.AI
01 AI · Yi License
1113±13
2,043$0.90 / $0.904.1K
297
287309
Microsoft · MIT
1111±12
2,564$0.13 / $0.52N/A
298
288310
Snowflake · Apache 2.0
1109±11
4,793N/AN/A
299
283315
DeepSeek · DeepSeek License
1107±23
576N/AN/A
300
285314
AllenAI/UW · AI2 ImpACT Low-risk
1107±19
888N/AN/A
301
289312
Google · Gemma license
1107±11
3,039$0.03 / $0.098.2K
302
288312
OpenChat · Apache-2.0
1107±14
1,726N/AN/A
303
280321
HuggingFace · Apache 2.0
1105±33
271N/AN/A
304
289320
NousResearch · Apache-2.0
1097±20
697$0.17 / $0.17N/A
305
294318
Meta
Meta · Llama 2 Community
1091±10
4,740$0.70 / $2.804.1K
306
294320
Microsoft · MIT
1089±13
2,813$0.13 / $0.52N/A
307
294321
Meta
Meta · Llama 3.2
1086±16
1,162$0.03 / $0.20131.1K
308
298321
Mistral · Apache-2.0
1085±12
2,605$0.20 / $0.2032.8K
309
298322
UC Berkeley · CC-BY-NC-4.0
1081±16
1,300N/AN/A
310
295324
Alibaba · Qianwen LICENSE
1080±20
690$0.20 / $0.20N/A
311
294328
Cognitive Computations · Apache-2.0
1076±32
219$0.50 / $0.5016.4K
312
296328
Nvidia · Llama 2 Community
1072±27
440N/AN/A
313
301327
OpenChat · Apache-2.0
1071±18
945$0.20 / $0.20N/A
314
303324
LMSYS · Non-commercial
1070±12
2,663$0 / $02K
315
301328
Alibaba · Qianwen LICENSE
1068±24
534N/AN/A
316
303327
Google · Gemma license
1066±16
1,120$0.05 / $0.088.2K
317
304327
Meta
Meta · Llama 2 Community
1065±13
2,218$0.25 / $0.254.1K
318
302330
Upstage AI · CC-BY-NC-4.0
1064±22
604$0.30 / $0.30N/A
319
303330
NousResearch · Apache-2.0
1060±21
628$0.90 / $0.90N/A
320
306331
Meta
Meta · Llama 2 Community
1056±19
770$0.35 / $1.4016.4K
321
309333
Google · Proprietary
1049±19
901$0.50 / $0.5025.8K
322
310332
Google · Gemma license
1047±16
1,355N/AN/A
323
304334
MosaicML · CC-BY-NC-SA-4.0
1046±34
242N/AN/A
324
312333
Meta
Meta · Llama 2 Community
1042±14
1,656$0.15 / $0.154.1K
325
312333
HuggingFace · MIT
1041±17
1,250$0.15 / $0.1516.4K
326
312334
Together AI · Apache 2.0
1033±20
676$0.20 / $0.20N/A
327
310335
UW · Non-commercial
1032±33
280N/AN/A
328
318333
LMSYS · Llama 2 Community
1030±14
2,146$0.30 / $0.30N/A
329
315335
Mistral · Apache 2.0
1027±19
974$0.07 / $0.284.1K
330
318335
Alibaba · Qianwen LICENSE
1026±18
988$0.10 / $0.10N/A
331
321335
Ai2 · Apache-2.0
1018±19
848$0.20 / $0.20N/A
332
320335
Microsoft · Llama 2 Community
1017±21
669$0.30 / $0.30N/A
333
322335
Google · Gemma license
1009±22
597$0.10 / $0.10N/A
334
326336
LMSYS · Llama 2 Community
994±21
658$0.20 / $0.20N/A
335
328336
Tsinghua · Apache-2.0
989±23
576N/AN/A
336
334343
Nomic AI · Non-commercial
941±37
211N/AN/A
337
336343
UC Berkeley · Non-commercial
932±21
751N/AN/A
338
336343
Tsinghua · Non-commercial
926±25
525N/AN/A
339
336344
RWKV · Apache 2.0
922±24
544N/AN/A
340
336344
MosaicML · CC-BY-NC-SA-4.0
919±25
471N/AN/A
341
336345
Tsinghua · Apache-2.0
915±35
227N/AN/A
342
336345
Stanford · Non-commercial
908±23
652N/AN/A
343
336346
OpenAssistant · Apache 2.0
892±22
687N/AN/A
344
339347
Databricks · MIT
871±29
370N/AN/A
345
341347
LMSYS · Apache 2.0
862±26
462N/AN/A
346
344347
Stability
Stability AI · CC-BY-NC-SA-4.0
839±29
353N/AN/A
347
343347
Meta
Meta · Non-commercial
838±33
252$0.23 / $0.23N/A

Remove Style Control Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

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)