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.

Mar 31, 2026
551,141 votes
326 models
Rank Spread
1
16
Anthropic
Anthropic · Proprietary
1515±19
935$5 / $251M
2
17
Anthropic
Anthropic · Proprietary
1512±21
809$5 / $251M
3
113
OpenAI · Proprietary
1511±29
428$2.50 / $151.1M
4
17
Google · Proprietary
1508±18
1,085$2 / $121M
5
143
Alibaba · Proprietary
1478±32
348N/AN/A
6
426
Google · Proprietary
1476±12
2,681$2 / $121M
7
231
Moonshot · Modified MIT
1476±17
1,148$0.60 / $3N/A
8
430
Google · Proprietary
1473±13
2,025$0.50 / $31M
9
166
Google · Apache 2.0
1469±34
267N/AN/A
10
448
Anthropic
Anthropic · Proprietary
1466±21
755$3 / $151M
11
468
OpenAI · Proprietary
1461±29
410$2.50 / $151.1M
12
542
Anthropic
1460±13
2,288$5 / $25200K
13
543
Anthropic
Anthropic · Proprietary
1458±12
2,752$5 / $25200K
14
552
1456±14
1,866$0.50 / $31M
15
566
Alibaba · Apache 2.0
1454±19
877$0.39 / $2.34262.1K
16
577
1453±27
455$2 / $62M
17
650
Google · Proprietary
1452±8
6,502$1.25 / $101M
18
569
Z.ai · MIT
1452±21
755$1 / $3.20202.8K
19
486
Google · Apache 2.0
1451±32
307N/AN/A
20
566
Alibaba · Proprietary
1450±15
1,534$0.78 / $3.90262.1K
21
580
1449±26
488$2 / $62M
22
577
OpenAI · Proprietary
1446±21
780$1.75 / $14128K
23
861
Anthropic
1446±10
3,501$3 / $15200K
24
669
Baidu · Proprietary
1446±16
1,253N/AN/A
25
769
OpenAI · Proprietary
1445±14
1,754$1.75 / $14400K
26
4105
1443±40
206N/AN/A
27
869
OpenAI · Proprietary
1443±12
2,510$1.25 / $10400K
28
589
xAI · Proprietary
1442±25
500N/AN/A
29
589
Moonshot · Modified MIT
1442±25
522$0.38 / $1.91262.1K
30
687
Meituan · MIT
1440±22
692$0.20 / $0.80131.1K
31
879
Alibaba · Apache 2.0
1440±17
1,227$0.09 / $1.10262.1K
32
594
Xiaomi · Proprietary
1439±27
462$1 / $31M
33
689
Alibaba · Proprietary
1439±24
588$0.78 / $3.90262.1K
34
982
DeepSeek · MIT
1435±12
2,483$0.26 / $0.38163.8K
35
890
Google · Proprietary
1434±19
861$0.25 / $1.501M
36
898
Alibaba · Apache 2.0
1433±23
607$0.20 / $1.56262.1K
37
1186
Z.ai · MIT
1432±13
2,139$0.39 / $1.90204.8K
38
5110
Meituan · Proprietary
1432±34
266N/AN/A
39
1481
Alibaba · Apache 2.0
1432±9
4,898$0.26 / $1.06N/A
40
1189
1431±15
1,596N/AN/A
41
1483
Anthropic
1431±11
3,050$15 / $75200K
42
8102
Alibaba · Apache 2.0
1430±23
627$0.26 / $2.08262.1K
43
1397
Z.ai · MIT
1427±16
1,432$0.60 / $2.20131.1K
44
1490
Moonshot · Modified MIT
1426±12
2,653$1.15 / $8262.1K
45
1497
OpenAI · Proprietary
1426±15
1,495$1.75 / $14400K
46
11103
1425±20
810N/AN/A
47
8105
Alibaba · Apache 2.0
1425±23
707$0.20 / $0.88262.1K
48
8110
1425±27
487$0.27 / $0.41163.8K
49
1892
OpenAI · Proprietary
1424±10
3,748$2 / $8200K
50
11104
Z.ai · MIT
1424±21
711$0.39 / $1.75202.8K
51
1597
xAI · Proprietary
1424±12
2,657N/AN/A
52
1597
xAI · Proprietary
1424±12
2,292$3 / $15256K
53
2397
Anthropic
Anthropic · Proprietary
1421±9
4,761$15 / $75200K
54
8122
1421±37
234N/AN/A
55
14106
DeepSeek · MIT
1420±18
998$1.23 / $4.94N/A
56
14109
DeepSeek · MIT
1420±21
781$0.27 / $0.41163.8K
57
11118
xAI · Proprietary
1417±29
400$3 / $15256K
58
12118
Alibaba · Apache 2.0
1416±28
434$0.26 / $2.60131.1K
59
23106
1415±13
1,958$0.30 / $2.501M
60
23106
DeepSeek · MIT
1415±13
2,005$0.26 / $0.38163.8K
61
14117
DeepSeek · MIT
1414±22
669$1.23 / $4.94N/A
62
25104
xAI · Proprietary
1414±11
3,212N/AN/A
63
15117
Alibaba · Proprietary
1413±23
659N/AN/A
64
14117
Alibaba · Apache 2.0
1413±25
492$0.15 / $1.50131.1K
65
27105
Anthropic
Anthropic · Proprietary
1413±10
3,503$3 / $15200K
66
29103
Google · Proprietary
1413±7
6,739$0.30 / $2.501M
67
25109
Mistral · Apache 2.0
1412±13
2,276$0.50 / $1.50N/A
68
19117
MiniMax · Modified MIT
1412±19
908$0.12 / $1196.6K
69
23113
OpenAI · Proprietary
1412±15
1,393$75 / $150128K
70
8136
Tencent
Tencent · Proprietary
1412±39
235N/AN/A
71
26113
OpenAI · Proprietary
1410±14
1,810$1.25 / $10128K
72
33108
Mistral · Proprietary
1410±9
4,699$2.70 / $8.1032K
73
13136
Baidu · Proprietary
1409±34
270N/AN/A
74
8139
1409±42
200$0.21 / $0.79163.8K
75
30111
OpenAI · Proprietary
1408±11
2,891$1.25 / $10400K
76
32115
xAI · Proprietary
1407±12
2,497$0.20 / $0.502M
77
23120
OpenAI · Proprietary
1406±22
729$1.75 / $14128K
78
23120
Alibaba · Apache 2.0
1406±22
643$0.16 / $1.30262.1K
79
40110
OpenAI · Proprietary
1406±8
5,778$5 / $15128K
80
23125
Baidu · Proprietary
1405±23
627N/AN/A
81
12141
OpenAI · Proprietary
1404±41
208$0.20 / $1.25400K
82
28123
DeepSeek · MIT
1403±20
876$0.45 / $2.15163.8K
83
15137
MiniMax · Proprietary
1403±33
310$0.30 / $1.20204.8K
84
30120
xAI · Proprietary
1402±18
1,096$0.20 / $0.502M
85
15139
1402±34
265N/AN/A
86
30129
Microsoft AI · Proprietary
1400±19
895N/AN/A
87
41120
OpenAI · Proprietary
1399±14
1,905$1.25 / $10400K
88
23139
Alibaba · Apache 2.0
1398±30
316$0.08 / $0.2441K
89
41124
Z.ai · MIT
1397±15
1,553$0.13 / $0.85131.1K
90
47120
Alibaba · Apache 2.0
1397±12
2,413$0.46 / $1.82131.1K
91
14142
DeepSeek · MIT
1397±39
218$0.21 / $0.79163.8K
92
33134
Moonshot · Modified MIT
1397±21
767$0.60 / $2.50262.1K
93
47127
Alibaba · Apache 2.0
1396±14
1,617$0.46 / $1.82131.1K
94
47125
OpenAI · Proprietary
1395±13
1,909$1.10 / $4.40200K
95
37135
Alibaba · Apache 2.0
1395±20
839$0.10 / $0.78131.1K
96
40134
MiniMax · MIT
1395±18
1,018$0.27 / $0.95196.6K
97
41134
Stepfun
StepFun · Apache 2.0
1395±18
1,029$0.10 / $0.30262.1K
98
47129
Alibaba · Apache 2.0
1394±15
1,438$0.09 / $0.30262.1K
99
18143
1394±39
195$0.10 / $0.40131.1K
100
48130
DeepSeek · MIT
1392±14
1,606$0.70 / $2.5064K
101
59129
xAI · Proprietary
1390±11
2,691$3 / $15131.1K
102
50136
1389±14
1,690$0.09 / $0.29262.1K
103
58133
Anthropic
Anthropic · Proprietary
1389±12
2,269$15 / $75200K
104
61132
OpenAI · Proprietary
1388±11
2,986$15 / $60200K
105
58136
OpenAI · Apache 2.0
1388±14
1,810$0.04 / $0.19131.1K
106
65135
OpenAI · Proprietary
1386±11
2,963$1.10 / $4.40200K
107
67136
Anthropic
Anthropic · Proprietary
1385±10
3,483$1 / $5200K
108
52139
xAI · Proprietary
1385±18
990$0.30 / $0.50131.1K
109
39144
Prime Intellect · MIT
1383±31
332$0.20 / $1.10131.1K
110
55142
1380±22
644$0.09 / $0.29262.1K
111
39148
OpenAI · Proprietary
1379±35
256$0.75 / $4.50400K
112
68141
OpenAI · Proprietary
1378±15
1,475$0.25 / $2400K
113
68143
Nvidia · NVIDIA Open Model
1374±19
1,001$0.06 / $0.24262.1K
114
74141
Anthropic
1374±13
2,050$3 / $151M
115
79141
DeepSeek · MIT
1374±10
3,212$3 / $4.5032.8K
116
84141
OpenAI · Proprietary
1374±8
4,738$1.10 / $4.40200K
117
82141
OpenAI · Proprietary
1373±10
4,569$15 / $60N/A
118
80141
Anthropic
Anthropic · Proprietary
1372±11
2,791$15 / $75200K
119
81141
1372±11
2,923$0.10 / $0.401M
120
46152
Nvidia · NVIDIA Open Model
1372±38
224N/AN/A
121
79143
xAI · Proprietary
1370±14
1,556$0.30 / $0.50131.1K
122
67148
Ant Group · MIT
1369±27
464N/AN/A
123
88142
Alibaba · Proprietary
1369±10
3,316N/AN/A
124
89142
OpenAI · Proprietary
1368±10
3,269$2 / $81M
125
84144
Alibaba · Apache 2.0
1368±15
1,648$0.40 / $1.60262.1K
126
85144
Moonshot · Modified MIT
1367±14
1,727$0.60 / $2.50131.1K
127
65152
Stepfun
StepFun · Apache 2.0
1365±31
354$0.57 / $1.4265.5K
128
96144
1363±12
2,122$0.10 / $0.401M
129
94145
MiniMax · Apache 2.0
1363±13
1,811$0.40 / $2.201M
130
85151
Z.ai · MIT
1360±22
722$0.06 / $0.40202.8K
131
100147
Alibaba · Apache 2.0
1359±14
1,725$0.15 / $0.58131.1K
132
64157
Nvidia · Nvidia Open Model
1359±38
209$0.60 / $1.80131.1K
133
89151
Amazon · Proprietary
1358±20
837$0.30 / $2.501M
134
106144
OpenAI · Proprietary
1358±8
7,499$1.10 / $4.40N/A
135
91151
Tencent
Tencent · Proprietary
1358±19
853N/AN/A
136
102147
Anthropic
Anthropic · Proprietary
1357±12
2,502$3 / $151M
137
72156
MiniMax · Apache 2.0
1355±33
322$0.26 / $1196.6K
138
102149
Alibaba · Apache 2.0
1355±13
1,730$0.08 / $0.2841K
139
106148
Mistral · Proprietary
1353±12
2,255$0.40 / $2131.1K
140
114148
Google · Proprietary
1352±9
4,085$0.10 / $0.401M
141
74161
Z.ai · MIT
1352±34
278$0.60 / $1.8065.5K
142
90156
Ant Group · MIT
1350±27
456N/AN/A
143
121153
OpenAI · Proprietary
1343±11
2,711$0.40 / $1.601M
144
118156
Mistral · Apache 2.0
1340±17
1,056$0.10 / $0.3032K
145
127154
Anthropic
1337±11
2,805$3 / $15200K
146
126169
Arcee AI · Apache 2.0
1327±22
712N/AN/A
147
129169
Alibaba · Proprietary
1326±19
732$0.40 / $1.20131.1K
148
134176
OpenAI · Apache 2.0
1319±22
686$0.03 / $0.11131.1K
149
140168
Anthropic
Anthropic · Proprietary
1318±10
3,380$3 / $15200K
150
133176
Stepfun
StepFun · Proprietary
1318±24
571N/AN/A
151
127186
Ai2 · Apache 2.0
1314±32
321$0.15 / $0.5065.5K
152
134181
OpenAI · Proprietary
1314±27
497$0.05 / $0.40400K
153
144168
Google · Proprietary
1314±7
7,610$3.50 / $10.502.1M
154
145172
Google · Gemma
1312±9
3,611$0.08 / $0.16131.1K
155
139181
Ai2 · Apache 2.0
1311±23
701$0.20 / $0.6065.5K
156
145173
DeepSeek · DeepSeek
1310±11
2,721$1.14 / $4.56N/A
157
145173
1309±10
2,814$0.07 / $0.301M
158
137188
Google · Gemma
1307±27
389$0.04 / $0.13131.1K
159
146173
Anthropic
Anthropic · Proprietary
1306±6
10,044$6 / $30200K
160
141185
Stepfun
StepFun · Proprietary
1304±20
642N/AN/A
161
146176
Anthropic
Anthropic · Proprietary
1303±7
11,359$6 / $30200K
162
146180
1300±11
2,859$0.63 / $1.80131.1K
163
146178
NexusFlow · NexusFlow
1300±9
3,412N/AN/A
164
146179
Cohere
Cohere · CC-BY-NC-4.0
1299±9
4,036$2.50 / $10256K
165
146180
01.AI
01 AI · Proprietary
1299±10
3,921N/AN/A
166
146186
Alibaba · Proprietary
1297±14
1,404N/AN/A
167
145202
Ai2 · Apache 2.0
1295±27
475$0.15 / $0.5065.5K
168
141206
Tencent
Tencent · Proprietary
1294±32
238N/AN/A
169
150199
DeepSeek · DeepSeek
1288±17
1,031N/AN/A
170
151196
1287±13
1,965$0.40 / $0.708.2K
171
148202
Zhipu · Proprietary
1287±19
721N/AN/A
172
157192
OpenAI · Proprietary
1285±8
6,826$2.50 / $10128K
173
157192
OpenAI · Proprietary
1284±7
15,103$5 / $15128K
174
159194
xAI · Proprietary
1283±7
8,950$2 / $10131.1K
175
158197
Alibaba · Qwen
1282±8
5,415$1.20 / $1.20N/A
176
161198
Meta
Meta · Llama 3.1 Community
1281±7
8,482$4 / $432.8K
177
150208
Tencent
Tencent · Proprietary
1280±24
497N/AN/A
178
163199
Meta
Meta · Llama 3.1 Community
1278±8
5,215$4 / $432.8K
179
163206
Alibaba · Qwen
1275±12
2,249$1.60 / $6.4032.8K
180
163205
Zhipu AI · Proprietary
1275±10
3,599$0.44 / $1.76204.8K
181
154213
OpenAI · Proprietary
1274±23
582$0.10 / $0.401M
182
154213
Tencent
Tencent · Proprietary
1274±24
499N/AN/A
183
150215
Tencent
Tencent · Proprietary
1273±31
243N/AN/A
184
167204
Anthropic
Anthropic · Proprietary
1272±6
25,769$15 / $75200K
185
166206
Google · Proprietary
1271±9
6,395N/AN/A
186
167205
OpenAI · Proprietary
1271±8
13,217$10 / $30128K
187
163210
1271±17
1,041$1.20 / $1.20131.1K
188
166207
DeepSeek · DeepSeek
1270±10
3,649N/AN/A
189
168206
Google · Proprietary
1269±8
10,492$3.50 / $10.502.1M
190
169207
OpenAI · Proprietary
1269±8
13,306$10 / $30128K
191
167207
Google · Proprietary
1269±9
4,789$0.07 / $0.301M
192
170207
OpenAI · Proprietary
1267±8
12,374$10 / $30128K
193
172207
OpenAI · Proprietary
1267±7
9,325$0.15 / $0.60128K
194
171207
Meta
Meta · Llama-3.3
1267±8
5,790$0.10 / $0.32131.1K
195
154220
Tencent
Tencent · Proprietary
1266±30
353N/AN/A
196
173208
xAI · Proprietary
1265±8
7,261$2 / $10131.1K
197
170213
1262±13
2,153$0.10 / $0.3032K
198
175211
Mistral · Mistral Research
1261±8
6,664$2 / $6131.1K
199
175212
Mistral · MRL
1261±9
3,574$2 / $6131.1K
200
164227
IBM · Apache 2.0
1252±32
364N/AN/A
201
167224
Mistral · Proprietary
1251±26
557$2 / $540K
202
190214
Meta
Meta · Llama 3.1 Community
1251±8
7,677$0.40 / $0.40131.1K
203
184215
Amazon · Proprietary
1251±10
2,978$0.80 / $3.20300K
204
178222
Google · Gemma
1250±15
1,585$0.02 / $0.0432.8K
205
175223
Alibaba · Apache 2.0
1250±19
725$0.87 / $0.8732K
206
192222
Microsoft · MIT
1245±10
2,764$0.07 / $0.1416.4K
207
195218
Anthropic
Anthropic · Proprietary
1244±7
6,389$0.80 / $4200K
208
177229
Ai2 · Llama 3.1
1242±25
397N/AN/A
209
192224
DeepSeek · DeepSeek License
1241±14
1,858$0.14 / $0.28128K
210
193224
Mistral · Apache 2.0
1240±13
1,683$0.05 / $0.0832.8K
211
177231
Google · Gemma
1239±28
423$0.04 / $0.08131.1K
212
198224
Alibaba · Qianwen LICENSE
1234±9
4,835$0.90 / $0.9032.8K
213
180235
Tencent
Tencent · Proprietary
1234±29
361N/AN/A
214
199227
NexusFlow · CC-BY-NC-4.0
1231±10
2,921N/AN/A
215
201228
OpenAI · Proprietary
1230±10
7,052$30 / $608.2K
216
194235
1230±23
507N/AN/A
217
202227
Google · Proprietary
1228±8
8,392$0.07 / $0.301M
218
201230
Amazon · Proprietary
1226±11
2,511$0.06 / $0.24300K
219
203235
Reka AI · Proprietary
1221±14
1,207N/AN/A
220
202235
AI21 Labs · Jamba Open
1221±15
1,147$2 / $8256K
221
205235
Zhipu AI · Proprietary
1218±16
1,191N/AN/A
222
210231
Meta
Meta · Llama 3 Community
1218±7
20,941$0.51 / $0.748.2K
223
210234
OpenAI · Proprietary
1217±8
11,181$30 / $608.2K
224
206235
Nvidia · NVIDIA Open Model
1216±12
2,352N/AN/A
225
201243
Alibaba · Apache 2.0
1213±25
480$0.15 / $0.58131.1K
226
210235
Anthropic
Anthropic · Proprietary
1213±8
13,766$3 / $15200K
227
214235
Google · Gemma license
1212±7
10,170$0.65 / $0.658.2K
228
203250
Ai2 · Apache-2.0
1207±29
375$0.05 / $0.20128K
229
216236
Google · Proprietary
1206±8
5,036$0.07 / $0.301M
230
215238
Amazon · Proprietary
1206±11
2,455$0.04 / $0.14128K
231
218241
Mistral · Proprietary
1199±9
7,987$4 / $1232K
232
218243
Cohere
Cohere · CC-BY-NC-4.0
1199±10
3,854N/AN/A
233
218249
Reka AI · Proprietary
1195±14
1,284N/AN/A
234
213254
Ai2 · Llama 3.1
1194±26
363N/AN/A
235
219254
Mistral · MRL
1188±20
683$0.10 / $0.10131.1K
236
228249
Anthropic
Anthropic · Proprietary
1188±7
14,983$0.25 / $1.25200K
237
227251
Cohere
Cohere · CC-BY-NC-4.0
1187±14
1,467$2.50 / $10128K
238
228251
Alibaba · Qianwen LICENSE
1185±11
3,188N/AN/A
239
229251
Mistral · Apache 2.0
1184±9
6,778$0.90 / $0.9065.5K
240
230251
Google · Gemma license
1183±8
7,110$0.03 / $0.098.2K
241
229253
01.AI
01 AI · Apache-2.0
1182±11
2,985N/AN/A
242
230254
Mistral · Proprietary
1179±11
4,406$2.70 / $8.1032K
243
229258
InternLM · Other
1179±15
1,387$0 / $032.8K
244
232253
Meta
Meta · Llama 3.1 Community
1179±8
7,135$0.02 / $0.0516.4K
245
232259
Microsoft · MIT
1173±11
3,238$0.17 / $0.68N/A
246
232261
Princeton · MIT
1172±15
1,285$0.03 / $0.098.2K
247
232264
Cohere
Cohere · CC-BY-NC-4.0
1168±15
1,307N/AN/A
248
232264
Reka AI · Proprietary
1168±14
2,028N/AN/A
249
239263
Cohere
Cohere · CC-BY-NC-4.0
1164±8
9,769$2.50 / $10128K
250
239264
Alibaba · Qianwen LICENSE
1163±10
5,327N/AN/A
251
235267
AI21 Labs · Jamba Open
1160±16
1,094$0.20 / $0.40256K
252
232274
IBM · Apache 2.0
1159±26
391N/AN/A
253
244267
Reka AI · Proprietary
1155±11
3,363N/AN/A
254
244267
Alibaba · Qianwen LICENSE
1155±12
2,649N/AN/A
255
244269
Cohere
Cohere · CC-BY-NC-4.0
1154±14
1,601$0.15 / $0.60128K
256
244270
1152±14
1,568$0.13 / $0.524.1K
257
234279
IBM · Apache 2.0
1151±28
382N/AN/A
258
246267
Meta
Meta · Llama 3 Community
1151±8
14,252$0.03 / $0.048.2K
259
245272
Microsoft · MIT
1150±13
2,092$0.15 / $0.60N/A
260
241278
HuggingFace · Apache 2.0
1147±22
589N/AN/A
261
248270
Mistral · Apache 2.0
1147±9
9,663$0.63 / $0.6332K
262
247274
Databricks · DBRX LICENSE
1145±12
4,001$0.60 / $0.6032.8K
263
246278
IBM · Apache 2.0
1143±19
873N/AN/A
264
251274
OpenAI · Proprietary
1141±8
8,626$0.50 / $1.5016.4K
265
247278
OpenAI · Proprietary
1141±15
2,134$1 / $216.4K
266
255277
Google · Gemma license
1134±8
6,599N/AN/A
267
251282
Google · Proprietary
1132±14
2,274$0.35 / $1.0532.8K
268
251283
Google · Proprietary
1129±19
993$0.35 / $1.0532.8K
269
255283
Meta
Meta · Llama 3.2
1126±16
1,136$0.05 / $0.3480K
270
256283
Alibaba · Qianwen LICENSE
1125±14
2,184$0.30 / $0.30N/A
271
258283
Nexusflow · Apache-2.0
1124±14
1,973N/AN/A
272
262283
Cohere
Cohere · CC-BY-NC-4.0
1120±9
6,682$0.15 / $0.60128K
273
259289
IBM · Apache 2.0
1117±19
908N/AN/A
274
259291
Microsoft · Llama 2 Community
1116±19
903N/AN/A
275
262287
01.AI
01 AI · Yi License
1113±13
2,043$0.90 / $0.904.1K
276
266288
Microsoft · MIT
1111±12
2,564$0.13 / $0.52N/A
277
267290
Snowflake · Apache 2.0
1108±11
4,793N/AN/A
278
262294
DeepSeek · DeepSeek License
1107±24
576N/AN/A
279
263293
AllenAI/UW · AI2 ImpACT Low-risk
1107±19
888N/AN/A
280
267291
Google · Gemma license
1106±11
3,039$0.03 / $0.098.2K
281
267291
OpenChat · Apache-2.0
1106±14
1,726N/AN/A
282
258300
HuggingFace · Apache 2.0
1104±33
271N/AN/A
283
268299
NousResearch · Apache-2.0
1097±20
697$0.17 / $0.17N/A
284
273298
Meta
Meta · Llama 2 Community
1091±10
4,740$0.70 / $2.804.1K
285
273299
Microsoft · MIT
1089±13
2,813$0.13 / $0.52N/A
286
273300
Meta
Meta · Llama 3.2
1085±16
1,162$0.03 / $0.2060K
287
276300
Mistral · Apache-2.0
1085±12
2,605$0.20 / $0.2032.8K
288
277301
UC Berkeley · CC-BY-NC-4.0
1081±16
1,300N/AN/A
289
274303
Alibaba · Qianwen LICENSE
1079±21
690$0.20 / $0.20N/A
290
273309
Cognitive Computations · Apache-2.0
1076±33
219$0.50 / $0.5016.4K
291
275307
Nvidia · Llama 2 Community
1071±27
440N/AN/A
292
280306
OpenChat · Apache-2.0
1070±18
945$0.20 / $0.20N/A
293
282303
LMSYS · Non-commercial
1070±13
2,663$0 / $02K
294
280308
Alibaba · Qianwen LICENSE
1067±24
534N/AN/A
295
282306
Google · Gemma license
1066±17
1,120$0.05 / $0.088.2K
296
283306
Meta
Meta · Llama 2 Community
1065±13
2,218$0.25 / $0.254.1K
297
281309
Upstage AI · CC-BY-NC-4.0
1064±22
604$0.30 / $0.30N/A
298
282309
NousResearch · Apache-2.0
1060±22
628$0.90 / $0.90N/A
299
285310
Meta
Meta · Llama 2 Community
1056±19
770$0.35 / $1.4016.4K
300
288312
Google · Proprietary
1048±20
901$0.50 / $0.5025.8K
301
289311
Google · Gemma license
1047±16
1,355N/AN/A
302
282314
MosaicML · CC-BY-NC-SA-4.0
1046±35
242N/AN/A
303
291312
Meta
Meta · Llama 2 Community
1042±14
1,656$0.15 / $0.154.1K
304
291312
HuggingFace · MIT
1041±17
1,250$0.15 / $0.1516.4K
305
291313
Together AI · Apache 2.0
1033±20
676$0.20 / $0.20N/A
306
289314
UW · Non-commercial
1032±33
280N/AN/A
307
295312
LMSYS · Llama 2 Community
1030±14
2,146$0.30 / $0.30N/A
308
294314
Mistral · Apache 2.0
1027±19
974$0.07 / $0.284.1K
309
296314
Alibaba · Qianwen LICENSE
1026±18
988$0.10 / $0.10N/A
310
300314
Ai2 · Apache-2.0
1017±19
848$0.20 / $0.20N/A
311
299314
Microsoft · Llama 2 Community
1017±21
669$0.30 / $0.30N/A
312
301314
Google · Gemma license
1008±22
597$0.10 / $0.10N/A
313
305315
LMSYS · Llama 2 Community
993±22
658$0.20 / $0.20N/A
314
306315
Tsinghua · Apache-2.0
989±24
576N/AN/A
315
313322
Nomic AI · Non-commercial
940±38
211N/AN/A
316
315322
UC Berkeley · Non-commercial
932±21
751N/AN/A
317
315323
Tsinghua · Non-commercial
925±26
525N/AN/A
318
315323
RWKV · Apache 2.0
922±25
544N/AN/A
319
315323
MosaicML · CC-BY-NC-SA-4.0
919±26
471N/AN/A
320
315324
Tsinghua · Apache-2.0
915±35
227N/AN/A
321
315324
Stanford · Non-commercial
908±23
652N/AN/A
322
315325
OpenAssistant · Apache 2.0
892±22
687N/AN/A
323
317326
Databricks · MIT
871±29
370N/AN/A
324
320326
LMSYS · Apache 2.0
861±26
462N/AN/A
325
323326
Stability
Stability AI · CC-BY-NC-SA-4.0
839±29
353N/AN/A
326
322326
Meta
Meta · Non-commercial
837±33
252$0.23 / $0.23N/A

Remove Style Control Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

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)