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.

Jun 16, 2026
395,187 votes
316 models
Rank Spread
1
18
Anthropic
Anthropic · Proprietary
1547±11
3,648$5 / $251M
2
110
Anthropic
Anthropic · Proprietary
1538±10
4,466$5 / $251M
3
129
Anthropic
Anthropic · Proprietary
1536±28
434$10 / $501M
4
116
Anthropic
Anthropic · Proprietary
1533±11
3,228$5 / $251M
5
124
Anthropic
Anthropic · Proprietary
1530±17
1,258$5 / $251M
6
119
Anthropic
Anthropic · Proprietary
1529±12
3,082$5 / $251M
7
224
OpenAI · Proprietary
1524±11
3,597$2.50 / $151.1M
8
224
OpenAI · Proprietary
1523±12
2,590$5 / $301.1M
9
132
Anthropic
Anthropic · Proprietary
1521±17
1,222$5 / $251M
10
329
Google · Proprietary
1515±9
5,352$2 / $121M
11
334
Xiaomi · MIT
1513±13
2,300$0.43 / $0.871M
12
349
Google · Proprietary
1509±19
1,040$1.50 / $91M
13
164
Alibaba · Proprietary
1508±33
342$1.25 / $3.751M
14
439
OpenAI · Proprietary
1507±12
2,771$5 / $301.1M
15
536
Anthropic
Anthropic · Proprietary
1506±11
3,658$3 / $151M
16
350
Z.ai · MIT
1505±16
1,438$1.40 / $4.40202.8K
17
444
Anthropic
1505±13
2,202$5 / $25200K
18
537
Anthropic
Anthropic · Proprietary
1504±9
5,091$5 / $25200K
19
546
Google · Proprietary
1503±12
2,532$2 / $121M
20
551
Moonshot · Modified MIT
1501±13
2,211$0.95 / $4262.1K
21
843
Anthropic
1501±9
5,464$3 / $15200K
22
555
Alibaba · Proprietary
1499±14
1,994N/AN/A
23
367
Alibaba · Proprietary
1499±26
520$1.04 / $6.24262.1K
24
851
OpenAI · Proprietary
1498±11
3,846$2.50 / $151.1M
25
855
Google · Proprietary
1497±13
1,932$0.50 / $31M
26
1056
OpenAI · Proprietary
1493±12
2,878$1.75 / $14128K
27
384
1493±34
270N/AN/A
28
1059
Xiaomi · Proprietary
1492±14
2,041$1 / $31M
29
485
Z.ai · MIT
1489±31
340$1.40 / $4.401M
30
1170
Meta
Meta · Proprietary
1487±17
1,271N/AN/A
31
1075
MiniMax · Proprietary
1486±19
1,073$0.60 / $2.40N/A
32
1460
Anthropic
Anthropic · Proprietary
1486±9
5,571$3 / $15200K
33
1168
Z.ai · MIT
1486±14
1,878$1 / $3.20202.8K
34
1465
1484±10
3,775$2 / $62M
35
1270
Baidu · Proprietary
1483±13
2,178N/AN/A
36
1368
Anthropic
1483±12
2,333$15 / $75200K
37
1568
Moonshot · Modified MIT
1482±10
3,856$0.60 / $3N/A
38
890
Google · Apache 2.0
1482±26
444$0.14 / $0.40262.1K
39
1568
OpenAI · Proprietary
1482±11
3,590$0.75 / $4.50400K
40
1668
Alibaba · Apache 2.0
1482±10
3,928$0.39 / $2.45256K
41
1572
OpenAI · Proprietary
1481±13
2,328$1.25 / $10400K
42
1970
Bytedance
Bytedance · Proprietary
1480±10
4,380N/AN/A
43
1775
DeepSeek · MIT
1479±12
2,615$0.43 / $0.871M
44
2075
OpenAI · Proprietary
1479±10
3,649$1.75 / $14400K
45
1776
OpenAI · Proprietary
1478±13
2,516$5 / $301.1M
46
1875
Xiaomi · MIT
1478±13
2,506$0.14 / $0.281M
47
1876
1477±13
2,341$0.43 / $0.871M
48
2275
1476±10
3,780$2 / $62M
49
2279
Alibaba · Proprietary
1475±12
2,674$0.33 / $1.951M
50
11103
Google · Apache 2.0
1475±27
408N/AN/A
51
2282
xAI · Proprietary
1474±13
2,258N/AN/A
52
8116
1472±36
252N/AN/A
53
2484
OpenAI · Proprietary
1470±12
2,762$1.75 / $14128K
54
2295
Alibaba · Proprietary
1470±17
1,263$0.78 / $3.90262.1K
55
2784
xAI · Proprietary
1468±9
4,529N/AN/A
56
18107
1467±24
629N/AN/A
57
2594
1467±12
2,676$0.10 / $0.201M
58
2695
Meituan · Proprietary
1466±12
2,542N/AN/A
59
2790
Anthropic
Anthropic · Proprietary
1466±10
3,892$15 / $75200K
60
2890
OpenAI · Proprietary
1465±9
4,965$1.75 / $14400K
61
2990
1465±9
5,420$0.50 / $31M
62
15117
Alibaba · Apache 2.0
1463±29
410$0.10 / $0.10262.1K
63
25107
Xiaomi · Proprietary
1462±17
1,221$0.40 / $2262.1K
64
3995
Google · Proprietary
1461±7
7,689$1.25 / $101M
65
3597
Moonshot · Modified MIT
1460±10
4,294$1.15 / $8262.1K
66
27107
OpenAI · Proprietary
1459±16
1,588$1.25 / $10400K
67
35104
DeepSeek · MIT
1458±12
2,633$0.10 / $0.201M
68
39107
OpenAI · Proprietary
1457±12
2,722$1.25 / $10400K
69
46104
Anthropic
Anthropic · Proprietary
1455±8
6,618$1 / $5200K
70
25120
Moonshot · Modified MIT
1455±24
562$0.38 / $2.02262.1K
71
46107
xAI · Proprietary
1455±9
4,623N/AN/A
72
44110
DeepSeek · MIT
1453±12
2,591$0.23 / $0.34131.1K
73
48107
Alibaba · Apache 2.0
1452±8
5,893$0.26 / $1.06N/A
74
30125
Baidu · Proprietary
1450±22
671N/AN/A
75
48115
DeepSeek · MIT
1449±11
3,093$0.23 / $0.34131.1K
76
29125
Alibaba · Apache 2.0
1449±25
563$0.20 / $0.88262.1K
77
27133
1448±29
396$0.27 / $0.41163.8K
78
47119
OpenAI · Proprietary
1447±16
1,449$1.25 / $10128K
79
38125
Z.ai · MIT
1447±22
716$0.40 / $1.75202.8K
80
47117
Anthropic
Anthropic · Proprietary
1447±14
1,711$15 / $75200K
81
38125
Tencent
Tencent · tencent-hunyuan-community
1447±23
652$0.29 / $1.17262.1K
82
52117
Baidu · Proprietary
1446±12
2,664N/AN/A
83
51117
xAI · Proprietary
1446±12
2,601$1.25 / $2.501M
84
56116
Google · Proprietary
1446±10
4,298$0.25 / $1.501M
85
52117
Alibaba · Apache 2.0
1445±12
2,473$0.26 / $2.08262.1K
86
52117
MiniMax · Modified MIT
1445±12
2,868$0.25 / $1204.8K
87
56117
OpenAI · Proprietary
1444±11
2,952$2 / $8200K
88
47125
Mistral · Modified MIT
1442±19
1,030$1.50 / $7.50262.1K
89
56125
Z.ai · MIT
1441±14
1,856$0.43 / $1.74202.8K
90
61120
xAI · Proprietary
1441±10
4,069$0.20 / $0.502M
91
57125
1440±15
1,629$0.30 / $2.501M
92
60125
Alibaba · Apache 2.0
1439±13
2,383$0.20 / $1.56262.1K
93
52128
Z.ai · MIT
1439±18
1,107$0.60 / $2.20131.1K
94
61125
OpenAI · Proprietary
1437±11
3,595$0.20 / $1.25400K
95
62125
Anthropic
Anthropic · Proprietary
1435±13
2,220$15 / $75200K
96
39150
Baidu · Proprietary
1434±34
275N/AN/A
97
46146
Alibaba · Apache 2.0
1434±30
378$0.26 / $2.60131.1K
98
61132
Anthropic
1434±15
1,650$3 / $151M
99
64133
xAI · Proprietary
1432±13
2,013$3 / $15256K
100
61138
MiniMax · MIT
1432±18
1,055$0.29 / $0.95204.8K
101
70128
Stepfun
StepFun · Apache 2.0
1431±10
3,604$0.09 / $0.30262.1K
102
56145
DeepSeek · MIT
1431±25
529$1.23 / $4.94N/A
103
71130
OpenAI · Proprietary
1429±9
4,317$5 / $15128K
104
59145
OpenAI · Proprietary
1429±24
608$75 / $150128K
105
61146
DeepSeek · MIT
1427±22
726$1.23 / $4.94N/A
106
84136
Google · Proprietary
1423±7
7,786$0.30 / $2.501M
107
64150
DeepSeek · MIT
1422±23
609$0.27 / $0.41163.8K
108
61151
Meituan · MIT
1422±26
515$0.20 / $0.80131.1K
109
52160
xAI · Proprietary
1422±34
298$3 / $15256K
110
81142
Mistral · Apache 2.0
1421±11
3,120$0.50 / $1.50N/A
111
82140
1421±10
3,615$0.10 / $0.30262.1K
112
71149
DeepSeek · MIT
1420±20
882$0.50 / $2.15163.8K
113
81145
Alibaba · Apache 2.0
1420±12
2,531$0.14 / $1262.1K
114
84144
MiniMax · Modified MIT
1420±11
3,475$0.15 / $0.90204.8K
115
64158
Alibaba · Proprietary
1419±27
448$0.78 / $3.90262.1K
116
84145
Alibaba · Proprietary
1418±11
3,487N/AN/A
117
70156
Moonshot · Modified MIT
1418±25
555$0.60 / $2.50262.1K
118
72151
xAI · Proprietary
1418±20
862$0.20 / $0.502M
119
71153
1418±22
709$0.10 / $0.30262.1K
120
94145
Mistral · Proprietary
1415±8
6,007$2.70 / $8.1032K
121
84151
Moonshot · Modified MIT
1414±16
1,459$0.60 / $2.50131.1K
122
84151
1413±15
1,531N/AN/A
123
94155
Anthropic
1408±14
1,875$3 / $15200K
124
98156
OpenAI · Proprietary
1406±13
2,254$1.10 / $4.40200K
125
100156
OpenAI · Proprietary
1406±12
2,508$2 / $81M
126
71174
1405±36
241N/AN/A
127
97160
xAI · Proprietary
1405±15
1,539$3 / $15131.1K
128
94163
OpenAI · Proprietary
1404±18
1,143$0.25 / $2400K
129
71177
Tencent
Tencent · Proprietary
1402±38
215N/AN/A
130
101160
Arcee AI · Apache 2.0
1402±12
2,631$0.15 / $0.45131K
131
70179
Z.ai · MIT
1402±41
196$0.60 / $1.8065.5K
132
96165
xAI · Proprietary
1402±19
920$0.25 / $1.27N/A
133
101160
Arcee AI · Apache 2.0
1401±13
2,641$0.22 / $0.85262.1K
134
100165
OpenAI · Proprietary
1401±17
1,330$15 / $60200K
135
97166
DeepSeek · MIT
1400±20
848$0.70 / $2.50163.8K
136
102163
Anthropic
Anthropic · Proprietary
1400±13
2,049$3 / $151M
137
74179
Alibaba · Apache 2.0
1398±37
236$0.08 / $0.28131.1K
138
103163
DeepSeek · MIT
1398±13
2,294$3 / $4.5032.8K
139
100170
OpenAI · Proprietary
1397±20
847$1.10 / $4.40200K
140
96173
Nvidia · NVIDIA Open Model
1397±24
597N/AN/A
141
104165
Alibaba · Apache 2.0
1396±14
1,877$0.46 / $1.82131.1K
142
102170
Alibaba · Apache 2.0
1395±18
1,004$0.09 / $1.10262.1K
143
104172
Alibaba · Apache 2.0
1393±17
1,144$0.05 / $0.19131.1K
144
110173
Z.ai · MIT
1390±16
1,389$0.13 / $0.85131.1K
145
103174
Z.ai · MIT
1390±20
798$0.06 / $0.40202.8K
146
112172
Anthropic
Anthropic · Proprietary
1388±13
2,127$3 / $15200K
147
115172
1387±12
2,538$0.10 / $0.401M
148
112174
Alibaba · Apache 2.0
1385±16
1,319$0.46 / $1.82131.1K
149
105178
Alibaba · Apache 2.0
1385±23
620$0.10 / $0.78262.1K
150
119174
OpenAI · Proprietary
1383±13
2,002$0.40 / $1.601M
151
121174
Mistral · Proprietary
1381±14
1,766$0.40 / $2131.1K
152
120175
OpenAI · Proprietary
1380±15
1,982$15 / $60N/A
153
120178
Alibaba · Apache 2.0
1379±17
1,319$0.40 / $1.60262.1K
154
124180
xAI · Proprietary
1375±17
1,168$0.30 / $0.50131.1K
155
113195
Alibaba · Proprietary
1370±30
358$0.40 / $1.20131.1K
156
132182
1370±15
1,577$0.10 / $0.401M
157
125190
1369±23
654N/AN/A
158
136179
Anthropic
Anthropic · Proprietary
1368±9
5,018$3 / $15200K
159
135184
Alibaba · Proprietary
1367±14
1,668N/AN/A
160
136183
OpenAI · Proprietary
1366±11
2,861$1.10 / $4.40200K
161
136187
MiniMax · Apache 2.0
1364±15
1,591$0.40 / $2.201M
162
136190
Alibaba · Apache 2.0
1363±17
1,200$0.50 / $116.4K
163
132195
Amazon · Proprietary
1362±22
711$0.30 / $2.501M
164
112211
1361±42
180$0.10 / $0.40131.1K
165
125200
Ant Group · MIT
1361±30
340N/AN/A
166
119203
Stepfun
StepFun · Apache 2.0
1361±35
258$0.57 / $1.4265.5K
167
124202
Ant Group · MIT
1360±33
333N/AN/A
168
138195
OpenAI · Apache 2.0
1359±16
1,315$0.04 / $0.18131.1K
169
129210
OpenAI · Proprietary
1354±33
324$0.05 / $0.40400K
170
148195
Google · Proprietary
1354±13
2,182$0.10 / $0.401M
171
129211
Prime Intellect · MIT
1354±34
310$0.20 / $1.10131.1K
172
150195
OpenAI · Proprietary
1351±12
3,191$1.10 / $4.40N/A
173
141202
Tencent
Tencent · Proprietary
1350±24
581N/AN/A
174
129221
Inception AI · Proprietary
1349±38
229$0.25 / $0.75128K
175
149200
DeepSeek · DeepSeek
1347±17
1,236$1.14 / $4.56N/A
176
149203
Nvidia · NVIDIA Open Model
1345±20
944$0.06 / $0.24262.1K
177
152202
Alibaba · Apache 2.0
1344±17
1,316$0.12 / $0.50131.1K
178
143222
IBM · Apache 2.0
1341±32
393$0.05 / $0.10131.1K
179
138228
MiniMax · Apache 2.0
1340±35
257$0.26 / $1204.8K
180
159200
Anthropic
Anthropic · Proprietary
1340±11
4,314$3 / $15200K
181
159202
Cohere
Cohere · CC-BY-NC-4.0
1339±11
2,782$2.50 / $10256K
182
156216
Mistral · Apache 2.0
1336±20
840$0.10 / $0.3032K
183
160203
Google · Proprietary
1336±11
3,319$3.50 / $10.502.1M
184
160208
Google · Gemma
1335±13
2,228$0.08 / $0.16131.1K
185
157222
Ai2 · Apache 2.0
1332±22
751$0.20 / $0.6065.5K
186
162216
01.AI
01 AI · Proprietary
1330±15
1,533N/AN/A
187
162218
1329±16
1,237$0.07 / $0.301M
188
156234
Stepfun
StepFun · Proprietary
1325±31
310N/AN/A
189
167221
1325±13
1,991$0.63 / $1.80131.1K
190
159230
Ai2 · Apache 2.0
1323±27
502$0.15 / $0.5065.5K
191
155236
Tencent
Tencent · Proprietary
1322±36
228N/AN/A
192
162228
Alibaba · Proprietary
1322±21
664N/AN/A
193
167222
Meta
Meta · Llama 3.1 Community
1321±12
3,123$4 / $432.8K
194
160234
OpenAI · Apache 2.0
1318±28
489$0.03 / $0.14131.1K
195
170228
Google · Proprietary
1316±12
3,896$3.50 / $10.502.1M
196
158242
Ai2 · Apache 2.0
1316±38
275$0.15 / $0.5065.5K
197
177228
Anthropic
Anthropic · Proprietary
1315±9
10,374$15 / $75200K
198
177228
xAI · Proprietary
1314±11
3,541$2 / $10131.1K
199
162241
OpenAI · Proprietary
1313±31
328$0.10 / $0.401M
200
177228
Anthropic
Anthropic · Proprietary
1312±11
3,505$0.80 / $4200K
201
174232
NexusFlow · NexusFlow
1311±15
1,469N/AN/A
202
179228
OpenAI · Proprietary
1310±10
5,887$5 / $15128K
203
177230
OpenAI · Proprietary
1309±13
2,349$2.50 / $10128K
204
167242
Z.ai · Proprietary
1309±29
354N/AN/A
205
177234
1309±16
1,503$0.40 / $0.708.2K
206
178232
Meta
Meta · Llama 3.1 Community
1308±13
2,128$4 / $432.8K
207
162251
IBM · Apache 2.0
1306±37
284N/AN/A
208
167242
DeepSeek · DeepSeek
1306±26
441N/AN/A
209
181235
1304±15
1,642$0.10 / $0.3032K
210
181236
Z.ai · Proprietary
1302±15
1,608$0.44 / $1.76204.8K
211
184236
Mistral · Mistral Research
1300±13
2,505$2 / $6131.1K
212
167253
Tencent
Tencent · Proprietary
1300±34
287N/AN/A
213
181241
Alibaba · Qwen
1299±18
1,011$1.60 / $6.4032.8K
214
181243
NexusFlow · CC-BY-NC-4.0
1297±19
867N/AN/A
215
186242
DeepSeek · DeepSeek
1295±15
1,523N/AN/A
216
189238
OpenAI · Proprietary
1295±11
5,195$10 / $30128K
217
189240
Meta
Meta · Llama-3.3
1294±11
2,895$0.10 / $0.32131.1K
218
189242
Google · Proprietary
1294±14
2,449N/AN/A
219
189241
Alibaba · Qwen
1294±12
2,397$1.20 / $1.20N/A
220
178253
1294±27
453$1.20 / $1.20131.1K
221
189241
xAI · Proprietary
1293±12
2,759$2 / $10131.1K
222
181254
Stepfun
StepFun · Proprietary
1291±27
472N/AN/A
223
170261
Tencent
Tencent · Proprietary
1290±39
207N/AN/A
224
183254
Mistral · Proprietary
1289±27
552$2 / $540K
225
183254
Reka AI · Proprietary
1288±25
458N/AN/A
226
196248
OpenAI · Proprietary
1287±12
4,240$10 / $30128K
227
200249
OpenAI · Proprietary
1284±11
3,547$0.15 / $0.60128K
228
184258
AI21 Labs · Jamba Open
1283±29
331$2 / $8256K
229
200251
Google · Proprietary
1281±13
2,116$0.07 / $0.301M
230
198258
Google · Gemma
1278±18
1,070$0.06 / $0.1232.8K
231
203254
OpenAI · Proprietary
1278±12
4,454$10 / $30128K
232
189267
Alibaba · Apache 2.0
1275±33
267$0.87 / $0.8732K
233
198263
Reka AI · Proprietary
1273±23
493N/AN/A
234
208256
Meta
Meta · Llama 3.1 Community
1272±12
2,924$0.40 / $0.40131.1K
235
204258
Amazon · Proprietary
1272±16
1,387$0.80 / $3.20300K
236
184276
Google · Gemma
1271±41
186$0.05 / $0.15131.1K
237
207258
Mistral · MRL
1269±15
1,510$2 / $6128K
238
213258
Anthropic
Anthropic · Proprietary
1269±12
5,614$3 / $15200K
239
208264
Microsoft · MIT
1266±17
1,124$0.07 / $0.1416.4K
240
219258
Google · Proprietary
1265±12
3,194$0.07 / $0.301M
241
207267
DeepSeek · DeepSeek License
1264±21
769$0.14 / $0.28128K
242
219264
Cohere
Cohere · CC-BY-NC-4.0
1263±14
1,764N/AN/A
243
219266
Amazon · Proprietary
1260±17
1,138$0.06 / $0.24300K
244
219266
OpenAI · Proprietary
1260±15
2,160$30 / $608.2K
245
218274
Mistral · Apache 2.0
1257±21
754$0.05 / $0.0832.8K
246
221267
Alibaba · Qianwen LICENSE
1257±15
1,763$0.90 / $0.9032.8K
247
196281
Google · Gemma
1257±41
208$0.05 / $0.10131.1K
248
219273
Nvidia · NVIDIA Open Model
1257±19
1,027N/AN/A
249
223265
Google · Gemma license
1256±11
4,025$0.65 / $0.658.2K
250
220278
Z.ai · Proprietary
1250±25
514N/AN/A
251
209281
1249±33
265N/AN/A
252
230272
Anthropic
Anthropic · Proprietary
1249±11
6,336$0.25 / $1.25200K
253
229275
OpenAI · Proprietary
1248±13
3,617$30 / $608.2K
254
221279
Cohere
Cohere · CC-BY-NC-4.0
1246±25
524$2.50 / $10128K
255
230278
Amazon · Proprietary
1242±17
1,094$0.04 / $0.14128K
256
236276
Meta
Meta · Llama 3 Community
1241±11
7,958$0.51 / $0.748.2K
257
236278
Google · Proprietary
1239±13
2,111$0.07 / $0.301M
258
237278
Cohere
Cohere · CC-BY-NC-4.0
1238±12
4,031$2.50 / $10128K
259
225285
Mistral · MRL
1236±30
332$0.10 / $0.10131.1K
260
241279
Google · Gemma license
1234±12
2,847$0.03 / $0.098.2K
261
223291
IBM · Apache 2.0
1232±35
237N/AN/A
262
240281
Alibaba · Qianwen LICENSE
1231±15
1,846N/AN/A
263
229288
Princeton · MIT
1231±30
369$0.03 / $0.098.2K
264
235286
Cohere
Cohere · CC-BY-NC-4.0
1229±24
600N/AN/A
265
238286
Cohere
Cohere · CC-BY-NC-4.0
1227±22
604$0.15 / $0.60128K
266
246282
Alibaba · Qianwen LICENSE
1225±17
1,411N/AN/A
267
246281
Mistral · Proprietary
1225±14
2,940$4 / $1232K
268
246286
Mistral · Proprietary
1222±17
1,357$2.70 / $8.1032K
269
243289
Reka AI · Proprietary
1222±21
830N/AN/A
270
248288
Alibaba · Qianwen LICENSE
1219±18
1,176N/AN/A
271
249290
01.AI
01 AI · Apache-2.0
1218±19
1,049N/AN/A
272
246291
InternLM · Other
1217±22
604$0 / $032.8K
273
237298
IBM · Apache 2.0
1215±36
225N/AN/A
274
252289
Mistral · Apache 2.0
1214±14
2,582$0.90 / $0.9065.5K
275
252291
Reka AI · Proprietary
1212±17
1,325N/AN/A
276
246298
AI21 Labs · Jamba Open
1210±31
332$0.20 / $0.40256K
277
256291
Cohere
Cohere · CC-BY-NC-4.0
1210±14
2,830$0.15 / $0.60128K
278
247296
OpenAI · Proprietary
1210±28
437$1 / $216.4K
279
258291
Meta
Meta · Llama 3 Community
1207±12
5,360$0.14 / $0.148.2K
280
258294
Microsoft · MIT
1202±18
1,091$0.17 / $0.68N/A
281
250301
IBM · Apache 2.0
1201±31
345N/AN/A
282
263294
Meta
Meta · Llama 3.1 Community
1195±12
2,589$0.02 / $0.03131.1K
283
263298
Mistral · Apache 2.0
1193±13
3,240$0.63 / $0.6332K
284
264298
OpenAI · Proprietary
1193±13
3,207$0.50 / $1.5016.4K
285
262301
Alibaba · Qianwen LICENSE
1190±20
944$0.30 / $0.30N/A
286
267301
Databricks · DBRX LICENSE
1186±16
1,678$0.60 / $0.6032.8K
287
271308
Meta
Meta · Llama 3.2
1175±25
499$0.05 / $0.34131.1K
288
272306
Google · Proprietary
1175±24
694$0.35 / $1.0532.8K
289
267310
IBM · Apache 2.0
1173±29
407N/AN/A
290
277308
Nexusflow · Apache-2.0
1171±20
952N/AN/A
291
277306
Google · Gemma license
1169±18
1,247$0.03 / $0.098.2K
292
280306
Google · Gemma license
1168±13
2,525N/AN/A
293
263313
HuggingFace · Apache 2.0
1168±40
219N/AN/A
294
279311
Microsoft · MIT
1163±19
895$0.15 / $0.60N/A
295
284311
Snowflake · Apache 2.0
1160±17
1,722N/AN/A
296
279312
OpenChat · Apache-2.0
1159±23
611N/AN/A
297
269314
OpenChat · Apache-2.0
1159±42
194$0.20 / $0.20N/A
298
284313
01.AI
01 AI · Yi License
1152±25
559$0.90 / $0.904.1K
299
277314
Alibaba · Apache 2.0
1152±36
232$0.50 / $116.4K
300
284314
1145±26
486$0.13 / $0.524.1K
301
280315
Alibaba · Qianwen LICENSE
1144±37
231$0.20 / $0.20N/A
302
287314
LMSYS · Non-commercial
1142±27
484$0 / $02K
303
287314
Microsoft · MIT
1137±20
936$0.13 / $0.52N/A
304
287314
Mistral · Apache-2.0
1136±21
798$0.20 / $0.2032.8K
305
287316
UC Berkeley · CC-BY-NC-4.0
1134±31
318N/AN/A
306
290314
Meta
Meta · Llama 2 Community
1134±17
1,356$0.70 / $2.804.1K
307
287316
Meta
Meta · Llama 2 Community
1130±28
411$0.15 / $0.154.1K
308
290316
Meta
Meta · Llama 2 Community
1126±25
539$0.25 / $0.254.1K
309
292316
Google · Gemma license
1117±31
340$0.05 / $0.088.2K
310
293316
LMSYS · Llama 2 Community
1112±31
321$0.30 / $0.30N/A
311
295316
Google · Gemma license
1112±26
578N/AN/A
312
292316
HuggingFace · MIT
1109±38
201$0.15 / $0.1516.4K
313
296316
Alibaba · Qianwen LICENSE
1103±31
356$0.10 / $0.10N/A
314
305316
Microsoft · MIT
1094±20
1,095$0.13 / $0.52N/A
315
298316
Mistral · Apache 2.0
1080±39
183$0.07 / $0.284.1K
316
306316
Meta
Meta · Llama 3.2
1080±28
487$0.03 / $0.20131.1K

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)