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.

Apr 10, 2026
967,782 votes
317 models
Rank Spread
1
12
Anthropic
Anthropic · Proprietary
1525±9
4,405$5 / $251M
2
14
Anthropic
Anthropic · Proprietary
1516±9
4,874$5 / $251M
3
29
Google · Proprietary
1506±8
5,955$2 / $121M
4
217
Z.ai · MIT
1499±15
1,548$0.95 / $3.15202.8K
5
312
Anthropic
1495±7
9,328$5 / $25200K
6
317
Anthropic
Anthropic · Proprietary
1495±11
3,128$3 / $151M
7
319
OpenAI · Proprietary
1493±11
2,779$2.50 / $151.1M
8
315
Anthropic
Anthropic · Proprietary
1492±6
12,081$5 / $25200K
9
316
Google · Proprietary
1492±7
10,566$2 / $121M
10
421
Anthropic
1485±6
11,226$15 / $75200K
11
424
OpenAI · Proprietary
1484±11
2,892$2.50 / $151.1M
12
523
Anthropic
1482±6
14,808$3 / $15200K
13
523
Anthropic
Anthropic · Proprietary
1481±6
14,888$3 / $15200K
14
431
xAI · Proprietary
1477±13
2,105N/AN/A
15
928
Google · Proprietary
1476±7
7,934$0.50 / $31M
16
732
1474±11
2,959$2 / $62M
17
634
Alibaba · Proprietary
1473±12
2,256N/AN/A
18
1128
Anthropic
Anthropic · Proprietary
1472±5
17,860$15 / $75200K
19
1034
OpenAI · Proprietary
1470±9
4,521$1.75 / $14128K
20
942
Google · Apache 2.0
1469±14
1,638$0.14 / $0.40262.1K
21
1041
OpenAI · Proprietary
1469±13
2,042$2.50 / $151.1M
22
551
Meta
Meta · Proprietary
1467±19
894N/AN/A
23
1142
Xiaomi · Proprietary
1466±12
2,301$1 / $31M
24
1435
1465±7
9,039$0.50 / $31M
25
1439
Anthropic
Anthropic · Proprietary
1464±8
6,994$15 / $75200K
26
1345
1463±11
2,758$2 / $62M
27
1445
OpenAI · Proprietary
1462±9
4,096$1.75 / $14128K
28
1446
Z.ai · MIT
1460±9
4,026$1 / $3.20202.8K
29
1641
Google · Proprietary
1460±5
24,851$1.25 / $101M
30
1644
OpenAI · Proprietary
1459±7
10,331$1.25 / $10400K
31
1648
Moonshot · Modified MIT
1458±9
4,610$0.60 / $3N/A
32
1859
Z.ai · MIT
1452±11
3,117$0.39 / $1.75202.8K
33
2157
xAI · Proprietary
1451±6
11,905N/AN/A
34
2257
xAI · Proprietary
1450±6
12,561N/AN/A
35
2161
Alibaba · Apache 2.0
1449±9
4,409$0.39 / $2.34262.1K
36
2161
Bytedance
Bytedance · Proprietary
1448±8
5,376N/AN/A
37
1870
Google · Apache 2.0
1448±15
1,568N/AN/A
38
2069
Moonshot · Modified MIT
1447±12
2,226$0.38 / $1.72262.1K
39
2663
Anthropic
Anthropic · Proprietary
1446±7
8,428$15 / $75200K
40
2663
OpenAI · Proprietary
1446±7
7,613$1.75 / $14400K
41
2170
DeepSeek · MIT
1446±12
2,377$1.23 / $4.94N/A
42
2969
Alibaba · Proprietary
1444±8
6,089$0.78 / $3.90262.1K
43
3067
OpenAI · Proprietary
1444±6
11,533$1.25 / $10400K
44
2276
OpenAI · Proprietary
1443±14
1,796$75 / $150128K
45
3069
Baidu · Proprietary
1442±8
5,862N/AN/A
46
1787
1442±22
690$0.21 / $0.79163.8K
47
3169
DeepSeek · MIT
1442±7
10,127$0.26 / $0.38163.8K
48
2773
DeepSeek · MIT
1441±11
2,962$0.27 / $0.41163.8K
49
3169
DeepSeek · MIT
1441±7
8,640$0.26 / $0.38163.8K
50
2479
Meituan · Proprietary
1440±15
1,559N/AN/A
51
3171
Anthropic
1440±8
6,781$3 / $151M
52
3269
OpenAI · Proprietary
1440±5
17,460$5 / $15128K
53
3273
OpenAI · Proprietary
1438±7
8,184$1.75 / $14400K
54
3277
Google · Proprietary
1436±9
4,618$0.25 / $1.501M
55
3477
OpenAI · Proprietary
1436±8
6,794$1.25 / $10128K
56
3574
Alibaba · Apache 2.0
1435±5
19,217$0.26 / $1.06N/A
57
3282
Baidu · Proprietary
1435±12
2,476N/AN/A
58
3577
Moonshot · Modified MIT
1434±6
11,769$1.15 / $8262.1K
59
3778
Z.ai · MIT
1433±7
8,828$0.39 / $1.90204.8K
60
3977
Anthropic
Anthropic · Proprietary
1433±6
14,971$1 / $5200K
61
3287
Alibaba · Proprietary
1433±13
2,091$0.78 / $3.90262.1K
62
3492
1431±13
2,088$0.27 / $0.41163.8K
63
3985
xAI · Proprietary
1430±9
4,895$3 / $15131.1K
64
32104
1427±18
959N/AN/A
65
4692
Anthropic
1426±8
6,186$3 / $15200K
66
4889
Anthropic
Anthropic · Proprietary
1426±7
7,761$3 / $151M
67
39101
Alibaba · Apache 2.0
1425±13
2,232$0.20 / $0.88262.1K
68
5192
xAI · Proprietary
1424±6
10,960$0.20 / $0.502M
69
5292
OpenAI · Proprietary
1424±6
9,908$2 / $81M
70
4997
MiniMax · Modified MIT
1424±9
4,736$0.12 / $0.99196.6K
71
39107
xAI · Proprietary
1422±15
1,464$3 / $15256K
72
5893
Google · Proprietary
1421±5
23,918$0.30 / $2.501M
73
49101
DeepSeek · MIT
1421±10
3,248$1.23 / $4.94N/A
74
37110
1420±19
890N/AN/A
75
52104
Alibaba · Apache 2.0
1419±10
3,476$0.26 / $2.08262.1K
76
40109
Baidu · Proprietary
1419±17
1,171N/AN/A
77
59101
1418±7
7,986$0.30 / $2.501M
78
40115
DeepSeek · MIT
1418±20
853$0.21 / $0.79163.8K
79
59101
xAI · Proprietary
1417±7
8,932$3 / $15256K
80
59104
Z.ai · MIT
1417±9
5,064$0.60 / $2.20131.1K
81
53110
MiniMax · Proprietary
1415±14
1,808$0.30 / $1.20196.6K
82
61107
Mistral · Apache 2.0
1414±7
10,100$0.50 / $1.50N/A
83
60108
xAI · Proprietary
1412±9
4,496$0.20 / $0.502M
84
60109
Alibaba · Apache 2.0
1412±10
3,374$0.20 / $1.56262.1K
85
63108
Alibaba · Apache 2.0
1412±8
7,196$0.46 / $1.82131.1K
86
60109
OpenAI · Proprietary
1411±10
3,571$15 / $60200K
87
64108
OpenAI · Proprietary
1411±8
6,890$1.25 / $10400K
88
69107
Mistral · Proprietary
1411±5
18,991$2.70 / $8.1032K
89
63110
MiniMax · MIT
1411±9
4,278$0.29 / $0.95196.6K
90
69109
Anthropic
Anthropic · Proprietary
1409±7
6,718$3 / $15200K
91
68112
Alibaba · Apache 2.0
1408±9
4,934$0.40 / $1.60262.1K
92
64116
DeepSeek · MIT
1408±11
3,161$0.50 / $2.15163.8K
93
70109
OpenAI · Proprietary
1408±6
11,553$2 / $8200K
94
69113
Stepfun
StepFun · Apache 2.0
1407±8
4,987$0.10 / $0.30262.1K
95
61117
Alibaba · Apache 2.0
1407±14
1,748$0.26 / $2.60131.1K
96
64120
OpenAI · Proprietary
1405±14
1,861$2.50 / $151.1M
97
70117
Alibaba · Proprietary
1403±10
3,522N/AN/A
98
74116
1403±7
8,011$0.09 / $0.29262.1K
99
70119
1403±11
2,826$0.09 / $0.29262.1K
100
69123
Alibaba · Apache 2.0
1402±14
1,638$0.15 / $1.50131.1K
101
57134
Tencent
Tencent · Proprietary
1402±25
507N/AN/A
102
70122
Moonshot · Modified MIT
1402±12
2,558$0.60 / $2.50262.1K
103
74127
DeepSeek · MIT
1398±12
2,303$0.70 / $2.5064K
104
77122
Alibaba · Apache 2.0
1398±10
3,506$0.16 / $1.30262.1K
105
77124
Arcee AI · Apache 2.0
1398±10
3,574N/AN/A
106
92127
DeepSeek · MIT
1393±7
8,530$3 / $4.5032.8K
107
91130
Moonshot · Modified MIT
1392±8
5,543$0.60 / $2.50131.1K
108
94126
Anthropic
Anthropic · Proprietary
1392±6
13,820$3 / $15200K
109
88132
Microsoft AI · Proprietary
1391±10
3,622N/AN/A
110
91131
Alibaba · Apache 2.0
1391±8
5,271$0.09 / $1.10262.1K
111
93132
Mistral · Proprietary
1390±8
5,943$0.40 / $2131.1K
112
74143
Tencent
Tencent · Proprietary
1390±20
893N/AN/A
113
96132
OpenAI · Proprietary
1389±7
7,098$0.40 / $1.601M
114
77149
1387±20
764N/AN/A
115
93137
Meituan · MIT
1387±12
2,364$0.20 / $0.80131.1K
116
98134
1386±6
11,571$0.10 / $0.401M
117
98136
Alibaba · Proprietary
1384±9
4,531N/AN/A
118
100140
Alibaba · Apache 2.0
1382±9
4,928$0.09 / $0.30262.1K
119
100143
OpenAI · Proprietary
1381±10
4,578$15 / $60N/A
120
103140
Z.ai · MIT
1380±8
6,707$0.13 / $0.85131.1K
121
83163
Z.ai · MIT
1380±23
663$0.30 / $0.90131.1K
122
104146
Alibaba · Apache 2.0
1379±9
4,614$0.46 / $1.82131.1K
123
105143
1379±8
6,360$0.10 / $0.401M
124
102147
xAI · Proprietary
1378±10
3,325$0.30 / $0.50131.1K
125
99154
Tencent
Tencent · Proprietary
1377±15
1,541N/AN/A
126
80169
Tencent
Tencent · Proprietary
1376±28
371N/AN/A
127
109149
1375±8
6,149N/AN/A
128
107150
DeepSeek · DeepSeek
1375±11
3,123$1.14 / $4.56N/A
129
107151
Z.ai · MIT
1374±11
3,196$0.06 / $0.40202.8K
130
107155
OpenAI · Proprietary
1372±12
2,160$1.10 / $4.40200K
131
112160
Alibaba · Apache 2.0
1369±11
2,871$0.10 / $0.78131.1K
132
115151
Cohere
Cohere · CC-BY-NC-4.0
1369±6
10,610$2.50 / $10256K
133
114155
OpenAI · Proprietary
1369±8
5,829$0.25 / $2400K
134
114161
xAI · Proprietary
1367±9
4,177$0.30 / $0.50131.1K
135
116155
OpenAI · Proprietary
1367±7
8,606$1.10 / $4.40200K
136
118161
MiniMax · Apache 2.0
1365±7
7,031$0.40 / $2.201M
137
120163
Google · Gemma
1363±7
6,696$0.08 / $0.16131.1K
138
121163
Google · Proprietary
1363±7
6,521$0.10 / $0.401M
139
108178
Alibaba · Proprietary
1362±21
690$0.40 / $1.20131.1K
140
116169
Nvidia · NVIDIA Open Model
1361±13
1,993N/AN/A
141
121165
Mistral · Apache 2.0
1360±10
3,433$0.10 / $0.3032K
142
126165
OpenAI · Proprietary
1357±6
9,277$1.10 / $4.40200K
143
128168
Google · Proprietary
1356±7
8,372$3.50 / $10.502.1M
144
112192
Alibaba · Apache 2.0
1355±25
504$0.08 / $0.2441K
145
104201
Tencent
Tencent · Proprietary
1355±32
287N/AN/A
146
125177
1354±12
2,599N/AN/A
147
122187
Prime Intellect · MIT
1351±17
1,267$0.20 / $1.10131.1K
148
133177
Anthropic
Anthropic · Proprietary
1350±8
10,574$3 / $15200K
149
135179
Google · Proprietary
1349±8
9,750$3.50 / $10.502.1M
150
135182
1347±10
2,940$0.07 / $0.301M
151
128193
Stepfun
StepFun · Apache 2.0
1346±16
1,271$0.57 / $1.4265.5K
152
123200
1345±22
650$0.10 / $0.40131.1K
153
116204
Google · Gemma
1345±29
371$0.04 / $0.13131.1K
154
138182
OpenAI · Proprietary
1345±8
7,913$1.10 / $4.40N/A
155
132195
MiniMax · Apache 2.0
1344±15
1,608$0.26 / $1196.6K
156
129195
Stepfun
StepFun · Proprietary
1344±17
1,277N/AN/A
157
118208
Tencent
Tencent · Proprietary
1343±30
313N/AN/A
158
141182
Anthropic
Anthropic · Proprietary
1342±6
11,031$0.80 / $4200K
159
128203
Stepfun
StepFun · Proprietary
1342±21
693N/AN/A
160
118209
Nvidia · Nvidia Open Model
1341±30
321$0.60 / $1.80131.1K
161
132201
Z.ai · MIT
1341±18
1,075$0.60 / $1.8065.5K
162
140192
Alibaba · Apache 2.0
1340±9
4,494$0.08 / $0.2841K
163
132203
Zhipu · Proprietary
1339±20
765N/AN/A
164
140195
Ai2 · Apache 2.0
1338±11
2,896$0.20 / $0.6065.5K
165
140195
Amazon · Proprietary
1338±11
2,930$0.30 / $2.501M
166
123213
1337±30
317N/AN/A
167
138203
DeepSeek · DeepSeek
1337±17
1,037N/AN/A
168
143195
OpenAI · Proprietary
1337±8
6,160$2.50 / $10128K
169
143195
Alibaba · Apache 2.0
1336±9
4,052$0.15 / $0.58131.1K
170
132209
1335±24
578N/AN/A
171
145195
1334±7
7,106$0.63 / $1.80131.1K
172
146195
xAI · Proprietary
1334±7
8,902$2 / $10131.1K
173
143202
Mistral · Proprietary
1334±12
2,405$2 / $540K
174
132213
Tencent
Tencent · Proprietary
1333±27
432N/AN/A
175
147200
OpenAI · Proprietary
1331±7
14,922$5 / $15128K
176
143205
Ant Group · MIT
1331±16
1,351N/AN/A
177
143206
OpenAI · Proprietary
1328±15
1,632$0.05 / $0.40400K
178
143209
Ant Group · MIT
1327±16
1,271N/AN/A
179
150203
1326±8
5,789$0.40 / $0.708.2K
180
151203
OpenAI · Proprietary
1326±7
8,983$0.15 / $0.60128K
181
151203
Anthropic
Anthropic · Proprietary
1326±6
23,374$15 / $75200K
182
151203
OpenAI · Apache 2.0
1326±8
6,531$0.04 / $0.19131.1K
183
147207
Alibaba · Qwen
1325±12
2,440$1.60 / $6.4032.8K
184
151204
Meta
Meta · Llama 3.1 Community
1325±8
5,486$4 / $432.8K
185
150205
Zhipu AI · Proprietary
1325±10
3,992$0.44 / $1.76204.8K
186
150205
01.AI
01 AI · Proprietary
1325±11
3,634N/AN/A
187
143216
OpenAI · Proprietary
1325±20
730$0.10 / $0.401M
188
143217
Inception AI · Proprietary
1324±21
846$0.25 / $0.75128K
189
151209
Google · Proprietary
1322±10
5,486N/AN/A
190
154205
1322±8
6,354$0.10 / $0.3032K
191
154208
Google · Proprietary
1321±8
5,463$0.07 / $0.301M
192
153209
NexusFlow · NexusFlow
1321±10
3,663N/AN/A
193
150218
Ai2 · Apache 2.0
1318±17
1,355$0.15 / $0.5065.5K
194
162209
Meta
Meta · Llama 3.1 Community
1317±8
8,047$4 / $432.8K
195
162210
Alibaba · Qwen
1317±8
6,008$1.20 / $1.20N/A
196
162210
xAI · Proprietary
1316±8
7,048$2 / $10131.1K
197
164213
OpenAI · Proprietary
1315±8
11,559$10 / $30128K
198
150226
Tencent
Tencent · Proprietary
1315±20
881N/AN/A
199
162217
DeepSeek · DeepSeek
1314±10
3,499N/AN/A
200
174216
Meta
Meta · Llama-3.3
1311±7
8,332$0.10 / $0.32131.1K
201
147234
Google · Gemma
1310±28
444$0.04 / $0.08131.1K
202
167221
Google · Gemma
1310±11
2,872$0.02 / $0.0432.8K
203
166227
Alibaba · Proprietary
1308±14
1,586N/AN/A
204
180223
OpenAI · Proprietary
1305±9
9,653$10 / $30128K
205
181227
Mistral · MRL
1304±10
3,607$2 / $6131.1K
206
184227
Mistral · Mistral Research
1303±9
5,885$2 / $6131.1K
207
176230
Ai2 · Apache 2.0
1302±14
1,979$0.15 / $0.5065.5K
208
182230
OpenAI · Apache 2.0
1300±13
2,105$0.03 / $0.14131.1K
209
190230
Amazon · Proprietary
1299±10
3,398$0.80 / $3.20300K
210
192230
Google · Proprietary
1299±9
7,837$0.07 / $0.301M
211
192230
OpenAI · Proprietary
1299±9
9,140$10 / $30128K
212
195229
Google · Gemma license
1298±7
9,918$0.65 / $0.658.2K
213
162243
Inception AI · Proprietary
1297±27
500$0.25 / $0.75128K
214
199234
Nvidia · NVIDIA Open Model
1292±10
3,870$0.06 / $0.24262.1K
215
200231
Meta
Meta · Llama 3.1 Community
1292±8
7,622$0.40 / $0.40131.1K
216
197235
NexusFlow · CC-BY-NC-4.0
1291±12
2,123N/AN/A
217
192241
IBM · Apache 2.0
1290±17
1,293N/AN/A
218
201235
Cohere
Cohere · CC-BY-NC-4.0
1288±9
4,165N/AN/A
219
195245
Princeton · MIT
1287±19
841$0.03 / $0.098.2K
220
195245
Alibaba · Apache 2.0
1286±19
804$0.87 / $0.8732K
221
200241
Nvidia · NVIDIA Open Model
1286±13
2,130N/AN/A
222
200242
DeepSeek · DeepSeek License
1285±14
1,842$0.14 / $0.28128K
223
206240
Anthropic
Anthropic · Proprietary
1283±9
11,870$3 / $15200K
224
201245
1280±18
1,049$1.20 / $1.20131.1K
225
203245
Cohere
Cohere · CC-BY-NC-4.0
1280±15
1,369$2.50 / $10128K
226
206245
Mistral · Apache 2.0
1279±14
1,767$0.05 / $0.0832.8K
227
202246
Reka AI · Proprietary
1278±18
951N/AN/A
228
213245
OpenAI · Proprietary
1275±9
7,523$30 / $608.2K
229
212245
OpenAI · Proprietary
1274±12
4,251$30 / $608.2K
230
213245
Amazon · Proprietary
1274±11
2,784$0.06 / $0.24300K
231
202252
Ai2 · Llama 3.1
1271±25
463N/AN/A
232
202253
Tencent
Tencent · Proprietary
1270±27
414N/AN/A
233
206252
1268±23
587N/AN/A
234
213251
Zhipu AI · Proprietary
1266±17
1,174N/AN/A
235
217249
Microsoft · MIT
1266±11
2,896$0.07 / $0.1416.4K
236
218248
Google · Proprietary
1265±8
5,573$0.07 / $0.301M
237
220249
Google · Gemma license
1263±8
6,877$0.03 / $0.098.2K
238
221249
Anthropic
Anthropic · Proprietary
1263±8
13,976$0.25 / $1.25200K
239
215253
Reka AI · Proprietary
1262±18
992N/AN/A
240
217252
Cohere
Cohere · CC-BY-NC-4.0
1260±15
1,421$0.15 / $0.60128K
241
217253
AI21 Labs · Jamba Open
1260±17
1,024$2 / $8256K
242
222251
Cohere
Cohere · CC-BY-NC-4.0
1259±9
9,149$2.50 / $10128K
243
222251
Alibaba · Qianwen LICENSE
1258±10
4,614$0.90 / $0.9032.8K
244
217256
Mistral · MRL
1258±20
720$0.10 / $0.10131.1K
245
231253
Meta
Meta · Llama 3 Community
1250±8
17,500$0.51 / $0.748.2K
246
231256
Amazon · Proprietary
1247±11
2,625$0.04 / $0.14128K
247
230258
Cohere
Cohere · CC-BY-NC-4.0
1247±15
1,483N/AN/A
248
235257
Mistral · Proprietary
1243±10
6,217$4 / $1232K
249
217273
Ai2 · Apache-2.0
1242±34
261$0.05 / $0.20128K
250
241265
Alibaba · Qianwen LICENSE
1233±12
3,483N/AN/A
251
245265
Cohere
Cohere · CC-BY-NC-4.0
1230±10
6,160$0.15 / $0.60128K
252
232276
IBM · Apache 2.0
1229±27
461N/AN/A
253
245268
Alibaba · Qianwen LICENSE
1226±12
3,345N/AN/A
254
235277
Ai2 · Llama 3.1
1225±26
454N/AN/A
255
249268
Meta
Meta · Llama 3.1 Community
1222±8
6,736$0.02 / $0.0516.4K
256
245274
Google · Proprietary
1222±18
1,351$0.35 / $1.0532.8K
257
247272
Alibaba · Qianwen LICENSE
1221±13
2,574N/AN/A
258
238278
IBM · Apache 2.0
1220±26
489N/AN/A
259
249272
OpenAI · Proprietary
1217±9
6,707$0.50 / $1.5016.4K
260
249275
Mistral · Proprietary
1217±13
2,718$2.70 / $8.1032K
261
248277
AI21 Labs · Jamba Open
1216±18
1,023$0.20 / $0.40256K
262
249273
Mistral · Apache 2.0
1215±10
5,865$0.90 / $0.9065.5K
263
249277
Reka AI · Proprietary
1214±16
1,650N/AN/A
264
249276
Reka AI · Proprietary
1214±13
2,719N/AN/A
265
253278
Meta
Meta · Llama 3 Community
1205±9
11,165$0.03 / $0.048.2K
266
251281
01.AI
01 AI · Apache-2.0
1202±13
2,098N/AN/A
267
249286
IBM · Apache 2.0
1200±24
603N/AN/A
268
251285
InternLM · Other
1198±16
1,266$0 / $032.8K
269
258288
Alibaba · Qianwen LICENSE
1189±15
2,102$0.30 / $0.30N/A
270
261288
Microsoft · MIT
1188±13
2,150$0.17 / $0.68N/A
271
264290
Databricks · DBRX LICENSE
1185±13
3,489$0.60 / $0.6032.8K
272
266286
Google · Gemma license
1185±9
5,866N/AN/A
273
259294
OpenAI · Proprietary
1183±21
933$1 / $216.4K
274
253297
HuggingFace · Apache 2.0
1180±28
448N/AN/A
275
251301
DeepSeek · DeepSeek License
1180±37
243N/AN/A
276
255297
OpenChat · Apache-2.0
1179±28
414$0.20 / $0.20N/A
277
266292
Mistral · Apache 2.0
1179±10
6,572$0.63 / $0.6332K
278
253300
Microsoft · Llama 2 Community
1179±32
355N/AN/A
279
257297
Alibaba · Apache 2.0
1178±26
475$0.15 / $0.58131.1K
280
253301
AllenAI/UW · AI2 ImpACT Low-risk
1175±34
280N/AN/A
281
267298
01.AI
01 AI · Yi License
1168±18
1,106$0.90 / $0.904.1K
282
267299
OpenChat · Apache-2.0
1167±19
1,097N/AN/A
283
268300
Nexusflow · Apache-2.0
1163±16
1,676N/AN/A
284
270297
Google · Gemma license
1163±13
2,649$0.03 / $0.098.2K
285
266305
Alibaba · Qianwen LICENSE
1161±30
372$0.20 / $0.20N/A
286
272301
Microsoft · MIT
1159±13
2,238$0.15 / $0.60N/A
287
270302
Meta
Meta · Llama 3.2
1157±18
1,046$0.05 / $0.3480K
288
273306
UC Berkeley · CC-BY-NC-4.0
1148±23
666N/AN/A
289
267311
Microsoft · Llama 2 Community
1146±41
203$0.30 / $0.30N/A
290
273309
IBM · Apache 2.0
1145±25
647N/AN/A
291
274309
LMSYS · Llama 2 Community
1141±22
756$0.30 / $0.30N/A
292
267314
LMSYS · Llama 2 Community
1139±45
162$0.20 / $0.20N/A
293
275309
Meta
Meta · Llama 2 Community
1137±18
1,193$0.25 / $0.254.1K
294
274311
NousResearch · Apache-2.0
1136±33
270$0.17 / $0.17N/A
295
272313
Google · Proprietary
1136±38
251$0.50 / $0.5025.8K
296
281307
Meta
Meta · Llama 2 Community
1135±13
2,813$0.70 / $2.804.1K
297
283310
Mistral · Apache-2.0
1131±15
1,592$0.20 / $0.2032.8K
298
279311
LMSYS · Non-commercial
1131±19
1,047$0 / $02K
299
275314
HuggingFace · Apache 2.0
1129±33
328N/AN/A
300
286311
Snowflake · Apache 2.0
1125±14
2,793N/AN/A
301
275316
Alibaba · Qianwen LICENSE
1124±38
214N/AN/A
302
287314
Google · Gemma license
1113±18
1,179N/AN/A
303
280317
NousResearch · Apache-2.0
1113±36
230$0.90 / $0.90N/A
304
287315
Google · Gemma license
1109±23
676$0.05 / $0.088.2K
305
290315
Microsoft · MIT
1105±15
1,706$0.13 / $0.52N/A
306
289316
1104±19
1,035$0.13 / $0.524.1K
307
287317
HuggingFace · MIT
1103±28
461$0.15 / $0.1516.4K
308
293316
Meta
Meta · Llama 3.2
1099±19
1,057$0.03 / $0.2060K
309
288317
Meta
Meta · Llama 2 Community
1095±33
320$0.35 / $1.4016.4K
310
290317
Mistral · Apache 2.0
1094±27
448$0.07 / $0.284.1K
311
294317
Google · Gemma license
1081±31
377$0.10 / $0.10N/A
312
298317
Alibaba · Qianwen LICENSE
1075±24
692$0.10 / $0.10N/A
313
302317
Meta
Meta · Llama 2 Community
1073±20
835$0.15 / $0.154.1K
314
298317
Together AI · Apache 2.0
1069±32
334$0.20 / $0.20N/A
315
304317
Microsoft · MIT
1069±16
2,074$0.13 / $0.52N/A
316
299317
Nvidia · Llama 2 Community
1054±44
208N/AN/A
317
307317
Tsinghua · Apache-2.0
1039±40
205N/AN/A

Default Leaderboard Plots

Fraction of Model A Wins for All Non-tied A vs. B Battles

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

Average Win Rate Against All Other Models (Uniform Sampling and No Ties)