Text Arena⚖️Legal & Government

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
337,192 votes
310 models
Rank Spread
1
121
xAI · Proprietary
1517±27
489N/AN/A
2
118
Anthropic
Anthropic · Proprietary
1512±19
990$5 / $251M
3
118
Google · Proprietary
1510±17
1,298$2 / $121M
4
123
Anthropic
Anthropic · Proprietary
1506±19
1,010$5 / $251M
5
121
Google · Proprietary
1501±11
2,931$2 / $121M
6
143
OpenAI · Proprietary
1492±27
513$2.50 / $151.1M
7
142
1490±24
554$2 / $62M
8
131
Google · Proprietary
1488±13
2,344$0.50 / $31M
9
131
Anthropic
1488±12
2,695$5 / $25200K
10
145
OpenAI · Proprietary
1484±21
821$1.75 / $14128K
11
135
xAI · Proprietary
1483±11
3,209N/AN/A
12
338
Anthropic
Anthropic · Proprietary
1480±11
3,207$5 / $25200K
13
153
Anthropic
Anthropic · Proprietary
1475±21
817$3 / $151M
14
644
xAI · Proprietary
1475±11
3,474N/AN/A
15
160
OpenAI · Proprietary
1474±26
520$2.50 / $151.1M
16
646
1473±13
2,227$0.50 / $31M
17
184
Bytedance
Bytedance · Proprietary
1473±42
199N/AN/A
18
162
1473±25
508$2 / $62M
19
354
OpenAI · Proprietary
1471±20
946$1.75 / $14128K
20
175
Google · Apache 2.0
1469±31
335$0.14 / $0.40262.1K
21
177
OpenAI · Proprietary
1469±33
325$0.75 / $4.50400K
22
557
Z.ai · MIT
1469±20
895$1 / $3.20202.8K
23
362
OpenAI · Proprietary
1469±23
701$75 / $150128K
24
850
Google · Proprietary
1466±8
7,309$1.25 / $101M
25
954
Anthropic
1461±11
3,219$15 / $75200K
26
954
Anthropic
Anthropic · Proprietary
1461±10
3,894$3 / $15200K
27
584
Xiaomi · Proprietary
1460±28
394$1 / $31M
28
674
Baidu · Proprietary
1459±21
767N/AN/A
29
192
1459±35
264$0.21 / $0.79163.8K
30
1056
OpenAI · Proprietary
1459±9
5,332$5 / $15128K
31
1057
Anthropic
Anthropic · Proprietary
1458±9
5,315$15 / $75200K
32
964
OpenAI · Proprietary
1458±14
1,967$1.25 / $10128K
33
1063
OpenAI · Proprietary
1456±12
2,968$1.25 / $10400K
34
685
Alibaba · Proprietary
1456±27
417N/AN/A
35
1162
Anthropic
1456±10
3,911$3 / $15200K
36
877
Z.ai · MIT
1455±19
963$0.39 / $1.75202.8K
37
1073
OpenAI · Proprietary
1454±14
1,883$1.25 / $10400K
38
884
Moonshot · Modified MIT
1453±21
787$0.60 / $2.50262.1K
39
1468
OpenAI · Proprietary
1452±10
3,851$2 / $8200K
40
694
Baidu · Proprietary
1451±29
336N/AN/A
41
1279
OpenAI · Proprietary
1450±15
1,769$1.75 / $14400K
42
1575
OpenAI · Proprietary
1449±11
3,083$1.25 / $10400K
43
6104
Meituan · Proprietary
1449±34
280N/AN/A
44
1384
Baidu · Proprietary
1448±16
1,451N/AN/A
45
893
Moonshot · Modified MIT
1447±25
520$0.38 / $1.72262.1K
46
1684
OpenAI · Proprietary
1445±14
1,968$1.75 / $14400K
47
6111
Google · Apache 2.0
1445±34
279N/AN/A
48
6116
1444±36
249N/AN/A
49
1692
Moonshot · Modified MIT
1441±16
1,263$0.60 / $3N/A
50
1594
Google · Proprietary
1440±18
1,003$0.25 / $1.501M
51
2087
Anthropic
Anthropic · Proprietary
1439±11
2,935$15 / $75200K
52
2388
OpenAI · Proprietary
1438±11
3,296$2 / $81M
53
2390
Moonshot · Modified MIT
1438±11
3,093$1.15 / $8262.1K
54
16100
Alibaba · Apache 2.0
1436±19
904$0.39 / $2.34262.1K
55
15106
Alibaba · Apache 2.0
1436±22
762$0.20 / $0.88262.1K
56
2492
Z.ai · MIT
1436±12
2,429$0.39 / $1.90204.8K
57
2492
Anthropic
Anthropic · Proprietary
1435±12
2,473$15 / $75200K
58
3092
Alibaba · Apache 2.0
1432±9
5,275$0.26 / $1.06N/A
59
28101
Alibaba · Proprietary
1430±14
1,752$0.78 / $3.90262.1K
60
2999
DeepSeek · MIT
1430±12
2,776$0.26 / $0.38163.8K
61
29101
1429±13
2,188$0.30 / $2.501M
62
21118
Alibaba · Apache 2.0
1428±22
711$0.26 / $2.08262.1K
63
31104
DeepSeek · MIT
1427±12
2,394$0.26 / $0.38163.8K
64
3798
Google · Proprietary
1427±8
7,175$0.30 / $2.501M
65
32106
xAI · Proprietary
1427±12
2,766$0.20 / $0.502M
66
15133
MiniMax · Proprietary
1424±35
305$0.30 / $1.20204.8K
67
30116
xAI · Proprietary
1424±17
1,201$0.20 / $0.502M
68
17124
xAI · Proprietary
1424±28
443$3 / $15256K
69
23124
1424±25
523$0.27 / $0.41163.8K
70
34116
Moonshot · Modified MIT
1423±14
1,783$0.60 / $2.50131.1K
71
29122
DeepSeek · MIT
1423±21
786$1.23 / $4.94N/A
72
30120
DeepSeek · MIT
1422±18
1,019$1.23 / $4.94N/A
73
37114
xAI · Proprietary
1421±12
2,718$3 / $15256K
74
37116
Mistral · Apache 2.0
1421±12
2,535$0.50 / $1.50N/A
75
37119
xAI · Proprietary
1420±14
1,890$3 / $15131.1K
76
44112
Mistral · Proprietary
1419±9
5,032$2.70 / $8.1032K
77
30128
Alibaba · Proprietary
1417±24
575$0.78 / $3.90262.1K
78
36124
MiniMax · Modified MIT
1417±19
1,062$0.12 / $0.99196.6K
79
20142
DeepSeek · MIT
1416±35
273$0.21 / $0.79163.8K
80
36126
DeepSeek · MIT
1415±20
807$0.27 / $0.41163.8K
81
42124
Z.ai · MIT
1415±16
1,504$0.60 / $2.20131.1K
82
46123
Anthropic
Anthropic · Proprietary
1413±12
2,703$3 / $151M
83
43124
DeepSeek · MIT
1412±16
1,394$0.45 / $2.15163.8K
84
45124
Alibaba · Apache 2.0
1412±16
1,438$0.09 / $1.10262.1K
85
27152
Tencent
Tencent · Proprietary
1410±34
272N/AN/A
86
54124
DeepSeek · MIT
1409±11
2,963$3 / $4.5032.8K
87
54124
Mistral · Proprietary
1409±13
2,156$0.40 / $2131.1K
88
54125
Anthropic
1408±13
2,289$3 / $151M
89
43135
Alibaba · Apache 2.0
1407±22
723$0.16 / $1.30262.1K
90
52132
OpenAI · Proprietary
1406±16
1,454$15 / $60200K
91
59125
Anthropic
Anthropic · Proprietary
1406±10
3,922$1 / $5200K
92
45137
Arcee AI · Apache 2.0
1405±22
722N/AN/A
93
57128
Alibaba · Apache 2.0
1405±12
2,587$0.46 / $1.82131.1K
94
30160
OpenAI · Proprietary
1403±37
278$0.20 / $1.25400K
95
51139
1402±20
863$0.09 / $0.29262.1K
96
46151
Alibaba · Apache 2.0
1401±25
521$0.26 / $2.60131.1K
97
34160
1401±36
262N/AN/A
98
29164
Z.ai · MIT
1401±42
203$0.30 / $0.90131.1K
99
56138
MiniMax · MIT
1400±18
1,196$0.27 / $0.95196.6K
100
63134
Anthropic
1400±12
2,525$3 / $15200K
101
61136
Alibaba · Apache 2.0
1400±15
1,599$0.40 / $1.60262.1K
102
63133
OpenAI · Proprietary
1400±12
2,787$1.10 / $4.40200K
103
65133
1399±11
3,186$0.10 / $0.401M
104
63134
OpenAI · Proprietary
1399±12
2,491$0.40 / $1.601M
105
59139
Microsoft AI · Proprietary
1399±17
1,195N/AN/A
106
59144
DeepSeek · MIT
1398±18
1,097$0.70 / $2.5064K
107
61145
Stepfun
StepFun · Apache 2.0
1397±17
1,138$0.10 / $0.30262.1K
108
66135
Anthropic
Anthropic · Proprietary
1397±12
2,511$3 / $15200K
109
54154
Alibaba · Apache 2.0
1397±23
662$0.20 / $1.56262.1K
110
64137
1397±14
1,910$0.09 / $0.29262.1K
111
37163
1397±36
254N/AN/A
112
70151
OpenAI · Proprietary
1392±15
1,726$0.25 / $2400K
113
71149
OpenAI · Proprietary
1392±14
1,945$15 / $60N/A
114
63158
Meituan · MIT
1391±21
783$0.20 / $0.80131.1K
115
63162
Alibaba · Apache 2.0
1389±24
549$0.15 / $1.50131.1K
116
75156
Alibaba · Proprietary
1385±14
1,872N/AN/A
117
74158
DeepSeek · DeepSeek
1385±16
1,312$1.14 / $4.56N/A
118
88154
Anthropic
Anthropic · Proprietary
1383±9
5,544$6 / $30200K
119
73162
Z.ai · MIT
1383±20
832$0.06 / $0.40202.8K
120
73164
Tencent
Tencent · Proprietary
1382±21
744N/AN/A
121
86158
1382±13
2,112$0.10 / $0.401M
122
88158
Google · Gemma
1381±12
2,736$0.08 / $0.16131.1K
123
83160
Alibaba · Apache 2.0
1380±15
1,503$0.09 / $0.30262.1K
124
65184
Zhipu · Proprietary
1380±30
367N/AN/A
125
88159
Google · Proprietary
1380±12
2,597$0.10 / $0.401M
126
86162
1380±15
1,435$0.07 / $0.301M
127
55200
Google · Gemma
1379±39
217$0.04 / $0.13131.1K
128
70186
Alibaba · Proprietary
1378±28
392$0.40 / $1.20131.1K
129
85164
xAI · Proprietary
1378±17
1,186$0.30 / $0.50131.1K
130
88162
Google · Proprietary
1377±14
2,962N/AN/A
131
94160
Cohere
Cohere · CC-BY-NC-4.0
1376±10
3,508$2.50 / $10256K
132
100162
OpenAI · Proprietary
1373±10
6,743$5 / $15128K
133
96169
Z.ai · MIT
1371±14
1,950$0.13 / $0.85131.1K
134
72205
Z.ai · MIT
1370±34
278$0.60 / $1.8065.5K
135
99169
Meta
Meta · Llama 3.1 Community
1370±13
2,330$4 / $432.8K
136
102165
Meta
Meta · Llama 3.1 Community
1370±11
3,383$4 / $432.8K
137
66206
Nvidia · NVIDIA Open Model
1368±40
219N/AN/A
138
89190
Alibaba · Proprietary
1368±22
687N/AN/A
139
105171
Google · Proprietary
1367±11
3,342$3.50 / $10.502.1M
140
97185
Mistral · Apache 2.0
1367±17
1,175$0.10 / $0.3032K
141
103184
01.AI
01 AI · Proprietary
1366±15
1,697N/AN/A
142
105184
1365±14
1,848N/AN/A
143
106179
MiniMax · Apache 2.0
1365±12
2,433$0.40 / $2.201M
144
109176
xAI · Proprietary
1364±11
3,813$2 / $10131.1K
145
105185
Alibaba · Apache 2.0
1364±14
1,741$0.46 / $1.82131.1K
146
105202
Alibaba · Apache 2.0
1359±20
871$0.10 / $0.78131.1K
147
106198
OpenAI · Proprietary
1359±18
1,023$1.10 / $4.40200K
148
108205
Ai2 · Apache 2.0
1356±20
917$0.20 / $0.6065.5K
149
112201
xAI · Proprietary
1355±15
1,517$0.30 / $0.50131.1K
150
121195
Anthropic
Anthropic · Proprietary
1354±11
4,818$6 / $30200K
151
103212
MiniMax · Apache 2.0
1353±28
446$0.26 / $1196.6K
152
102212
OpenAI · Proprietary
1353±29
382$0.10 / $0.401M
153
92222
1351±37
237$0.10 / $0.40131.1K
154
127197
Anthropic
Anthropic · Proprietary
1351±10
4,282$0.80 / $4200K
155
121205
Zhipu AI · Proprietary
1350±15
1,723$0.44 / $1.76204.8K
156
126204
OpenAI · Proprietary
1350±12
2,674$2.50 / $10128K
157
130200
Anthropic
Anthropic · Proprietary
1349±9
11,095$15 / $75200K
158
109217
Ant Group · MIT
1348±27
439N/AN/A
159
131205
OpenAI · Proprietary
1347±11
3,866$0.15 / $0.60128K
160
104224
Stepfun
StepFun · Proprietary
1347±33
278N/AN/A
161
131206
OpenAI · Apache 2.0
1344±14
1,951$0.04 / $0.19131.1K
162
134206
Meta
Meta · Llama-3.3
1343±11
3,177$0.10 / $0.32131.1K
163
133206
1343±14
2,008$0.40 / $0.708.2K
164
134206
OpenAI · Proprietary
1343±12
3,138$1.10 / $4.40N/A
165
102229
1343±39
212N/AN/A
166
134206
1342±12
2,638$0.63 / $1.80131.1K
167
111228
Tencent
Tencent · Proprietary
1340±34
288N/AN/A
168
136207
Mistral · Mistral Research
1340±12
2,735$2 / $6131.1K
169
142206
OpenAI · Proprietary
1339±10
3,649$1.10 / $4.40200K
170
117227
Stepfun
StepFun · Apache 2.0
1339±28
418$0.57 / $1.4265.5K
171
141206
OpenAI · Proprietary
1339±11
5,381$10 / $30128K
172
136214
Alibaba · Apache 2.0
1337±15
1,643$0.15 / $0.58131.1K
173
111231
Google · Gemma
1337±36
245$0.04 / $0.08131.1K
174
112231
Tencent
Tencent · Proprietary
1335±36
252N/AN/A
175
143216
Google · Proprietary
1333±12
4,795$3.50 / $10.502.1M
176
116236
1332±36
230N/AN/A
177
136225
NexusFlow · CC-BY-NC-4.0
1332±19
1,008N/AN/A
178
142221
DeepSeek · DeepSeek
1331±15
1,518N/AN/A
179
143219
Alibaba · Qwen
1331±13
2,386$1.20 / $1.20N/A
180
136227
1330±21
821N/AN/A
181
139227
Amazon · Proprietary
1330±20
893$0.30 / $2.501M
182
131231
Reka AI · Proprietary
1329±29
371N/AN/A
183
136228
Stepfun
StepFun · Proprietary
1329±23
661N/AN/A
184
146220
Meta
Meta · Llama 3.1 Community
1329±12
3,177$0.40 / $0.40131.1K
185
149220
OpenAI · Proprietary
1328±12
5,037$10 / $30128K
186
148221
xAI · Proprietary
1328±12
3,012$2 / $10131.1K
187
135230
Princeton · MIT
1328±25
543$0.03 / $0.098.2K
188
146223
Google · Proprietary
1327±13
2,160$0.07 / $0.301M
189
133233
Prime Intellect · MIT
1327±30
399$0.20 / $1.10131.1K
190
134231
AI21 Labs · Jamba Open
1327±27
448$2 / $8256K
191
144227
NexusFlow · NexusFlow
1327±16
1,443N/AN/A
192
134233
DeepSeek · DeepSeek
1327±30
375N/AN/A
193
143227
Alibaba · Qwen
1327±18
1,085$1.60 / $6.4032.8K
194
145227
Mistral · MRL
1326±15
1,593$2 / $6131.1K
195
134231
OpenAI · Proprietary
1326±27
476$0.05 / $0.40400K
196
135231
1326±27
489$1.20 / $1.20131.1K
197
144227
Amazon · Proprietary
1326±16
1,296$0.80 / $3.20300K
198
142230
OpenAI · Apache 2.0
1326±23
700$0.03 / $0.11131.1K
199
131237
Alibaba · Apache 2.0
1325±33
285$0.08 / $0.2441K
200
142231
Alibaba · Proprietary
1325±24
588N/AN/A
201
151227
Alibaba · Apache 2.0
1323±14
1,782$0.08 / $0.2841K
202
150228
Google · Gemma
1323±16
1,421$0.02 / $0.0432.8K
203
143234
Cohere
Cohere · CC-BY-NC-4.0
1320±23
592$2.50 / $10128K
204
154232
Nvidia · NVIDIA Open Model
1316±18
1,177N/AN/A
205
164229
OpenAI · Proprietary
1316±11
5,572$10 / $30128K
206
164230
Cohere
Cohere · CC-BY-NC-4.0
1314±12
4,403$2.50 / $10128K
207
150241
Zhipu AI · Proprietary
1314±25
556N/AN/A
208
167230
Google · Gemma license
1312±10
4,458$0.65 / $0.658.2K
209
143246
Alibaba · Apache 2.0
1310±34
273$0.87 / $0.8732K
210
168236
1308±13
2,167$0.10 / $0.3032K
211
169236
Google · Proprietary
1307±12
3,784$0.07 / $0.301M
212
166241
Nvidia · NVIDIA Open Model
1306±18
1,202$0.06 / $0.24262.1K
213
170237
Anthropic
Anthropic · Proprietary
1306±12
6,062$3 / $15200K
214
163244
Mistral · Proprietary
1305±22
860$2 / $540K
215
164245
Cohere
Cohere · CC-BY-NC-4.0
1303±24
569$0.15 / $0.60128K
216
177237
Meta
Meta · Llama 3 Community
1302±11
8,328$0.51 / $0.748.2K
217
176244
Cohere
Cohere · CC-BY-NC-4.0
1300±14
1,742N/AN/A
218
174244
Microsoft · MIT
1299±17
1,341$0.07 / $0.1416.4K
219
167246
Ai2 · Apache 2.0
1298±24
633$0.15 / $0.5065.5K
220
178244
OpenAI · Proprietary
1298±14
2,897$30 / $608.2K
221
166250
Ai2 · Apache 2.0
1295±29
432$0.15 / $0.5065.5K
222
186245
Google · Proprietary
1294±13
2,128$0.07 / $0.301M
223
164251
Tencent
Tencent · Proprietary
1294±31
397N/AN/A
224
164255
IBM · Apache 2.0
1292±35
327N/AN/A
225
169251
Ant Group · MIT
1290±28
448N/AN/A
226
178251
AI21 Labs · Jamba Open
1287±25
531$0.20 / $0.40256K
227
203246
Anthropic
Anthropic · Proprietary
1287±11
6,799$0.25 / $1.25200K
228
172255
Reka AI · Proprietary
1287±30
414N/AN/A
229
205246
Google · Gemma license
1286±11
3,243$0.03 / $0.098.2K
230
195250
Amazon · Proprietary
1284±18
1,079$0.06 / $0.24300K
231
206248
Cohere
Cohere · CC-BY-NC-4.0
1283±14
3,073$0.15 / $0.60128K
232
191251
Reka AI · Proprietary
1283±21
876N/AN/A
233
202255
DeepSeek · DeepSeek License
1278±20
888$0.14 / $0.28128K
234
212250
OpenAI · Proprietary
1277±12
4,695$30 / $608.2K
235
212251
Alibaba · Qianwen LICENSE
1276±14
2,262$0.90 / $0.9032.8K
236
206255
Mistral · Apache 2.0
1276±21
869$0.05 / $0.0832.8K
237
175263
Ai2 · Apache-2.0
1274±41
202$0.05 / $0.20128K
238
214254
Mistral · Proprietary
1272±13
3,306$4 / $1232K
239
214255
Alibaba · Qianwen LICENSE
1271±17
1,506N/AN/A
240
189262
Mistral · MRL
1271±34
324$0.10 / $0.10131.1K
241
212259
Google · Proprietary
1268±21
970$0.35 / $1.0532.8K
242
214259
Amazon · Proprietary
1267±19
1,082$0.04 / $0.14128K
243
212260
Cohere
Cohere · CC-BY-NC-4.0
1266±25
551N/AN/A
244
218259
Reka AI · Proprietary
1264±18
1,350N/AN/A
245
220259
Alibaba · Qianwen LICENSE
1262±15
2,091N/AN/A
246
224259
Mistral · Apache 2.0
1258±14
2,798$0.90 / $0.9065.5K
247
224262
Mistral · Proprietary
1255±16
1,811$2.70 / $8.1032K
248
225260
OpenAI · Proprietary
1254±13
3,573$0.50 / $1.5016.4K
249
225262
01.AI
01 AI · Apache-2.0
1252±16
1,510N/AN/A
250
209283
IBM · Apache 2.0
1252±42
215N/AN/A
251
233262
Meta
Meta · Llama 3 Community
1247±11
5,578$0.03 / $0.048.2K
252
234263
Meta
Meta · Llama 3.1 Community
1246±12
2,882$0.02 / $0.0516.4K
253
233285
OpenChat · Apache-2.0
1233±28
467$0.20 / $0.20N/A
254
239282
Alibaba · Qianwen LICENSE
1231±18
1,227N/AN/A
255
246278
Mistral · Apache 2.0
1227±13
3,953$0.63 / $0.6332K
256
228290
HuggingFace · Apache 2.0
1226±38
240N/AN/A
257
233289
Google · Proprietary
1226±34
309$0.35 / $1.0532.8K
258
244285
01.AI
01 AI · Yi License
1223±22
857$0.90 / $0.904.1K
259
250283
Google · Gemma license
1221±13
2,655N/AN/A
260
239289
Microsoft · Llama 2 Community
1221±29
434N/AN/A
261
239289
AllenAI/UW · AI2 ImpACT Low-risk
1220±31
377N/AN/A
262
239295
NousResearch · Apache-2.0
1214±36
275$0.17 / $0.17N/A
263
252285
Microsoft · MIT
1214±17
1,474$0.17 / $0.68N/A
264
252287
Google · Gemma license
1212±17
1,416$0.03 / $0.098.2K
265
252287
Databricks · DBRX LICENSE
1212±17
1,748$0.60 / $0.6032.8K
266
252290
OpenAI · Proprietary
1209±23
944$1 / $216.4K
267
252290
Nexusflow · Apache-2.0
1209±21
878N/AN/A
268
252291
OpenChat · Apache-2.0
1208±24
637N/AN/A
269
252290
Alibaba · Qianwen LICENSE
1208±20
1,037$0.30 / $0.30N/A
270
252295
UC Berkeley · CC-BY-NC-4.0
1205±27
504N/AN/A
271
246298
DeepSeek · DeepSeek License
1204±35
300N/AN/A
272
252291
Snowflake · Apache 2.0
1201±18
1,535N/AN/A
273
252298
Microsoft · Llama 2 Community
1196±32
365$0.30 / $0.30N/A
274
253295
Microsoft · MIT
1196±18
1,187$0.15 / $0.60N/A
275
252299
IBM · Apache 2.0
1195±34
428N/AN/A
276
252298
InternLM · Other
1194±24
685$0 / $032.8K
277
254298
LMSYS · Non-commercial
1192±19
1,246$0 / $02K
278
256296
Meta
Meta · Llama 2 Community
1192±16
2,073$0.70 / $2.804.1K
279
252298
Meta
Meta · Llama 3.2
1190±28
506$0.05 / $0.3480K
280
253298
HuggingFace · MIT
1188±26
621$0.15 / $0.1516.4K
281
256298
Mistral · Apache-2.0
1186±21
976$0.20 / $0.2032.8K
282
252302
Upstage AI · CC-BY-NC-4.0
1185±40
219$0.30 / $0.30N/A
283
253301
IBM · Apache 2.0
1182±32
435N/AN/A
284
252305
Alibaba · Qianwen LICENSE
1180±41
230$0.20 / $0.20N/A
285
253305
Alibaba · Qianwen LICENSE
1175±38
274N/AN/A
286
259300
LMSYS · Llama 2 Community
1174±22
899$0.30 / $0.30N/A
287
261306
Google · Proprietary
1161±33
428$0.50 / $0.5025.8K
288
261306
Meta
Meta · Llama 2 Community
1160±32
383$0.35 / $1.4016.4K
289
264306
Google · Gemma license
1160±29
462$0.05 / $0.088.2K
290
273306
Meta
Meta · Llama 2 Community
1157±21
1,004$0.25 / $0.254.1K
291
274305
Microsoft · MIT
1156±19
1,126$0.13 / $0.52N/A
292
270306
1156±25
706$0.13 / $0.524.1K
293
259307
Alibaba · Apache 2.0
1155±43
214$0.15 / $0.58131.1K
294
270307
Mistral · Apache 2.0
1153±30
487$0.07 / $0.284.1K
295
270307
Meta
Meta · Llama 3.2
1151±30
489$0.03 / $0.2060K
296
268307
LMSYS · Llama 2 Community
1149±35
305$0.20 / $0.20N/A
297
274307
Alibaba · Qianwen LICENSE
1143±32
390$0.10 / $0.10N/A
298
270308
Google · Gemma license
1142±38
273$0.10 / $0.10N/A
299
282307
Meta
Meta · Llama 2 Community
1138±23
760$0.15 / $0.154.1K
300
284308
Google · Gemma license
1121±28
578N/AN/A
301
285308
Microsoft · MIT
1120±23
1,033$0.13 / $0.52N/A
302
283309
Together AI · Apache 2.0
1116±36
309$0.20 / $0.20N/A
303
281309
RWKV · Apache 2.0
1113±48
190N/AN/A
304
285309
Ai2 · Apache-2.0
1106±36
301$0.20 / $0.20N/A
305
285309
Stanford · Non-commercial
1098±44
230N/AN/A
306
288309
Tsinghua · Apache-2.0
1095±41
268N/AN/A
307
293310
UC Berkeley · Non-commercial
1083±40
248N/AN/A
308
299310
OpenAssistant · Apache 2.0
1069±41
266N/AN/A
309
302310
LMSYS · Apache 2.0
1034±46
184N/AN/A
310
307310
Tsinghua · Non-commercial
996±48
195N/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)

Battle Count for Each Combination of Models (without Ties)

Confidence Intervals on Model Strength (via Bootstrapping)