Text Arena📝Instruction Following

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

May 17, 2026
2,010,887 votes
360 models
Rank Spread
1
13
Anthropic
Anthropic · Proprietary
1517±7
7,644$5 / $251M
2
14
Anthropic
Anthropic · Proprietary
1506±10
4,087$5 / $251M
3
14
Anthropic
Anthropic · Proprietary
1502±7
8,610$5 / $251M
4
211
Anthropic
Anthropic · Proprietary
1495±9
4,393$5 / $251M
5
415
Google · Proprietary
1485±7
10,116$2 / $121M
6
415
Anthropic
1485±7
9,456$5 / $25200K
7
421
OpenAI · Proprietary
1479±11
3,340$5 / $301.1M
8
421
OpenAI · Proprietary
1479±11
3,134$5 / $301.1M
9
420
OpenAI · Proprietary
1478±8
6,398$2.50 / $151.1M
10
424
Xiaomi · MIT
1478±11
2,950$1 / $31M
11
521
Anthropic
Anthropic · Proprietary
1477±8
6,156$3 / $151M
12
520
Anthropic
Anthropic · Proprietary
1475±6
16,323$5 / $25200K
13
521
Google · Proprietary
1474±6
11,192$2 / $121M
14
534
Google · Proprietary
1471±13
1,869$1.50 / $91M
15
439
Alibaba · Proprietary
1470±17
1,292N/AN/A
16
732
OpenAI · Proprietary
1468±8
6,816$2.50 / $151.1M
17
733
Alibaba · Proprietary
1468±8
5,219N/AN/A
18
734
Z.ai · MIT
1467±10
3,761$1.40 / $4.40202.8K
19
739
Meta
Meta · Proprietary
1463±10
3,389N/AN/A
20
1334
Anthropic
1463±5
19,532$3 / $15200K
21
1334
Anthropic
Anthropic · Proprietary
1462±5
18,975$3 / $15200K
22
1438
Anthropic
1460±6
12,968$15 / $75200K
23
741
Baidu · Proprietary
1459±12
2,617N/AN/A
24
941
OpenAI · Proprietary
1459±10
3,649$5 / $301.1M
25
1440
OpenAI · Proprietary
1459±7
8,427$1.75 / $14128K
26
1440
Google · Proprietary
1458±7
8,098$0.50 / $31M
27
1346
Moonshot · Modified MIT
1456±10
3,160$0.95 / $4262.1K
28
1540
Anthropic
Anthropic · Proprietary
1455±5
20,325$15 / $75200K
29
1446
xAI · Proprietary
1453±8
6,515N/AN/A
30
1449
1453±11
3,184$0.43 / $0.871M
31
1455
Google · Apache 2.0
1452±14
1,632$0.14 / $0.40262.1K
32
1648
1450±8
6,609$2 / $62M
33
1451
DeepSeek · MIT
1450±10
3,371$0.43 / $0.871M
34
2049
OpenAI · Proprietary
1449±7
10,759$1.25 / $10400K
35
2048
1449±6
13,090$0.50 / $31M
36
2051
Xiaomi · Proprietary
1447±8
5,836$1 / $31M
37
2053
Z.ai · MIT
1447±8
6,240$1 / $3.20202.8K
38
2153
1446±8
6,606$2 / $62M
39
1465
Alibaba · Proprietary
1445±15
1,336$1.04 / $6.24262.1K
40
2657
Anthropic
Anthropic · Proprietary
1443±7
9,141$15 / $75200K
41
3057
Google · Proprietary
1440±4
31,911$1.25 / $101M
42
2862
Moonshot · Modified MIT
1440±7
8,693$0.60 / $3N/A
43
2865
OpenAI · Proprietary
1439±8
5,827$0.75 / $4.50400K
44
2374
Google · Apache 2.0
1438±14
1,583N/AN/A
45
3067
OpenAI · Proprietary
1437±8
5,501$75 / $150128K
46
2870
1436±10
3,278$0.11 / $0.221M
47
2869
Alibaba · Proprietary
1436±10
3,879$0.33 / $1.951M
48
2876
Moonshot · Modified MIT
1435±12
2,237$0.40 / $1.90262.1K
49
3670
Bytedance
Bytedance · Proprietary
1432±7
9,049N/AN/A
50
3673
OpenAI · Proprietary
1432±7
8,073$1.75 / $14128K
51
3279
Xiaomi · MIT
1432±11
3,120$0.40 / $21M
52
3971
xAI · Proprietary
1431±5
16,073N/AN/A
53
3480
DeepSeek · MIT
1431±10
3,269$0.11 / $0.221M
54
4172
xAI · Proprietary
1431±5
16,917N/AN/A
55
4177
Alibaba · Apache 2.0
1429±7
7,668$0.39 / $2.34262.1K
56
4177
Baidu · Proprietary
1428±7
8,991N/AN/A
57
3885
Z.ai · MIT
1428±10
3,214$0.40 / $1.75202.8K
58
4275
OpenAI · Proprietary
1428±4
22,798$5 / $15128K
59
4177
OpenAI · Proprietary
1428±6
11,863$1.25 / $10400K
60
3886
xAI · Proprietary
1428±11
2,958$1.25 / $2.501M
61
4181
Alibaba · Proprietary
1427±7
7,283$0.78 / $3.90262.1K
62
4281
OpenAI · Proprietary
1426±6
12,196$1.75 / $14400K
63
4486
OpenAI · Proprietary
1423±6
11,500$1.75 / $14400K
64
34109
1420±20
865$0.27 / $0.95163.8K
65
4297
Baidu · Proprietary
1420±11
2,627N/AN/A
66
4989
DeepSeek · MIT
1420±6
12,079$0.25 / $0.38131.1K
67
4889
DeepSeek · MIT
1420±6
10,433$0.25 / $0.38131.1K
68
4499
DeepSeek · MIT
1419±11
2,862$1.23 / $4.94N/A
69
5292
Moonshot · Modified MIT
1418±5
15,805$1.15 / $8262.1K
70
39111
1418±19
931N/AN/A
71
5197
OpenAI · Proprietary
1417±7
8,143$1.25 / $10128K
72
45103
1416±12
2,543$0.27 / $0.41163.8K
73
45102
DeepSeek · MIT
1416±10
3,310$0.27 / $0.41163.8K
74
5994
Alibaba · Apache 2.0
1416±4
24,988$0.26 / $1.06N/A
75
5497
Z.ai · MIT
1416±6
10,007$0.43 / $1.74202.8K
76
46104
Alibaba · Proprietary
1415±11
2,638$0.78 / $3.90262.1K
77
5799
Anthropic
1415±7
8,554$3 / $151M
78
53102
Meituan · Proprietary
1414±8
5,078N/AN/A
79
6197
Anthropic
Anthropic · Proprietary
1414±5
19,858$1 / $5200K
80
50107
Alibaba · Apache 2.0
1414±11
2,927$0.20 / $0.88262.1K
81
61102
Anthropic
Anthropic · Proprietary
1413±6
10,702$15 / $75200K
82
61103
Google · Proprietary
1412±7
8,278$0.25 / $1.501M
83
62107
OpenAI · Proprietary
1410±7
8,265$1.25 / $10400K
84
64106
Anthropic
1409±6
10,146$3 / $15200K
85
57119
Tencent
Tencent · tencent-hunyuan-community
1407±14
1,596$0.29 / $1.17262.1K
86
67110
OpenAI · Proprietary
1406±6
10,246$15 / $60200K
87
66111
Alibaba · Apache 2.0
1406±7
6,925$0.26 / $2.08262.1K
88
67111
xAI · Proprietary
1406±7
9,673$3 / $15131.1K
89
66113
Z.ai · MIT
1405±8
6,165$0.60 / $2.20131.1K
90
68111
Mistral · Apache 2.0
1405±6
11,472$0.50 / $1.50N/A
91
66119
DeepSeek · MIT
1403±10
3,695$1.23 / $4.94N/A
92
72115
OpenAI · Proprietary
1402±6
13,282$2 / $81M
93
58131
1402±19
925N/AN/A
94
77113
Google · Proprietary
1402±4
31,492$0.30 / $2.501M
95
72117
1402±7
9,152$0.30 / $2.501M
96
74116
OpenAI · Proprietary
1402±6
15,515$2 / $8200K
97
74116
xAI · Proprietary
1401±5
14,900$0.20 / $0.502M
98
68120
MiniMax · Modified MIT
1401±9
4,981$0.28 / $1.20204.8K
99
64130
Baidu · Proprietary
1400±16
1,312N/AN/A
100
64128
xAI · Proprietary
1400±14
1,730$3 / $15256K
101
74120
Alibaba · Apache 2.0
1400±7
6,710$0.20 / $1.56262.1K
102
81118
Mistral · Proprietary
1398±4
24,467$2.70 / $8.1032K
103
80121
xAI · Proprietary
1397±6
10,814$3 / $15256K
104
61138
Tencent
Tencent · Proprietary
1397±22
626N/AN/A
105
80125
DeepSeek · MIT
1396±7
6,426$0.70 / $2.50163.8K
106
68136
DeepSeek · MIT
1393±18
1,030$0.27 / $0.95163.8K
107
85128
Anthropic
Anthropic · Proprietary
1393±7
9,984$3 / $151M
108
83131
DeepSeek · MIT
1392±9
4,049$0.50 / $2.15163.8K
109
89131
Alibaba · Apache 2.0
1391±7
7,134$0.14 / $1262.1K
110
83133
Meituan · MIT
1390±11
2,953$0.20 / $0.80131.1K
111
83134
Moonshot · Modified MIT
1389±11
2,887$0.60 / $2.50262.1K
112
91133
OpenAI · Proprietary
1389±8
5,672$0.20 / $1.25400K
113
94131
MiniMax · Modified MIT
1389±7
8,564$0.15 / $1.15204.8K
114
91133
xAI · Proprietary
1388±8
5,310$0.20 / $0.502M
115
95134
MiniMax · MIT
1386±9
4,473$0.29 / $0.95204.8K
116
89141
Alibaba · Apache 2.0
1386±12
2,105$0.15 / $1.50262.1K
117
79149
1385±19
922N/AN/A
118
100134
Stepfun
StepFun · Apache 2.0
1385±7
8,120$0.09 / $0.30262.1K
119
98134
Alibaba · Apache 2.0
1385±8
6,228$0.40 / $1.60262.1K
120
101134
1384±6
11,632$0.10 / $0.30262.1K
121
92143
Alibaba · Apache 2.0
1384±12
2,130$0.26 / $2.60131.1K
122
101134
Anthropic
Anthropic · Proprietary
1383±6
12,321$3 / $15200K
123
102138
Alibaba · Apache 2.0
1381±7
9,277$0.46 / $1.82131.1K
124
102141
OpenAI · Proprietary
1380±7
12,782$15 / $60N/A
125
101147
1380±11
2,977$0.10 / $0.30262.1K
126
102143
Alibaba · Apache 2.0
1379±8
6,305$0.09 / $1.10262.1K
127
104145
Alibaba · Proprietary
1378±7
6,774N/AN/A
128
105142
DeepSeek · MIT
1378±6
12,391$3 / $4.5032.8K
129
104145
Moonshot · Modified MIT
1378±8
6,753$0.60 / $2.50131.1K
130
96156
Tencent
Tencent · Proprietary
1376±17
1,115N/AN/A
131
109149
OpenAI · Proprietary
1374±8
6,915$0.25 / $2400K
132
112149
OpenAI · Proprietary
1372±6
10,068$0.40 / $1.601M
133
109151
Microsoft AI · Proprietary
1372±9
4,212N/AN/A
134
119149
Anthropic
Anthropic · Proprietary
1371±4
31,270$3 / $15200K
135
118152
1369±7
8,105$0.10 / $0.401M
136
101167
Z.ai · MIT
1369±22
733$0.30 / $0.90131.1K
137
118154
Arcee AI · Apache 2.0
1368±7
7,185$0.15 / $0.45131K
138
121152
OpenAI · Proprietary
1367±6
11,895$1.10 / $4.40200K
139
119156
Alibaba · Apache 2.0
1367±8
5,969$0.09 / $0.30262.1K
140
121156
Mistral · Proprietary
1366±7
7,942$0.40 / $2131.1K
141
121157
OpenAI · Proprietary
1366±8
6,681$1.10 / $4.40200K
142
123157
1365±7
6,719N/AN/A
143
126155
1365±6
12,892$0.10 / $0.401M
144
128158
Z.ai · MIT
1362±7
8,118$0.13 / $0.85131.1K
145
126159
xAI · Proprietary
1362±9
4,225$0.25 / $1.27N/A
146
128159
Arcee AI · Apache 2.0
1361±9
5,134$0.22 / $0.85262.1K
147
129164
Alibaba · Apache 2.0
1359±10
3,517$0.10 / $0.78262.1K
148
134161
Alibaba · Proprietary
1357±6
10,959N/AN/A
149
133164
Alibaba · Apache 2.0
1357±8
6,194$0.46 / $1.82131.1K
150
136169
xAI · Proprietary
1353±8
5,546$0.30 / $0.50131.1K
151
133175
Tencent
Tencent · Proprietary
1353±12
2,427N/AN/A
152
136176
Z.ai · MIT
1351±10
3,181$0.06 / $0.40202.8K
153
124189
Nvidia · Nvidia Open Model
1350±22
660$0.60 / $1.80131.1K
154
129183
Tencent
Tencent · Proprietary
1350±18
886N/AN/A
155
141179
1348±11
3,032N/AN/A
156
144173
Google · Proprietary
1348±6
13,633$0.10 / $0.401M
157
137181
Nvidia · NVIDIA Open Model
1347±13
1,940N/AN/A
158
146177
MiniMax · Apache 2.0
1346±7
8,690$0.40 / $2.201M
159
138188
Stepfun
StepFun · Apache 2.0
1345±14
1,641$0.57 / $1.4265.5K
160
147178
Google · Gemma
1343±6
12,526$0.08 / $0.16131.1K
161
147181
DeepSeek · DeepSeek
1343±7
8,606$1.14 / $4.56N/A
162
149177
OpenAI · Proprietary
1343±5
16,955$1.10 / $4.40200K
163
143191
Z.ai · MIT
1342±16
1,306$0.60 / $1.8065.5K
164
150181
Cohere
Cohere · CC-BY-NC-4.0
1341±5
15,482$2.50 / $10256K
165
146191
MiniMax · Apache 2.0
1339±13
1,983$0.26 / $1204.8K
166
149188
Mistral · Apache 2.0
1339±9
4,387$0.10 / $0.3032K
167
151181
Google · Proprietary
1338±5
22,789$3.50 / $10.502.1M
168
153188
Anthropic
Anthropic · Proprietary
1335±5
32,074$3 / $15200K
169
151196
Alibaba · Proprietary
1332±12
2,249$0.40 / $1.20131.1K
170
158191
OpenAI · Proprietary
1332±5
21,478$1.10 / $4.40N/A
171
147207
Alibaba · Apache 2.0
1331±19
858$0.08 / $0.28131.1K
172
158192
1331±6
9,249$0.07 / $0.301M
173
152196
Amazon · Proprietary
1330±10
3,329$0.30 / $2.501M
174
150206
Prime Intellect · MIT
1330±16
1,389$0.20 / $1.10131.1K
175
154207
OpenAI · Proprietary
1326±13
2,029$0.05 / $0.40400K
176
162198
OpenAI · Apache 2.0
1326±7
7,817$0.04 / $0.18131.1K
177
151213
1325±19
803N/AN/A
178
166197
OpenAI · Proprietary
1324±5
43,766$5 / $15128K
179
163201
Alibaba · Apache 2.0
1324±7
7,172$0.50 / $116.4K
180
151217
Inception AI · Proprietary
1322±20
836$0.25 / $0.75128K
181
162208
Ai2 · Apache 2.0
1322±11
3,230$0.20 / $0.6065.5K
182
152217
1322±20
807$0.10 / $0.40131.1K
183
157213
Google · Gemma
1321±16
1,145$0.04 / $0.13131.1K
184
163214
Ant Group · MIT
1318±14
1,793N/AN/A
185
171208
OpenAI · Proprietary
1317±6
18,305$2.50 / $10128K
186
163215
Ant Group · MIT
1317±14
1,852N/AN/A
187
156225
1316±21
720N/AN/A
188
167215
Stepfun
StepFun · Proprietary
1316±13
1,950N/AN/A
189
163218
Tencent
Tencent · Proprietary
1316±16
1,300N/AN/A
190
171210
Google · Proprietary
1315±7
18,524N/AN/A
191
167217
Z.ai · Proprietary
1314±12
2,160N/AN/A
192
170215
DeepSeek · DeepSeek
1314±11
2,970N/AN/A
193
163225
Tencent
Tencent · Proprietary
1313±18
842N/AN/A
194
173213
1313±6
10,494$0.63 / $1.80131.1K
195
175209
Anthropic
Anthropic · Proprietary
1313±5
22,011$0.80 / $4200K
196
175210
Meta
Meta · Llama 3.1 Community
1313±5
23,585$4 / $432.8K
197
175213
Meta
Meta · Llama 3.1 Community
1312±5
16,174$4 / $432.8K
198
176210
Anthropic
Anthropic · Proprietary
1312±5
72,001$15 / $75200K
199
176213
xAI · Proprietary
1311±5
25,659$2 / $10131.1K
200
174215
Alibaba · Apache 2.0
1311±8
6,130$0.09 / $0.45131.1K
201
176214
Google · Proprietary
1310±6
29,835$3.50 / $10.502.1M
202
149247
Ai2 · Apache 2.0
1309±39
217$0.20 / $0.2036.9K
203
176218
01.AI
01 AI · Proprietary
1308±7
10,932N/AN/A
204
171225
Stepfun
StepFun · Proprietary
1308±13
2,095N/AN/A
205
171235
IBM · Apache 2.0
1304±19
1,053$0.05 / $0.10131.1K
206
182225
NexusFlow · NexusFlow
1302±6
10,236N/AN/A
207
185225
OpenAI · Proprietary
1302±6
36,297$10 / $30128K
208
179231
Mistral · Proprietary
1301±11
3,114$2 / $540K
209
181228
Alibaba · Qwen
1301±8
6,919$1.60 / $6.4032.8K
210
177234
OpenAI · Proprietary
1300±12
2,015$0.10 / $0.401M
211
185228
Z.ai · Proprietary
1300±7
10,743$0.44 / $1.76204.8K
212
185228
1300±7
7,482$0.40 / $0.708.2K
213
176237
Ai2 · Apache 2.0
1299±16
1,495$0.15 / $0.5065.5K
214
192229
Mistral · Mistral Research
1298±6
18,321$2 / $6131.1K
215
190235
Alibaba · Proprietary
1295±9
4,234N/AN/A
216
199234
1295±7
8,041$0.10 / $0.3032K
217
201233
OpenAI · Proprietary
1294±6
34,416$10 / $30128K
218
201234
Mistral · MRL
1294±6
10,971$2 / $6131.1K
219
196236
Nvidia · NVIDIA Open Model
1293±9
4,207$0.06 / $0.24262.1K
220
201234
OpenAI · Proprietary
1293±5
26,705$0.15 / $0.60128K
221
201235
Alibaba · Qwen
1292±6
16,363$1.20 / $1.20N/A
222
201235
Meta
Meta · Llama-3.3
1291±5
18,788$0.10 / $0.32131.1K
223
201236
DeepSeek · DeepSeek
1291±7
10,175N/AN/A
224
206237
Google · Proprietary
1289±6
14,561$0.07 / $0.301M
225
206237
OpenAI · Proprietary
1289±6
33,252$10 / $30128K
226
196247
Tencent
Tencent · Proprietary
1286±17
1,215N/AN/A
227
212240
xAI · Proprietary
1283±5
21,131$2 / $10131.1K
228
211244
OpenAI · Proprietary
1282±7
18,087$30 / $608.2K
229
201248
Tencent
Tencent · Proprietary
1281±15
1,329N/AN/A
230
211245
Google · Gemma
1281±9
4,986$0.06 / $0.1232.8K
231
209248
OpenAI · Apache 2.0
1280±12
2,555$0.03 / $0.14131.1K
232
210248
1280±11
2,959$1.20 / $1.20131.1K
233
210250
Ai2 · Apache 2.0
1278±13
2,161$0.15 / $0.5065.5K
234
220248
NexusFlow · CC-BY-NC-4.0
1277±8
7,490N/AN/A
235
225247
Amazon · Proprietary
1276±6
9,525$0.80 / $3.20300K
236
225248
OpenAI · Proprietary
1273±6
29,706$30 / $608.2K
237
226248
Meta
Meta · Llama 3.1 Community
1271±5
21,910$0.40 / $0.40131.1K
238
216257
Ai2 · Llama 3.1
1271±16
1,170N/AN/A
239
206265
Inception AI · Proprietary
1269±26
569$0.25 / $0.75128K
240
227250
Google · Gemma license
1269±5
29,545$0.65 / $0.658.2K
241
222259
Google · Gemma
1267±16
1,233$0.04 / $0.08131.1K
242
225259
IBM · Apache 2.0
1266±16
1,569N/AN/A
243
228254
Anthropic
Anthropic · Proprietary
1265±6
38,802$3 / $15200K
244
226257
AI21 Labs · Jamba Open
1265±11
3,266$2 / $8256K
245
231256
Google · Proprietary
1263±6
23,685$0.07 / $0.301M
246
226258
Alibaba · Apache 2.0
1263±12
2,227$0.87 / $0.8732K
247
228259
Reka AI · Proprietary
1260±10
3,118N/AN/A
248
226263
1260±15
1,484N/AN/A
249
237260
Nvidia · NVIDIA Open Model
1257±8
7,354N/AN/A
250
239259
Meta
Meta · Llama 3 Community
1256±5
56,558$0.51 / $0.748.2K
251
239263
Mistral · Apache 2.0
1255±8
5,485$0.05 / $0.0832.8K
252
237265
Z.ai · Proprietary
1254±10
3,766N/AN/A
253
239266
Cohere
Cohere · CC-BY-NC-4.0
1252±9
4,024$2.50 / $10128K
254
240268
DeepSeek · DeepSeek License
1250±9
5,614$0.14 / $0.28128K
255
239268
Princeton · MIT
1250±10
3,741$0.03 / $0.098.2K
256
243268
Cohere
Cohere · CC-BY-NC-4.0
1248±7
11,265N/AN/A
257
241268
Reka AI · Proprietary
1247±10
3,246N/AN/A
258
244268
Microsoft · MIT
1245±7
9,162$0.07 / $0.1416.4K
259
248268
Amazon · Proprietary
1243±7
7,809$0.06 / $0.24300K
260
249268
Google · Gemma license
1243±5
21,359$0.03 / $0.098.2K
261
240269
Tencent
Tencent · Proprietary
1243±17
1,098N/AN/A
262
249268
Anthropic
Anthropic · Proprietary
1243±5
43,031$0.25 / $1.25200K
263
249268
Alibaba · Qianwen LICENSE
1240±7
14,194$0.90 / $0.9032.8K
264
251268
Cohere
Cohere · CC-BY-NC-4.0
1239±6
28,069$2.50 / $10128K
265
253269
Google · Proprietary
1237±6
14,894$0.07 / $0.301M
266
254269
Mistral · Proprietary
1235±7
21,532$4 / $1232K
267
254269
Cohere
Cohere · CC-BY-NC-4.0
1233±9
4,153$0.15 / $0.60128K
268
251280
Ai2 · Apache-2.0
1228±17
1,063$0.05 / $0.20128K
269
268281
Alibaba · Qianwen LICENSE
1216±8
9,518N/AN/A
270
264285
Google · Proprietary
1215±17
1,897$0.35 / $1.0532.8K
271
268282
Amazon · Proprietary
1214±7
7,716$0.04 / $0.14128K
272
268283
Mistral · Apache 2.0
1213±7
18,515$0.90 / $0.9065.5K
273
268284
OpenAI · Proprietary
1211±6
23,523$0.50 / $1.5016.4K
274
268286
Mistral · MRL
1210±13
1,946$0.10 / $0.10131.1K
275
268285
Alibaba · Qianwen LICENSE
1209±7
13,814N/AN/A
276
268285
Mistral · Proprietary
1208±8
11,466$2.70 / $8.1032K
277
268290
Ai2 · Llama 3.1
1208±16
1,172N/AN/A
278
268288
Google · Proprietary
1206±11
5,876$0.35 / $1.0532.8K
279
268289
Cohere
Cohere · CC-BY-NC-4.0
1203±10
4,006N/AN/A
280
268290
AI21 Labs · Jamba Open
1203±11
3,254$0.20 / $0.40256K
281
269291
Reka AI · Proprietary
1199±10
5,558N/AN/A
282
273291
Cohere
Cohere · CC-BY-NC-4.0
1197±7
19,085$0.15 / $0.60128K
283
272296
OpenAI · Proprietary
1193±12
5,238$1 / $216.4K
284
270300
IBM · Apache 2.0
1191±17
1,258N/AN/A
285
271299
HuggingFace · Apache 2.0
1191±16
1,593N/AN/A
286
277293
Meta
Meta · Llama 3.1 Community
1190±6
19,781$0.02 / $0.05131.1K
287
277293
Meta
Meta · Llama 3 Community
1190±6
37,733$0.04 / $0.048.2K
288
276296
Reka AI · Proprietary
1190±8
9,018N/AN/A
289
278297
01.AI
01 AI · Apache-2.0
1186±8
8,996N/AN/A
290
279297
Databricks · DBRX LICENSE
1184±9
11,274$0.60 / $0.6032.8K
291
281300
Alibaba · Qianwen LICENSE
1182±9
7,653N/AN/A
292
285300
Mistral · Apache 2.0
1178±6
24,974$0.63 / $0.6332K
293
283301
InternLM · Other
1177±10
4,092$0 / $032.8K
294
285301
Microsoft · MIT
1175±7
9,385$0.17 / $0.68N/A
295
283311
IBM · Apache 2.0
1171±16
1,252N/AN/A
296
289303
Google · Gemma license
1170±6
18,240N/AN/A
297
287310
IBM · Apache 2.0
1169±12
2,597N/AN/A
298
285312
AllenAI/UW · AI2 ImpACT Low-risk
1169±15
2,008N/AN/A
299
289310
Alibaba · Qianwen LICENSE
1166±10
6,231$0.30 / $0.30N/A
300
290314
Microsoft · Llama 2 Community
1161±14
2,680N/AN/A
301
293319
DeepSeek · DeepSeek License
1155±17
1,525N/AN/A
302
296316
Google · Gemma license
1153±8
8,852$0.03 / $0.098.2K
303
296316
OpenChat · Apache-2.0
1152±11
4,414N/AN/A
304
296316
Microsoft · MIT
1152±9
6,632$0.15 / $0.60N/A
305
295319
OpenChat · Apache-2.0
1151±14
2,391$0.20 / $0.20N/A
306
295321
NousResearch · Apache-2.0
1150±15
1,577$0.17 / $0.17N/A
307
296318
01.AI
01 AI · Yi License
1150±10
5,099$0.90 / $0.904.1K
308
296317
Snowflake · Apache 2.0
1150±9
11,736N/AN/A
309
296324
Alibaba · Apache 2.0
1147±16
1,329$0.50 / $116.4K
310
298321
Meta
Meta · Llama 3.2
1144±11
3,171$0.05 / $0.34131.1K
311
299321
Nexusflow · Apache-2.0
1144±10
5,765N/AN/A
312
301325
LMSYS · Non-commercial
1137±9
6,983$0 / $02K
313
301328
UC Berkeley · CC-BY-NC-4.0
1134±12
3,316N/AN/A
314
306326
Meta
Meta · Llama 2 Community
1132±8
12,635$0.70 / $2.804.1K
315
300335
MosaicML · CC-BY-NC-SA-4.0
1132±21
718N/AN/A
316
296338
TII · Falcon-180B TII License
1131±29
389N/AN/A
317
304333
IBM · Apache 2.0
1129±12
2,698N/AN/A
318
300338
Cognitive Computations · Apache-2.0
1126±24
497$0.50 / $0.5016.4K
319
305337
Nvidia · Llama 2 Community
1122±18
1,076N/AN/A
320
311335
1122±10
4,431$0.13 / $0.524.1K
321
308336
Alibaba · Qianwen LICENSE
1122±14
1,715$0.20 / $0.20N/A
322
308337
Microsoft · Llama 2 Community
1121±14
2,003$0.30 / $0.30N/A
323
312335
Mistral · Apache-2.0
1121±9
6,659$0.20 / $0.2032.8K
324
311339
Alibaba · Qianwen LICENSE
1115±16
1,470N/AN/A
325
314337
LMSYS · Llama 2 Community
1114±10
5,665$0.30 / $0.30N/A
326
311341
Upstage AI · CC-BY-NC-4.0
1113±19
1,188$0.30 / $0.30N/A
327
313339
Google · Proprietary
1113±14
2,536$0.50 / $0.5025.8K
328
315338
Microsoft · MIT
1111±9
7,636$0.13 / $0.52N/A
329
315339
Meta
Meta · Llama 2 Community
1108±9
6,097$0.25 / $0.254.1K
330
315341
NousResearch · Apache-2.0
1106±16
1,421$0.90 / $0.90N/A
331
316341
Google · Gemma license
1101±13
2,835$0.05 / $0.088.2K
332
316341
Meta
Meta · Llama 2 Community
1101±13
2,294$0.35 / $1.4016.4K
333
315344
HuggingFace · Apache 2.0
1101±21
859N/AN/A
334
320342
Microsoft · MIT
1097±10
7,368$0.13 / $0.52N/A
335
319342
Google · Gemma license
1097±11
3,877N/AN/A
336
315346
HuggingFace · MIT
1097±24
534N/AN/A
337
313346
Meta
Meta · Llama 2 Community
1095±30
358$0.70 / $2.8016.4K
338
323346
Together AI · Apache 2.0
1088±15
1,660$0.20 / $0.20N/A
339
326346
HuggingFace · MIT
1087±13
3,094$0.15 / $0.1516.4K
340
329346
Meta
Meta · Llama 3.2
1084±11
3,248$0.03 / $0.20131.1K
341
329346
Mistral · Apache 2.0
1084±14
2,768$0.07 / $0.284.1K
342
333347
LMSYS · Llama 2 Community
1073±14
2,020$0.20 / $0.20N/A
343
336347
Meta
Meta · Llama 2 Community
1067±10
4,541$0.15 / $0.154.1K
344
335348
Google · Gemma license
1067±16
1,522$0.10 / $0.10N/A
345
336347
Alibaba · Qianwen LICENSE
1066±13
2,636$0.10 / $0.10N/A
346
335349
UW · Non-commercial
1063±21
777N/AN/A
347
342352
Nomic AI · Non-commercial
1034±25
483N/AN/A
348
345352
Tsinghua · Apache-2.0
1033±18
1,321N/AN/A
349
346352
Ai2 · Apache-2.0
1028±16
1,908$0.20 / $0.20N/A
350
347352
UC Berkeley · Non-commercial
1023±15
1,913N/AN/A
351
347352
Stanford · Non-commercial
1019±16
1,512N/AN/A
352
347355
MosaicML · CC-BY-NC-SA-4.0
1005±19
1,115N/AN/A
353
352357
OpenAssistant · Apache 2.0
984±16
1,744N/AN/A
354
352357
Tsinghua · Apache-2.0
980±23
762N/AN/A
355
352357
Tsinghua · Non-commercial
975±18
1,277N/AN/A
356
353358
RWKV · Apache 2.0
966±17
1,375N/AN/A
357
353359
LMSYS · Apache 2.0
954±19
1,134N/AN/A
358
356360
Databricks · MIT
934±21
899N/AN/A
359
357360
Meta
Meta · Non-commercial
912±25
584$0.23 / $0.23N/A
360
358360
Stability
Stability AI · CC-BY-NC-SA-4.0
907±20
814N/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)