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.

Jun 16, 2026
2,232,300 votes
367 models
Rank Spread
1
16
Anthropic
Anthropic · Proprietary
1517±16
1,426$10 / $501M
2
14
Anthropic
Anthropic · Proprietary
1514±6
14,204$5 / $251M
3
16
Anthropic
Anthropic · Proprietary
1504±7
11,075$5 / $251M
4
27
Anthropic
Anthropic · Proprietary
1501±6
15,834$5 / $251M
5
18
Anthropic
Anthropic · Proprietary
1498±10
4,258$5 / $251M
6
29
Anthropic
Anthropic · Proprietary
1495±7
11,542$5 / $251M
7
420
Anthropic
Anthropic · Proprietary
1485±10
4,330$5 / $251M
8
519
Anthropic
1484±7
9,458$5 / $25200K
9
620
Google · Proprietary
1482±6
19,527$2 / $121M
10
720
Anthropic
Anthropic · Proprietary
1479±6
12,635$3 / $151M
11
722
OpenAI · Proprietary
1479±7
9,331$5 / $301.1M
12
723
OpenAI · Proprietary
1477±6
13,343$2.50 / $151.1M
13
723
Anthropic
Anthropic · Proprietary
1475±5
20,748$5 / $25200K
14
725
Google · Proprietary
1474±6
11,193$2 / $121M
15
728
Xiaomi · MIT
1473±7
8,711$0.43 / $0.871M
16
728
OpenAI · Proprietary
1472±7
9,794$5 / $301.1M
17
731
Alibaba · Proprietary
1470±8
6,905N/AN/A
18
834
Z.ai · MIT
1469±9
5,420$1.40 / $4.40202.8K
19
743
Z.ai · MIT
1468±18
1,122$1.40 / $4.401M
20
744
Alibaba · Proprietary
1467±17
1,296$1.25 / $3.751M
21
1234
OpenAI · Proprietary
1465±6
14,474$2.50 / $151.1M
22
1434
Anthropic
1465±5
23,658$3 / $15200K
23
1434
Anthropic
Anthropic · Proprietary
1464±5
23,319$3 / $15200K
24
1141
Meta
Meta · Proprietary
1463±9
4,489N/AN/A
25
1143
Google · Proprietary
1462±11
3,458$1.50 / $91M
26
1541
Anthropic
1460±6
12,968$15 / $75200K
27
1543
Google · Proprietary
1459±7
8,089$0.50 / $31M
28
1743
OpenAI · Proprietary
1457±6
11,060$1.75 / $14128K
29
1745
Moonshot · Modified MIT
1456±7
8,265$0.95 / $4262.1K
30
1843
Anthropic
Anthropic · Proprietary
1455±5
20,321$15 / $75200K
31
1846
OpenAI · Proprietary
1455±7
9,261$5 / $301.1M
32
1846
Baidu · Proprietary
1455±8
7,816N/AN/A
33
1559
Google · Apache 2.0
1452±14
1,661$0.14 / $0.40262.1K
34
2249
DeepSeek · MIT
1451±7
9,656$0.43 / $0.871M
35
2251
1450±7
9,073$0.43 / $0.871M
36
1763
Alibaba · Proprietary
1449±14
1,776$1.04 / $6.24262.1K
37
2251
xAI · Proprietary
1449±7
8,420N/AN/A
38
2251
OpenAI · Proprietary
1448±6
10,743$1.25 / $10400K
39
2251
1448±6
14,000$2 / $62M
40
2254
Z.ai · MIT
1448±7
7,358$1 / $3.20202.8K
41
2259
MiniMax · Proprietary
1447±10
3,669$0.60 / $2.40N/A
42
2459
Xiaomi · Proprietary
1445±7
8,043$1 / $31M
43
3056
1444±5
20,625$0.50 / $31M
44
2959
Anthropic
Anthropic · Proprietary
1444±7
9,137$15 / $75200K
45
3159
1443±6
13,565$2 / $62M
46
3363
Moonshot · Modified MIT
1440±6
14,587$0.60 / $3N/A
47
3462
Google · Proprietary
1440±4
34,270$1.25 / $101M
48
2479
Google · Apache 2.0
1439±14
1,611N/AN/A
49
3373
OpenAI · Proprietary
1437±8
5,501$75 / $150128K
50
3473
Alibaba · Proprietary
1436±7
9,700$0.33 / $1.951M
51
3873
Alibaba · Apache 2.0
1435±6
13,770$0.39 / $2.45256K
52
3382
Moonshot · Modified MIT
1435±12
2,232$0.38 / $2.02262.1K
53
3874
OpenAI · Proprietary
1434±7
10,643$1.75 / $14128K
54
3974
Bytedance
Bytedance · Proprietary
1433±6
15,921N/AN/A
55
3977
OpenAI · Proprietary
1433±6
13,187$0.75 / $4.50400K
56
4079
1432±7
9,578$0.25 / $1.75200K
57
4079
Xiaomi · MIT
1431±7
9,010$0.14 / $0.281M
58
4577
xAI · Proprietary
1431±5
18,732N/AN/A
59
4577
xAI · Proprietary
1431±5
18,531N/AN/A
60
4090
Z.ai · MIT
1428±10
3,211$0.40 / $1.75202.8K
61
4880
OpenAI · Proprietary
1428±4
22,790$5 / $15128K
62
4686
DeepSeek · MIT
1428±7
9,473$0.09 / $0.181M
63
4885
OpenAI · Proprietary
1428±6
11,856$1.25 / $10400K
64
4885
OpenAI · Proprietary
1427±6
14,525$1.75 / $14400K
65
4886
Baidu · Proprietary
1427±6
10,514N/AN/A
66
4888
Alibaba · Proprietary
1427±7
7,283$0.78 / $3.90262.1K
67
4890
OpenAI · Proprietary
1424±5
18,857$1.75 / $14400K
68
48101
Xiaomi · Proprietary
1422±10
4,160$0.40 / $2262.1K
69
5394
DeepSeek · MIT
1421±6
12,931$0.23 / $0.34131.1K
70
48105
Mistral · Modified MIT
1421±11
3,422$1.50 / $7.50262.1K
71
38117
1421±20
862$0.27 / $0.95163.8K
72
48105
Baidu · Proprietary
1420±11
2,624N/AN/A
73
5599
DeepSeek · MIT
1419±6
11,169$0.23 / $0.34131.1K
74
48108
DeepSeek · MIT
1419±11
2,860$1.23 / $4.94N/A
75
60101
Moonshot · Modified MIT
1418±5
17,927$1.15 / $8262.1K
76
45119
1417±19
935N/AN/A
77
59105
OpenAI · Proprietary
1417±7
8,144$1.25 / $10128K
78
53110
DeepSeek · MIT
1417±10
3,310$0.27 / $0.41163.8K
79
51111
1417±12
2,544$0.27 / $0.41163.8K
80
65101
Alibaba · Apache 2.0
1416±4
26,979$0.26 / $1.06N/A
81
53112
Alibaba · Proprietary
1416±11
2,631$0.78 / $3.90262.1K
82
60107
xAI · Proprietary
1415±7
9,600$1.25 / $2.501M
83
61105
Z.ai · MIT
1415±6
10,000$0.43 / $1.74202.8K
84
61107
Anthropic
1415±7
8,554$3 / $151M
85
61107
Meituan · Proprietary
1415±7
9,095N/AN/A
86
66105
Anthropic
Anthropic · Proprietary
1414±4
26,995$1 / $5200K
87
56114
Alibaba · Apache 2.0
1414±11
2,925$0.20 / $0.88262.1K
88
65109
Anthropic
Anthropic · Proprietary
1414±6
10,700$15 / $75200K
89
68114
Anthropic
1410±6
10,144$3 / $15200K
90
68114
OpenAI · Proprietary
1410±7
8,266$1.25 / $10400K
91
68115
MiniMax · Modified MIT
1408±7
10,984$0.25 / $1204.8K
92
69115
Google · Proprietary
1408±6
15,755$0.25 / $1.501M
93
69117
OpenAI · Proprietary
1407±6
10,246$15 / $60200K
94
69119
Alibaba · Apache 2.0
1407±7
9,045$0.26 / $2.08262.1K
95
73119
xAI · Proprietary
1406±7
9,672$3 / $15131.1K
96
70120
Z.ai · MIT
1405±8
6,169$0.60 / $2.20131.1K
97
73119
Mistral · Apache 2.0
1404±6
12,420$0.50 / $1.50N/A
98
70126
DeepSeek · MIT
1403±10
3,691$1.23 / $4.94N/A
99
78120
OpenAI · Proprietary
1403±6
13,289$2 / $81M
100
63139
1402±19
925N/AN/A
101
82121
OpenAI · Proprietary
1402±6
15,509$2 / $8200K
102
83121
xAI · Proprietary
1402±5
16,594$0.20 / $0.502M
103
78122
1402±7
9,152$0.30 / $2.501M
104
84120
Google · Proprietary
1402±4
33,961$0.30 / $2.501M
105
68137
Baidu · Proprietary
1401±16
1,313N/AN/A
106
81125
Alibaba · Apache 2.0
1401±7
8,631$0.20 / $1.56262.1K
107
69137
xAI · Proprietary
1401±14
1,729$3 / $15256K
108
69135
1400±13
2,039N/AN/A
109
73136
Tencent
Tencent · tencent-hunyuan-community
1399±13
2,218$0.29 / $1.17262.1K
110
89126
Mistral · Proprietary
1398±4
26,757$2.70 / $8.1032K
111
86128
xAI · Proprietary
1397±6
10,816$3 / $15256K
112
85131
DeepSeek · MIT
1397±7
6,426$0.70 / $2.50163.8K
113
66144
Tencent
Tencent · Proprietary
1397±22
623N/AN/A
114
73144
DeepSeek · MIT
1394±18
1,028$0.27 / $0.95163.8K
115
93135
Anthropic
Anthropic · Proprietary
1393±7
9,987$3 / $151M
116
91139
DeepSeek · MIT
1392±9
4,050$0.50 / $2.15163.8K
117
91141
Moonshot · Modified MIT
1390±11
2,887$0.60 / $2.50262.1K
118
93141
Meituan · MIT
1389±11
2,953$0.20 / $0.80131.1K
119
100140
xAI · Proprietary
1388±8
5,312$0.20 / $0.502M
120
103140
Alibaba · Apache 2.0
1388±7
9,340$0.14 / $1262.1K
121
103139
Stepfun
StepFun · Apache 2.0
1388±6
13,840$0.09 / $0.30262.1K
122
97148
Alibaba · Apache 2.0
1386±12
2,099$0.10 / $0.10262.1K
123
103142
MiniMax · MIT
1386±9
4,473$0.29 / $0.95204.8K
124
106140
OpenAI · Proprietary
1386±6
12,936$0.20 / $1.25400K
125
106142
Alibaba · Apache 2.0
1385±8
6,224$0.40 / $1.60262.1K
126
86155
1385±19
921N/AN/A
127
107141
Anthropic
Anthropic · Proprietary
1384±6
12,322$3 / $15200K
128
108141
1384±6
14,012$0.10 / $0.30262.1K
129
102150
Alibaba · Apache 2.0
1384±12
2,132$0.26 / $2.60131.1K
130
108145
Alibaba · Apache 2.0
1381±7
9,276$0.46 / $1.82131.1K
131
108147
OpenAI · Proprietary
1381±7
12,782$15 / $60N/A
132
111146
MiniMax · Modified MIT
1380±6
13,048$0.15 / $0.90204.8K
133
107154
1380±11
2,971$0.10 / $0.30262.1K
134
108150
Alibaba · Apache 2.0
1379±8
6,313$0.09 / $1.10262.1K
135
113148
Alibaba · Proprietary
1379±6
12,965N/AN/A
136
110151
Moonshot · Modified MIT
1379±8
6,751$0.60 / $2.50131.1K
137
113149
DeepSeek · MIT
1379±6
12,396$3 / $4.5032.8K
138
104163
Tencent
Tencent · Proprietary
1376±17
1,113N/AN/A
139
116155
OpenAI · Proprietary
1374±8
6,916$0.25 / $2400K
140
119155
OpenAI · Proprietary
1373±6
10,064$0.40 / $1.601M
141
125155
Anthropic
Anthropic · Proprietary
1372±4
31,266$3 / $15200K
142
123158
Arcee AI · Apache 2.0
1371±7
9,223$0.15 / $0.45131K
143
125159
1369±7
8,103$0.10 / $0.401M
144
107175
Z.ai · MIT
1368±22
732$0.30 / $0.90131.1K
145
128159
OpenAI · Proprietary
1368±6
11,897$1.10 / $4.40200K
146
126163
Alibaba · Apache 2.0
1367±8
5,963$0.05 / $0.19131.1K
147
130162
Mistral · Proprietary
1367±7
7,938$0.40 / $2131.1K
148
129163
OpenAI · Proprietary
1366±8
6,681$1.10 / $4.40200K
149
136162
1365±6
12,900$0.10 / $0.401M
150
133165
1365±7
6,717N/AN/A
151
136165
Z.ai · MIT
1363±7
8,116$0.13 / $0.85131.1K
152
135166
xAI · Proprietary
1362±9
4,225$0.25 / $1.27N/A
153
137171
Alibaba · Apache 2.0
1359±10
3,517$0.10 / $0.78262.1K
154
141168
Arcee AI · Apache 2.0
1358±7
9,866$0.25 / $0.80262.1K
155
142168
Alibaba · Proprietary
1357±6
10,958N/AN/A
156
141171
Alibaba · Apache 2.0
1357±8
6,192$0.46 / $1.82131.1K
157
144177
xAI · Proprietary
1353±8
5,546$0.30 / $0.50131.1K
158
141182
Tencent
Tencent · Proprietary
1353±12
2,426N/AN/A
159
132196
Nvidia · Nvidia Open Model
1351±22
660$0.60 / $1.80131.1K
160
144183
Z.ai · MIT
1351±10
3,176$0.06 / $0.40202.8K
161
136188
Tencent
Tencent · Proprietary
1351±18
886N/AN/A
162
151180
Google · Proprietary
1348±6
13,632$0.10 / $0.401M
163
149188
1348±11
3,032N/AN/A
164
146188
Nvidia · NVIDIA Open Model
1346±13
1,997N/AN/A
165
152183
MiniMax · Apache 2.0
1346±7
8,687$0.40 / $2.201M
166
144194
Stepfun
StepFun · Apache 2.0
1345±14
1,638$0.57 / $1.4265.5K
167
154188
DeepSeek · DeepSeek
1344±7
8,606$1.14 / $4.56N/A
168
154184
Google · Gemma
1344±6
12,525$0.08 / $0.16131.1K
169
156184
OpenAI · Proprietary
1343±5
16,960$1.10 / $4.40200K
170
149198
Z.ai · MIT
1342±16
1,302$0.60 / $1.8065.5K
171
156188
Cohere
Cohere · CC-BY-NC-4.0
1342±5
15,485$2.50 / $10256K
172
152198
MiniMax · Apache 2.0
1339±13
1,987$0.26 / $1204.8K
173
156195
Mistral · Apache 2.0
1339±9
4,388$0.10 / $0.3032K
174
158188
Google · Proprietary
1339±5
22,789$3.50 / $10.502.1M
175
159193
Anthropic
Anthropic · Proprietary
1336±5
32,074$3 / $15200K
176
158203
Alibaba · Proprietary
1332±12
2,249$0.40 / $1.20131.1K
177
164198
OpenAI · Proprietary
1332±5
21,478$1.10 / $4.40N/A
178
154213
Alibaba · Apache 2.0
1332±19
858$0.08 / $0.28131.1K
179
164199
1331±6
9,249$0.07 / $0.301M
180
160203
Amazon · Proprietary
1330±10
3,327$0.30 / $2.501M
181
157212
Prime Intellect · MIT
1330±16
1,396$0.20 / $1.10131.1K
182
157220
1326±19
803N/AN/A
183
170206
OpenAI · Apache 2.0
1326±7
7,822$0.04 / $0.18131.1K
184
162214
OpenAI · Proprietary
1325±13
2,029$0.05 / $0.40400K
185
173203
OpenAI · Proprietary
1325±5
43,766$5 / $15128K
186
170207
Alibaba · Apache 2.0
1324±7
7,171$0.50 / $116.4K
187
158224
Inception AI · Proprietary
1322±20
838$0.25 / $0.75128K
188
159224
1322±20
807$0.10 / $0.40131.1K
189
170214
Ai2 · Apache 2.0
1322±11
3,226$0.20 / $0.6065.5K
190
164220
Google · Gemma
1321±16
1,145$0.05 / $0.15131.1K
191
178214
OpenAI · Proprietary
1318±6
18,305$2.50 / $10128K
192
171222
Ant Group · MIT
1317±14
1,853N/AN/A
193
172222
Ant Group · MIT
1317±14
1,795N/AN/A
194
164233
1317±21
720N/AN/A
195
170226
Tencent
Tencent · Proprietary
1316±16
1,300N/AN/A
196
174222
Stepfun
StepFun · Proprietary
1316±13
1,950N/AN/A
197
178215
Google · Proprietary
1316±7
18,524N/AN/A
198
177222
DeepSeek · DeepSeek
1315±11
2,970N/AN/A
199
174224
Z.ai · Proprietary
1315±12
2,160N/AN/A
200
181214
Anthropic
Anthropic · Proprietary
1314±5
22,004$0.80 / $4200K
201
170232
Tencent
Tencent · Proprietary
1314±18
842N/AN/A
202
178219
1314±6
10,494$0.63 / $1.80131.1K
203
181216
Meta
Meta · Llama 3.1 Community
1314±5
23,585$4 / $432.8K
204
182218
Meta
Meta · Llama 3.1 Community
1313±5
16,174$4 / $432.8K
205
183216
Anthropic
Anthropic · Proprietary
1313±5
72,001$15 / $75200K
206
183220
xAI · Proprietary
1312±5
25,659$2 / $10131.1K
207
181222
Alibaba · Apache 2.0
1312±8
6,129$0.12 / $0.50131.1K
208
183220
Google · Proprietary
1311±6
29,835$3.50 / $10.502.1M
209
156254
Ai2 · Apache 2.0
1309±38
217$0.20 / $0.2036.9K
210
183225
01.AI
01 AI · Proprietary
1309±7
10,932N/AN/A
211
178232
Stepfun
StepFun · Proprietary
1309±13
2,097N/AN/A
212
192232
OpenAI · Proprietary
1303±6
36,297$10 / $30128K
213
190232
NexusFlow · NexusFlow
1302±6
10,236N/AN/A
214
185238
Mistral · Proprietary
1302±11
3,116$2 / $540K
215
189235
Alibaba · Qwen
1302±8
6,919$1.60 / $6.4032.8K
216
184241
OpenAI · Proprietary
1301±12
2,015$0.10 / $0.401M
217
193235
Z.ai · Proprietary
1301±7
10,743$0.44 / $1.76204.8K
218
192236
1301±7
7,477$0.40 / $0.708.2K
219
183244
Ai2 · Apache 2.0
1299±16
1,495$0.15 / $0.5065.5K
220
198236
Mistral · Mistral Research
1299±6
18,321$2 / $6131.1K
221
198242
Alibaba · Proprietary
1295±9
4,234N/AN/A
222
203241
1295±7
8,048$0.10 / $0.3032K
223
207240
OpenAI · Proprietary
1295±6
34,416$10 / $30128K
224
208241
Mistral · MRL
1294±6
10,971$2 / $6128K
225
208241
OpenAI · Proprietary
1294±5
26,705$0.15 / $0.60128K
226
206244
Nvidia · NVIDIA Open Model
1293±9
4,207$0.06 / $0.24262.1K
227
208242
Meta
Meta · Llama-3.3
1292±5
18,787$0.10 / $0.32131.1K
228
208242
Alibaba · Qwen
1292±6
16,363$1.20 / $1.20N/A
229
208243
DeepSeek · DeepSeek
1291±7
10,175N/AN/A
230
212244
Google · Proprietary
1290±6
14,561$0.07 / $0.301M
231
194253
IBM · Apache 2.0
1290±18
1,397$0.05 / $0.10131.1K
232
213244
OpenAI · Proprietary
1289±6
33,252$10 / $30128K
233
203255
Tencent
Tencent · Proprietary
1287±17
1,214N/AN/A
234
219247
xAI · Proprietary
1284±5
21,131$2 / $10131.1K
235
218251
OpenAI · Proprietary
1283±7
18,087$30 / $608.2K
236
208255
Tencent
Tencent · Proprietary
1282±15
1,329N/AN/A
237
215255
OpenAI · Apache 2.0
1281±12
2,554$0.03 / $0.14131.1K
238
218252
Google · Gemma
1281±9
4,986$0.06 / $0.1232.8K
239
217255
1280±11
2,959$1.20 / $1.20131.1K
240
217257
Ai2 · Apache 2.0
1279±13
2,159$0.15 / $0.5065.5K
241
226255
NexusFlow · CC-BY-NC-4.0
1278±8
7,490N/AN/A
242
231255
Amazon · Proprietary
1276±6
9,525$0.80 / $3.20300K
243
231255
OpenAI · Proprietary
1275±6
29,706$30 / $608.2K
244
232255
Meta
Meta · Llama 3.1 Community
1272±5
21,910$0.40 / $0.40131.1K
245
223264
Ai2 · Llama 3.1
1272±16
1,170N/AN/A
246
233257
Google · Gemma license
1270±5
29,545$0.65 / $0.658.2K
247
213274
Inception AI · Proprietary
1269±26
570$0.25 / $0.75128K
248
227266
Google · Gemma
1268±16
1,233$0.05 / $0.10131.1K
249
231266
IBM · Apache 2.0
1267±16
1,575N/AN/A
250
234261
Anthropic
Anthropic · Proprietary
1267±6
38,802$3 / $15200K
251
232264
AI21 Labs · Jamba Open
1266±11
3,266$2 / $8256K
252
236263
Google · Proprietary
1264±6
23,685$0.07 / $0.301M
253
232265
Alibaba · Apache 2.0
1264±12
2,227$0.87 / $0.8732K
254
235266
Reka AI · Proprietary
1261±10
3,118N/AN/A
255
232270
1261±15
1,484N/AN/A
256
244267
Nvidia · NVIDIA Open Model
1258±8
7,354N/AN/A
257
246265
Meta
Meta · Llama 3 Community
1257±5
56,558$0.51 / $0.748.2K
258
244272
Z.ai · Proprietary
1255±10
3,766N/AN/A
259
246270
Mistral · Apache 2.0
1255±8
5,485$0.05 / $0.0832.8K
260
246274
Cohere
Cohere · CC-BY-NC-4.0
1253±9
4,024$2.50 / $10128K
261
247275
DeepSeek · DeepSeek License
1252±9
5,614$0.14 / $0.28128K
262
246275
Princeton · MIT
1251±10
3,741$0.03 / $0.098.2K
263
250275
Cohere
Cohere · CC-BY-NC-4.0
1248±7
11,265N/AN/A
264
248275
Reka AI · Proprietary
1248±10
3,246N/AN/A
265
252275
Microsoft · MIT
1245±7
9,162$0.07 / $0.1416.4K
266
256275
Google · Gemma license
1244±5
21,359$0.03 / $0.098.2K
267
255275
Amazon · Proprietary
1244±7
7,809$0.06 / $0.24300K
268
256275
Anthropic
Anthropic · Proprietary
1244±5
43,031$0.25 / $1.25200K
269
247276
Tencent
Tencent · Proprietary
1243±17
1,098N/AN/A
270
256275
Alibaba · Qianwen LICENSE
1241±7
14,194$0.90 / $0.9032.8K
271
258276
Cohere
Cohere · CC-BY-NC-4.0
1240±6
28,069$2.50 / $10128K
272
259276
Google · Proprietary
1238±6
14,894$0.07 / $0.301M
273
261276
Mistral · Proprietary
1236±7
21,532$4 / $1232K
274
259276
Cohere
Cohere · CC-BY-NC-4.0
1234±9
4,153$0.15 / $0.60128K
275
258287
Ai2 · Apache-2.0
1228±17
1,063$0.05 / $0.20128K
276
270292
Google · Proprietary
1217±17
1,897$0.35 / $1.0532.8K
277
275288
Alibaba · Qianwen LICENSE
1217±8
9,518N/AN/A
278
275289
Amazon · Proprietary
1215±7
7,716$0.04 / $0.14128K
279
275291
Mistral · Apache 2.0
1214±7
18,515$0.90 / $0.9065.5K
280
275291
OpenAI · Proprietary
1213±6
23,523$0.50 / $1.5016.4K
281
275293
Mistral · MRL
1211±13
1,946$0.10 / $0.10131.1K
282
275292
Alibaba · Qianwen LICENSE
1210±7
13,814N/AN/A
283
275292
Mistral · Proprietary
1209±8
11,466$2.70 / $8.1032K
284
275297
Ai2 · Llama 3.1
1208±16
1,172N/AN/A
285
275293
Google · Proprietary
1208±11
5,876$0.35 / $1.0532.8K
286
275297
AI21 Labs · Jamba Open
1204±11
3,254$0.20 / $0.40256K
287
275296
Cohere
Cohere · CC-BY-NC-4.0
1204±10
4,006N/AN/A
288
276298
Reka AI · Proprietary
1200±10
5,558N/AN/A
289
280298
Cohere
Cohere · CC-BY-NC-4.0
1198±7
19,085$0.15 / $0.60128K
290
278303
OpenAI · Proprietary
1195±12
5,238$1 / $216.4K
291
278306
HuggingFace · Apache 2.0
1192±16
1,593N/AN/A
292
277307
IBM · Apache 2.0
1192±17
1,258N/AN/A
293
285300
Meta
Meta · Llama 3 Community
1191±6
37,733$0.14 / $0.148.2K
294
285300
Meta
Meta · Llama 3.1 Community
1191±6
19,781$0.02 / $0.03131.1K
295
283303
Reka AI · Proprietary
1191±8
9,018N/AN/A
296
285304
01.AI
01 AI · Apache-2.0
1187±8
8,996N/AN/A
297
286304
Databricks · DBRX LICENSE
1186±9
11,274$0.60 / $0.6032.8K
298
288307
Alibaba · Qianwen LICENSE
1183±9
7,653N/AN/A
299
292308
Mistral · Apache 2.0
1179±6
24,974$0.63 / $0.6332K
300
290308
InternLM · Other
1177±10
4,092$0 / $032.8K
301
292308
Microsoft · MIT
1176±7
9,385$0.17 / $0.68N/A
302
290318
IBM · Apache 2.0
1172±16
1,252N/AN/A
303
296310
Google · Gemma license
1171±6
18,240N/AN/A
304
294317
IBM · Apache 2.0
1170±12
2,597N/AN/A
305
292318
AllenAI/UW · AI2 ImpACT Low-risk
1170±15
2,008N/AN/A
306
296317
Alibaba · Qianwen LICENSE
1167±10
6,231$0.30 / $0.30N/A
307
297321
Microsoft · Llama 2 Community
1162±13
2,680N/AN/A
308
299326
DeepSeek · DeepSeek License
1156±17
1,525N/AN/A
309
303322
Google · Gemma license
1155±8
8,852$0.03 / $0.098.2K
310
303323
OpenChat · Apache-2.0
1154±11
4,414N/AN/A
311
303323
Microsoft · MIT
1153±9
6,632$0.15 / $0.60N/A
312
302326
OpenChat · Apache-2.0
1152±14
2,391$0.20 / $0.20N/A
313
302328
NousResearch · Apache-2.0
1151±15
1,577$0.17 / $0.17N/A
314
303323
Snowflake · Apache 2.0
1151±9
11,736N/AN/A
315
303325
01.AI
01 AI · Yi License
1151±10
5,099$0.90 / $0.904.1K
316
303332
Alibaba · Apache 2.0
1147±16
1,329$0.50 / $116.4K
317
305328
Meta
Meta · Llama 3.2
1145±11
3,171$0.05 / $0.34131.1K
318
307328
Nexusflow · Apache-2.0
1145±10
5,765N/AN/A
319
308332
LMSYS · Non-commercial
1138±9
6,983$0 / $02K
320
309336
UC Berkeley · CC-BY-NC-4.0
1135±12
3,316N/AN/A
321
313334
Meta
Meta · Llama 2 Community
1133±8
12,635$0.70 / $2.804.1K
322
307342
MosaicML · CC-BY-NC-SA-4.0
1133±21
718N/AN/A
323
303345
TII · Falcon-180B TII License
1132±29
389N/AN/A
324
312340
IBM · Apache 2.0
1130±12
2,698N/AN/A
325
307345
Cognitive Computations · Apache-2.0
1127±24
497$0.50 / $0.5016.4K
326
312344
Nvidia · Llama 2 Community
1123±18
1,076N/AN/A
327
318342
1123±10
4,431$0.13 / $0.524.1K
328
315344
Alibaba · Qianwen LICENSE
1123±14
1,715$0.20 / $0.20N/A
329
315344
Microsoft · Llama 2 Community
1122±14
2,003$0.30 / $0.30N/A
330
318342
Mistral · Apache-2.0
1122±9
6,659$0.20 / $0.2032.8K
331
318346
Alibaba · Qianwen LICENSE
1117±16
1,470N/AN/A
332
321344
LMSYS · Llama 2 Community
1115±10
5,665$0.30 / $0.30N/A
333
320345
Google · Proprietary
1114±14
2,536$0.50 / $0.5025.8K
334
318348
Upstage AI · CC-BY-NC-4.0
1114±19
1,188$0.30 / $0.30N/A
335
322345
Microsoft · MIT
1112±9
7,636$0.13 / $0.52N/A
336
322346
Meta
Meta · Llama 2 Community
1109±9
6,097$0.25 / $0.254.1K
337
322348
NousResearch · Apache-2.0
1107±16
1,421$0.90 / $0.90N/A
338
323348
Google · Gemma license
1103±13
2,835$0.05 / $0.088.2K
339
323348
Meta
Meta · Llama 2 Community
1102±13
2,294$0.35 / $1.4016.4K
340
321351
HuggingFace · Apache 2.0
1102±21
859N/AN/A
341
326349
Google · Gemma license
1099±11
3,877N/AN/A
342
326349
Microsoft · MIT
1098±10
7,368$0.13 / $0.52N/A
343
322353
HuggingFace · MIT
1098±24
534N/AN/A
344
320353
Meta
Meta · Llama 2 Community
1096±30
358$0.70 / $2.8016.4K
345
330353
Together AI · Apache 2.0
1089±15
1,660$0.20 / $0.20N/A
346
334353
HuggingFace · MIT
1088±13
3,094$0.15 / $0.1516.4K
347
336353
Mistral · Apache 2.0
1085±14
2,768$0.07 / $0.284.1K
348
336353
Meta
Meta · Llama 3.2
1085±11
3,248$0.03 / $0.20131.1K
349
340354
LMSYS · Llama 2 Community
1075±14
2,020$0.20 / $0.20N/A
350
342355
Google · Gemma license
1068±16
1,522$0.10 / $0.10N/A
351
343354
Meta
Meta · Llama 2 Community
1068±10
4,541$0.15 / $0.154.1K
352
343354
Alibaba · Qianwen LICENSE
1068±13
2,636$0.10 / $0.10N/A
353
342356
UW · Non-commercial
1064±21
777N/AN/A
354
349359
Nomic AI · Non-commercial
1036±25
483N/AN/A
355
352359
Tsinghua · Apache-2.0
1035±18
1,321N/AN/A
356
353359
Ai2 · Apache-2.0
1028±16
1,908$0.20 / $0.20N/A
357
354359
UC Berkeley · Non-commercial
1024±15
1,913N/AN/A
358
354359
Stanford · Non-commercial
1021±16
1,512N/AN/A
359
354362
MosaicML · CC-BY-NC-SA-4.0
1007±19
1,115N/AN/A
360
359364
OpenAssistant · Apache 2.0
985±16
1,744N/AN/A
361
359364
Tsinghua · Apache-2.0
981±23
762N/AN/A
362
359364
Tsinghua · Non-commercial
976±18
1,277N/AN/A
363
360365
RWKV · Apache 2.0
968±17
1,375N/AN/A
364
360366
LMSYS · Apache 2.0
956±19
1,134N/AN/A
365
363367
Databricks · MIT
936±21
899N/AN/A
366
364367
Meta
Meta · Non-commercial
915±25
584$0.23 / $0.23N/A
367
365367
Stability
Stability AI · CC-BY-NC-SA-4.0
908±20
814N/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)