Text Arena🧠Hard Prompts (English)

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

Jun 5, 2026
1,502,971 votes
364 models
Rank Spread
1
12
Anthropic
Anthropic · Proprietary
1541±7
11,417$5 / $251M
2
16
Anthropic
Anthropic · Proprietary
1532±6
12,829$5 / $251M
3
27
Anthropic
Anthropic · Proprietary
1526±8
8,262$5 / $251M
4
211
Anthropic
Anthropic · Proprietary
1519±7
8,636$5 / $251M
5
216
Anthropic
Anthropic · Proprietary
1519±13
2,052$5 / $251M
6
217
Anthropic
Anthropic · Proprietary
1518±14
1,899$5 / $251M
7
323
Meta
Meta · Proprietary
1509±10
4,092N/AN/A
8
419
Google · Proprietary
1508±6
15,452$2 / $121M
9
421
Anthropic
Anthropic · Proprietary
1507±7
9,948$3 / $151M
10
426
Z.ai · MIT
1506±9
4,927$1.40 / $4.40202.8K
11
426
Xiaomi · MIT
1506±8
6,246$0.43 / $0.871M
12
524
Anthropic
1505±7
9,402$5 / $25200K
13
528
Google · Proprietary
1502±7
10,724$2 / $121M
14
537
OpenAI · Proprietary
1502±8
6,753$5 / $301.1M
15
537
OpenAI · Proprietary
1499±7
10,176$2.50 / $151.1M
16
737
Anthropic
Anthropic · Proprietary
1499±5
19,943$5 / $25200K
17
637
OpenAI · Proprietary
1498±7
10,284$1.75 / $14128K
18
737
Anthropic
1498±5
22,769$3 / $15200K
19
843
Alibaba · Proprietary
1493±8
6,490N/AN/A
20
844
Baidu · Proprietary
1492±8
5,944N/AN/A
21
944
OpenAI · Proprietary
1492±8
7,134$5 / $301.1M
22
1441
Anthropic
Anthropic · Proprietary
1491±5
23,025$3 / $15200K
23
1150
Xiaomi · Proprietary
1490±8
7,204$1 / $31M
24
1346
OpenAI · Proprietary
1490±7
11,158$2.50 / $151.1M
25
560
Alibaba · Proprietary
1489±17
1,308$1.25 / $3.751M
26
1447
1489±7
10,879$2 / $62M
27
1150
Moonshot · Modified MIT
1489±8
6,000$0.95 / $4262.1K
28
1446
Anthropic
1489±6
12,540$15 / $75200K
29
1450
OpenAI · Proprietary
1488±7
8,800$5 / $301.1M
30
1450
Google · Proprietary
1488±7
7,867$0.50 / $31M
31
1451
1487±8
6,447$0.43 / $0.871M
32
1450
xAI · Proprietary
1487±7
7,982N/AN/A
33
1450
Z.ai · MIT
1487±8
6,643$1 / $3.20202.8K
34
1956
1484±7
10,497$2 / $62M
35
968
MiniMax · Proprietary
1484±16
1,505$0.60 / $2.40N/A
36
1065
Google · Apache 2.0
1484±15
1,529$0.14 / $0.40262.1K
37
1461
Google · Proprietary
1483±11
3,285$1.50 / $91M
38
1955
Anthropic
Anthropic · Proprietary
1482±5
19,372$15 / $75200K
39
1369
Alibaba · Proprietary
1481±15
1,537$1.04 / $6.24262.1K
40
2060
Bytedance
Bytedance · Proprietary
1479±6
12,927N/AN/A
41
1961
DeepSeek · MIT
1479±8
6,856$0.43 / $0.871M
42
2060
OpenAI · Proprietary
1479±7
10,358$1.25 / $10400K
43
2360
xAI · Proprietary
1478±5
17,926N/AN/A
44
2161
Moonshot · Modified MIT
1478±6
11,743$0.60 / $3N/A
45
2661
xAI · Proprietary
1477±5
18,412N/AN/A
46
2565
Meituan · Proprietary
1476±7
8,714N/AN/A
47
2669
Alibaba · Proprietary
1475±8
7,233$0.33 / $1.951M
48
3267
1473±5
17,224$0.50 / $31M
49
2376
Z.ai · MIT
1473±11
3,097$0.40 / $1.75202.8K
50
3370
Alibaba · Apache 2.0
1472±6
11,488$0.39 / $2.34262.1K
51
3373
OpenAI · Proprietary
1471±7
10,124$0.75 / $4.50400K
52
3377
Xiaomi · MIT
1469±8
6,653$0.14 / $0.281M
53
3576
OpenAI · Proprietary
1469±7
9,761$1.75 / $14128K
54
1999
1468±19
885N/AN/A
55
2692
Google · Apache 2.0
1468±15
1,485N/AN/A
56
3579
Baidu · Proprietary
1467±7
9,570N/AN/A
57
3492
Moonshot · Modified MIT
1465±13
2,147$0.40 / $1.90262.1K
58
3396
Xiaomi · Proprietary
1464±14
1,961$0.40 / $2262.1K
59
3593
1464±12
2,383$0.27 / $0.41163.8K
60
4386
Anthropic
Anthropic · Proprietary
1463±7
8,390$15 / $75200K
61
4586
DeepSeek · MIT
1462±6
10,445$0.23 / $0.34131.1K
62
4391
DeepSeek · MIT
1462±8
6,826$0.10 / $0.201M
63
4786
OpenAI · Proprietary
1461±6
13,522$1.75 / $14400K
64
3999
Baidu · Proprietary
1461±12
2,524N/AN/A
65
4592
xAI · Proprietary
1460±8
7,019$1.25 / $2.501M
66
5091
Moonshot · Modified MIT
1459±5
16,805$1.15 / $8262.1K
67
5192
OpenAI · Proprietary
1458±6
15,534$1.75 / $14400K
68
43102
Alibaba · Proprietary
1458±12
2,527$0.78 / $3.90262.1K
69
5193
OpenAI · Proprietary
1458±6
11,315$1.25 / $10400K
70
4997
1457±8
6,717$0.10 / $0.201M
71
5096
Alibaba · Proprietary
1457±7
6,834$0.78 / $3.90262.1K
72
5492
Google · Proprietary
1456±4
32,094$1.25 / $101M
73
5498
DeepSeek · MIT
1455±6
12,288$0.23 / $0.34131.1K
74
5595
OpenAI · Proprietary
1455±5
19,985$5 / $15128K
75
53100
MiniMax · Modified MIT
1455±7
8,524$0.28 / $1.20204.8K
76
35118
1455±19
929N/AN/A
77
46111
Mistral · Modified MIT
1455±13
2,066$1.50 / $7.50262.1K
78
5596
Anthropic
Anthropic · Proprietary
1455±5
23,809$1 / $5200K
79
50107
DeepSeek · MIT
1454±10
3,210$0.27 / $0.41163.8K
80
55105
OpenAI · Proprietary
1453±7
7,687$1.25 / $10400K
81
51113
Alibaba · Apache 2.0
1452±12
2,949$0.20 / $0.88262.1K
82
58102
Alibaba · Apache 2.0
1451±4
25,302$0.26 / $1.06N/A
83
43128
1451±20
839$0.27 / $0.95163.8K
84
58108
Z.ai · MIT
1448±7
9,616$0.43 / $1.74202.8K
85
58112
OpenAI · Proprietary
1448±7
7,747$1.25 / $10128K
86
58112
Anthropic
1448±7
8,111$3 / $151M
87
65113
OpenAI · Proprietary
1446±6
13,965$2 / $8200K
88
55128
xAI · Proprietary
1445±15
1,612$3 / $15256K
89
55121
DeepSeek · MIT
1445±12
2,470$1.23 / $4.94N/A
90
55124
OpenAI · Proprietary
1444±12
2,260$75 / $150128K
91
71114
xAI · Proprietary
1444±5
15,663$0.20 / $0.502M
92
67117
Alibaba · Apache 2.0
1444±7
8,496$0.26 / $2.08262.1K
93
72118
Anthropic
Anthropic · Proprietary
1442±7
9,914$15 / $75200K
94
55140
1441±19
900N/AN/A
95
76121
Google · Proprietary
1441±6
12,721$0.25 / $1.501M
96
60130
Tencent
Tencent · tencent-hunyuan-community
1440±13
2,079$0.29 / $1.17262.1K
97
76121
Alibaba · Apache 2.0
1440±7
8,178$0.20 / $1.56262.1K
98
78121
Mistral · Apache 2.0
1440±6
11,759$0.50 / $1.50N/A
99
67129
Meituan · MIT
1440±11
2,858$0.20 / $0.80131.1K
100
79120
Mistral · Proprietary
1439±4
25,496$2.70 / $8.1032K
101
68129
Moonshot · Modified MIT
1439±11
2,839$0.60 / $2.50262.1K
102
75129
DeepSeek · MIT
1439±10
3,500$0.50 / $2.15163.8K
103
80128
OpenAI · Proprietary
1437±6
11,908$2 / $81M
104
78132
DeepSeek · MIT
1436±10
3,364$1.23 / $4.94N/A
105
58146
1435±20
954N/AN/A
106
86129
1434±6
12,895$0.10 / $0.30262.1K
107
81131
xAI · Proprietary
1433±8
6,350$3 / $15131.1K
108
81132
Moonshot · Modified MIT
1433±8
6,369$0.60 / $2.50131.1K
109
79140
DeepSeek · MIT
1433±11
2,656$0.70 / $2.50163.8K
110
84135
Z.ai · MIT
1432±8
5,696$0.60 / $2.20131.1K
111
87136
OpenAI · Proprietary
1431±7
9,999$0.20 / $1.25400K
112
87136
MiniMax · Modified MIT
1430±6
12,077$0.15 / $1.15204.8K
113
87140
Alibaba · Apache 2.0
1429±8
6,058$0.09 / $1.10262.1K
114
90140
Anthropic
1428±7
7,771$3 / $15200K
115
82146
Alibaba · Apache 2.0
1428±13
2,009$0.10 / $0.10262.1K
116
78155
DeepSeek · MIT
1428±18
1,049$0.27 / $0.95163.8K
117
90141
Alibaba · Apache 2.0
1427±8
6,042$0.40 / $1.60262.1K
118
81150
Baidu · Proprietary
1427±15
1,369N/AN/A
119
95141
Stepfun
StepFun · Apache 2.0
1426±6
10,678$0.09 / $0.30262.1K
120
73162
Tencent
Tencent · Proprietary
1426±23
583N/AN/A
121
91146
MiniMax · MIT
1425±9
4,199$0.29 / $0.95204.8K
122
96142
xAI · Proprietary
1425±6
10,380$3 / $15256K
123
88148
1425±11
2,768$0.10 / $0.30262.1K
124
96144
Anthropic
Anthropic · Proprietary
1424±7
9,267$3 / $151M
125
96145
Alibaba · Apache 2.0
1424±7
8,646$0.14 / $1262.1K
126
96146
xAI · Proprietary
1423±8
5,206$0.20 / $0.502M
127
99146
1423±7
8,797$0.30 / $2.501M
128
95148
OpenAI · Proprietary
1423±9
4,238$15 / $60200K
129
103149
Alibaba · Apache 2.0
1420±7
8,647$0.46 / $1.82131.1K
130
95156
Alibaba · Apache 2.0
1420±13
2,096$0.26 / $2.60131.1K
131
104149
Alibaba · Proprietary
1419±7
10,211N/AN/A
132
110148
Google · Proprietary
1418±4
31,823$0.30 / $2.501M
133
107150
DeepSeek · MIT
1418±6
10,238$3 / $4.5032.8K
134
107152
Arcee AI · Apache 2.0
1418±7
8,890$0.15 / $0.45131K
135
110151
OpenAI · Proprietary
1417±6
10,496$1.10 / $4.40200K
136
108155
Alibaba · Apache 2.0
1416±8
5,628$0.05 / $0.19131.1K
137
107162
OpenAI · Proprietary
1414±11
2,944$1.10 / $4.40200K
138
110160
OpenAI · Proprietary
1413±9
4,917$15 / $60N/A
139
114159
OpenAI · Proprietary
1413±7
8,751$0.40 / $1.601M
140
116159
Mistral · Proprietary
1412±7
7,333$0.40 / $2131.1K
141
117164
OpenAI · Proprietary
1410±8
6,483$0.25 / $2400K
142
129166
Anthropic
Anthropic · Proprietary
1405±7
8,831$3 / $15200K
143
133166
Anthropic
Anthropic · Proprietary
1404±5
15,820$3 / $15200K
144
124168
Z.ai · MIT
1404±11
3,077$0.06 / $0.40202.8K
145
105182
Z.ai · MIT
1404±22
715$0.30 / $0.90131.1K
146
131167
1403±8
6,545N/AN/A
147
133167
Z.ai · MIT
1403±7
7,659$0.13 / $0.85131.1K
148
132168
Alibaba · Apache 2.0
1403±8
5,751$0.46 / $1.82131.1K
149
118178
Stepfun
StepFun · Apache 2.0
1402±15
1,564$0.57 / $1.4265.5K
150
124180
Prime Intellect · MIT
1399±15
1,433$0.20 / $1.10131.1K
151
117184
Tencent
Tencent · Proprietary
1399±19
931N/AN/A
152
136177
Mistral · Apache 2.0
1398±9
4,071$0.10 / $0.3032K
153
110191
Nvidia · Nvidia Open Model
1397±27
448$0.60 / $1.80131.1K
154
127184
Z.ai · MIT
1397±16
1,235$0.60 / $1.8065.5K
155
136178
Alibaba · Apache 2.0
1397±10
3,496$0.10 / $0.78262.1K
156
141171
1396±6
12,538$0.10 / $0.401M
157
139173
Arcee AI · Apache 2.0
1396±7
9,138$0.22 / $0.85262.1K
158
136179
1395±11
2,997N/AN/A
159
135182
Nvidia · NVIDIA Open Model
1395±13
2,018N/AN/A
160
142178
MiniMax · Apache 2.0
1394±7
8,155$0.40 / $2.201M
161
138184
Tencent
Tencent · Proprietary
1391±13
2,209N/AN/A
162
141185
Ant Group · MIT
1389±14
1,835N/AN/A
163
146184
Alibaba · Proprietary
1388±8
6,011N/AN/A
164
142185
MiniMax · Apache 2.0
1387±14
1,905$0.26 / $1204.8K
165
119205
1387±29
344N/AN/A
166
150184
OpenAI · Proprietary
1383±6
11,292$1.10 / $4.40200K
167
149185
1383±7
7,542$0.10 / $0.401M
168
133212
Tencent
Tencent · Proprietary
1383±28
367N/AN/A
169
148188
xAI · Proprietary
1382±9
4,048$0.25 / $1.27N/A
170
139200
Alibaba · Apache 2.0
1382±21
729$0.08 / $0.28131.1K
171
149187
xAI · Proprietary
1382±8
5,303$0.30 / $0.50131.1K
172
148194
Ant Group · MIT
1380±13
1,865N/AN/A
173
150194
Amazon · Proprietary
1378±11
3,201$0.30 / $2.501M
174
156190
Cohere
Cohere · CC-BY-NC-4.0
1376±6
12,731$2.50 / $10256K
175
156193
OpenAI · Proprietary
1375±7
8,369$1.10 / $4.40N/A
176
155199
Ai2 · Apache 2.0
1374±11
3,037$0.20 / $0.6065.5K
177
158196
Alibaba · Apache 2.0
1373±8
5,073$0.50 / $116.4K
178
148213
Inception AI · Proprietary
1371±20
865$0.25 / $0.75128K
179
163197
Google · Gemma
1370±6
9,913$0.08 / $0.16131.1K
180
144219
Tencent
Tencent · Proprietary
1369±27
343N/AN/A
181
150214
1369±20
779N/AN/A
182
150215
1368±21
710$0.10 / $0.40131.1K
183
154214
Alibaba · Proprietary
1368±17
964$0.40 / $1.20131.1K
184
158212
OpenAI · Proprietary
1367±13
1,975$0.05 / $0.40400K
185
166202
Google · Proprietary
1367±7
8,535$0.10 / $0.401M
186
166203
OpenAI · Apache 2.0
1367±7
7,640$0.04 / $0.18131.1K
187
167202
Anthropic
Anthropic · Proprietary
1366±7
14,269$3 / $15200K
188
170212
Alibaba · Apache 2.0
1362±8
5,811$0.09 / $0.45131.1K
189
168213
DeepSeek · DeepSeek
1362±10
3,637$1.14 / $4.56N/A
190
169213
01.AI
01 AI · Proprietary
1361±10
3,939N/AN/A
191
170213
Meta
Meta · Llama 3.1 Community
1361±7
6,791$4 / $432.8K
192
168220
Ai2 · Apache 2.0
1357±15
1,505$0.15 / $0.5065.5K
193
176213
Anthropic
Anthropic · Proprietary
1357±6
13,436$0.80 / $4200K
194
177214
Google · Proprietary
1354±7
9,056$3.50 / $10.502.1M
195
173219
Mistral · Proprietary
1354±11
2,776$2 / $540K
196
175216
1354±9
4,113$0.07 / $0.301M
197
179216
Meta
Meta · Llama 3.1 Community
1352±7
9,964$4 / $432.8K
198
181216
1351±7
8,709$0.63 / $1.80131.1K
199
177222
Nvidia · NVIDIA Open Model
1351±10
3,884$0.06 / $0.24262.1K
200
174229
Stepfun
StepFun · Proprietary
1351±13
1,888N/AN/A
201
181219
1350±8
6,657$0.40 / $0.708.2K
202
181219
OpenAI · Proprietary
1349±6
19,579$5 / $15128K
203
173236
Stepfun
StepFun · Proprietary
1347±19
786N/AN/A
204
151251
Ai2 · Apache 2.0
1347±41
218$0.20 / $0.2036.9K
205
181228
NexusFlow · NexusFlow
1347±9
4,039N/AN/A
206
180233
Ai2 · Apache 2.0
1346±13
2,054$0.15 / $0.5065.5K
207
181236
Alibaba · Proprietary
1344±13
1,713N/AN/A
208
170245
Inception AI · Proprietary
1343±26
519$0.25 / $0.75128K
209
180240
IBM · Apache 2.0
1341±18
1,291$0.05 / $0.10131.1K
210
175245
Tencent
Tencent · Proprietary
1340±23
601N/AN/A
211
181242
OpenAI · Proprietary
1339±17
1,062$0.10 / $0.401M
212
192235
OpenAI · Proprietary
1339±8
8,010$2.50 / $10128K
213
189238
OpenAI · Apache 2.0
1339±12
2,448$0.03 / $0.14131.1K
214
196235
Meta
Meta · Llama-3.3
1338±6
10,092$0.10 / $0.32131.1K
215
184244
DeepSeek · DeepSeek
1337±16
1,132N/AN/A
216
181245
Google · Gemma
1337±21
700$0.04 / $0.13131.1K
217
196236
1335±7
7,627$0.10 / $0.3032K
218
201238
Mistral · Mistral Research
1334±8
7,818$2 / $6131.1K
219
202239
Google · Proprietary
1331±7
13,552$3.50 / $10.502.1M
220
202239
xAI · Proprietary
1331±7
10,486$2 / $10131.1K
221
202244
DeepSeek · DeepSeek
1331±9
4,055N/AN/A
222
202245
Alibaba · Qwen
1330±11
2,531$1.60 / $6.4032.8K
223
204242
OpenAI · Proprietary
1329±7
17,922$10 / $30128K
224
203244
Google · Proprietary
1329±9
8,405N/AN/A
225
204244
Alibaba · Qwen
1328±8
6,208$1.20 / $1.20N/A
226
196247
1327±17
1,136$1.20 / $1.20131.1K
227
204245
Z.ai · Proprietary
1327±10
4,016$0.44 / $1.76204.8K
228
205244
Anthropic
Anthropic · Proprietary
1326±6
34,293$15 / $75200K
229
201247
IBM · Apache 2.0
1326±15
1,596N/AN/A
230
204246
NexusFlow · CC-BY-NC-4.0
1325±10
3,605N/AN/A
231
200251
Z.ai · Proprietary
1324±18
955N/AN/A
232
207245
OpenAI · Proprietary
1324±7
18,316$10 / $30128K
233
205246
Mistral · MRL
1324±9
4,452$2 / $6128K
234
193254
Tencent
Tencent · Proprietary
1323±24
587N/AN/A
235
202251
Tencent
Tencent · Proprietary
1323±17
1,203N/AN/A
236
210246
OpenAI · Proprietary
1321±6
11,377$0.15 / $0.60128K
237
202254
Alibaba · Apache 2.0
1319±20
759$0.87 / $0.8732K
238
212247
OpenAI · Proprietary
1319±7
16,792$10 / $30128K
239
210248
Google · Gemma
1318±9
4,554$0.06 / $0.1232.8K
240
215249
xAI · Proprietary
1315±7
8,664$2 / $10131.1K
241
214251
Amazon · Proprietary
1315±9
4,069$0.80 / $3.20300K
242
217250
Meta
Meta · Llama 3.1 Community
1314±7
9,133$0.40 / $0.40131.1K
243
215252
OpenAI · Proprietary
1314±9
9,838$30 / $608.2K
244
217252
Google · Proprietary
1313±8
5,484$0.07 / $0.301M
245
228253
Meta
Meta · Llama 3 Community
1310±7
29,608$0.51 / $0.748.2K
246
236260
OpenAI · Proprietary
1300±8
16,244$30 / $608.2K
247
234265
DeepSeek · DeepSeek License
1298±12
2,699$0.14 / $0.28128K
248
222274
Ai2 · Apache-2.0
1296±24
538$0.05 / $0.20128K
249
237267
Mistral · Apache 2.0
1295±12
2,355$0.05 / $0.0832.8K
250
235269
AI21 Labs · Jamba Open
1295±14
1,528$2 / $8256K
251
244265
Google · Proprietary
1293±7
10,974$0.07 / $0.301M
252
231276
Ai2 · Llama 3.1
1290±23
499N/AN/A
253
246269
Microsoft · MIT
1290±9
3,804$0.07 / $0.1416.4K
254
246268
Google · Gemma license
1289±6
12,606$0.65 / $0.658.2K
255
247269
Anthropic
Anthropic · Proprietary
1285±7
19,193$3 / $15200K
256
246274
Z.ai · Proprietary
1285±14
1,775N/AN/A
257
247271
Alibaba · Qianwen LICENSE
1284±9
6,483$0.90 / $0.9032.8K
258
243278
Google · Gemma
1283±20
764$0.04 / $0.08131.1K
259
246276
Reka AI · Proprietary
1282±14
1,341N/AN/A
260
247276
Nvidia · NVIDIA Open Model
1280±11
3,257N/AN/A
261
246277
Princeton · MIT
1279±14
1,661$0.03 / $0.098.2K
262
247276
Amazon · Proprietary
1278±10
3,136$0.06 / $0.24300K
263
241292
Tencent
Tencent · Proprietary
1277±28
370N/AN/A
264
246284
1277±22
578N/AN/A
265
249276
Cohere
Cohere · CC-BY-NC-4.0
1276±9
4,272N/AN/A
266
251278
Mistral · Proprietary
1273±8
11,296$4 / $1232K
267
249283
Reka AI · Proprietary
1271±14
1,389N/AN/A
268
250283
Cohere
Cohere · CC-BY-NC-4.0
1270±13
1,735$2.50 / $10128K
269
254279
Anthropic
Anthropic · Proprietary
1269±7
20,673$0.25 / $1.25200K
270
247296
Mistral · MRL
1266±20
703$0.10 / $0.10131.1K
271
255283
Google · Proprietary
1266±8
5,581$0.07 / $0.301M
272
255286
Alibaba · Qianwen LICENSE
1264±10
4,572N/AN/A
273
254292
Cohere
Cohere · CC-BY-NC-4.0
1262±13
1,822$0.15 / $0.60128K
274
257283
Google · Gemma license
1262±7
9,094$0.03 / $0.098.2K
275
263292
Cohere
Cohere · CC-BY-NC-4.0
1257±8
13,980$2.50 / $10128K
276
257298
InternLM · Other
1256±15
1,456$0 / $032.8K
277
262296
Amazon · Proprietary
1256±10
3,050$0.04 / $0.14128K
278
265296
Mistral · Apache 2.0
1254±8
9,466$0.90 / $0.9065.5K
279
266298
Alibaba · Qianwen LICENSE
1251±9
7,597N/AN/A
280
255301
IBM · Apache 2.0
1249±24
517N/AN/A
281
266300
AI21 Labs · Jamba Open
1248±14
1,545$0.20 / $0.40256K
282
272299
Meta
Meta · Llama 3 Community
1244±7
19,891$0.14 / $0.148.2K
283
270301
Reka AI · Proprietary
1242±13
2,928N/AN/A
284
272300
Mistral · Proprietary
1242±10
6,398$2.70 / $8.1032K
285
266304
Google · Proprietary
1241±19
1,189$0.35 / $1.0532.8K
286
272301
01.AI
01 AI · Apache-2.0
1241±10
3,931N/AN/A
287
275300
Meta
Meta · Llama 3.1 Community
1240±8
8,195$0.02 / $0.03131.1K
288
271301
OpenAI · Proprietary
1239±14
3,150$1 / $216.4K
289
275300
OpenAI · Proprietary
1239±8
12,416$0.50 / $1.5016.4K
290
272301
Reka AI · Proprietary
1239±11
4,796N/AN/A
291
266311
IBM · Apache 2.0
1237±24
511N/AN/A
292
275301
Databricks · DBRX LICENSE
1236±11
5,516$0.60 / $0.6032.8K
293
275303
Google · Proprietary
1236±13
3,298$0.35 / $1.0532.8K
294
271309
IBM · Apache 2.0
1235±20
900N/AN/A
295
277302
Alibaba · Qianwen LICENSE
1235±11
3,830N/AN/A
296
278308
Cohere
Cohere · CC-BY-NC-4.0
1231±14
1,620N/AN/A
297
272316
HuggingFace · Apache 2.0
1229±21
820N/AN/A
298
280307
Microsoft · MIT
1228±10
4,087$0.17 / $0.68N/A
299
281305
Mistral · Apache 2.0
1228±8
13,360$0.63 / $0.6332K
300
272319
Ai2 · Llama 3.1
1225±26
452N/AN/A
301
285310
Cohere
Cohere · CC-BY-NC-4.0
1222±9
9,264$0.15 / $0.60128K
302
291319
Microsoft · MIT
1212±12
3,070$0.15 / $0.60N/A
303
292322
Meta
Meta · Llama 3.2
1208±15
1,377$0.05 / $0.34131.1K
304
294321
Alibaba · Qianwen LICENSE
1208±13
3,024$0.30 / $0.30N/A
305
296320
Google · Gemma license
1208±10
4,180$0.03 / $0.098.2K
306
295322
Nexusflow · Apache-2.0
1207±13
2,864N/AN/A
307
293325
AllenAI/UW · AI2 ImpACT Low-risk
1205±18
1,200N/AN/A
308
300322
Snowflake · Apache 2.0
1201±11
6,488N/AN/A
309
298325
1201±13
2,028$0.13 / $0.524.1K
310
300327
01.AI
01 AI · Yi License
1197±12
2,844$0.90 / $0.904.1K
311
300330
OpenChat · Apache-2.0
1196±13
2,468N/AN/A
312
301325
Google · Gemma license
1195±8
7,586N/AN/A
313
299331
NousResearch · Apache-2.0
1195±19
917$0.17 / $0.17N/A
314
300333
IBM · Apache 2.0
1192±19
974N/AN/A
315
300333
DeepSeek · DeepSeek License
1189±20
946N/AN/A
316
297340
MosaicML · CC-BY-NC-SA-4.0
1186±30
359N/AN/A
317
301333
Microsoft · Llama 2 Community
1186±16
1,475N/AN/A
318
303333
UC Berkeley · CC-BY-NC-4.0
1185±14
1,894N/AN/A
319
295345
Meta
Meta · Llama 2 Community
1182±36
207$0.70 / $2.8016.4K
320
305338
OpenChat · Apache-2.0
1178±17
1,389$0.20 / $0.20N/A
321
308336
Microsoft · MIT
1177±12
3,447$0.13 / $0.52N/A
322
301341
Alibaba · Apache 2.0
1177±25
519$0.50 / $116.4K
323
312336
Meta
Meta · Llama 2 Community
1175±9
6,989$0.70 / $2.804.1K
324
311338
LMSYS · Non-commercial
1174±11
3,964$0 / $02K
325
311338
Mistral · Apache-2.0
1174±11
3,709$0.20 / $0.2032.8K
326
312341
Google · Gemma license
1168±15
1,588$0.05 / $0.088.2K
327
308344
Upstage AI · CC-BY-NC-4.0
1168±22
765$0.30 / $0.30N/A
328
312341
Google · Proprietary
1168±17
1,366$0.50 / $0.5025.8K
329
304346
Cognitive Computations · Apache-2.0
1166±31
286$0.50 / $0.5016.4K
330
308349
HuggingFace · Apache 2.0
1158±32
334N/AN/A
331
314346
Alibaba · Qianwen LICENSE
1157±18
1,019$0.20 / $0.20N/A
332
318345
Meta
Meta · Llama 2 Community
1156±12
3,347$0.25 / $0.254.1K
333
313347
Nvidia · Llama 2 Community
1155±23
645N/AN/A
334
318346
Meta
Meta · Llama 3.2
1154±15
1,437$0.03 / $0.20131.1K
335
314347
Alibaba · Qianwen LICENSE
1152±20
830N/AN/A
336
320346
Microsoft · MIT
1152±13
4,149$0.13 / $0.52N/A
337
320346
Google · Gemma license
1150±14
1,941N/AN/A
338
323348
Meta
Meta · Llama 2 Community
1145±16
1,278$0.35 / $1.4016.4K
339
323349
NousResearch · Apache-2.0
1142±19
929$0.90 / $0.90N/A
340
324348
LMSYS · Llama 2 Community
1141±12
3,220$0.30 / $0.30N/A
341
318353
HuggingFace · MIT
1136±33
278N/AN/A
342
327349
HuggingFace · MIT
1135±16
1,847$0.15 / $0.1516.4K
343
327350
Mistral · Apache 2.0
1131±17
1,616$0.07 / $0.284.1K
344
327351
Microsoft · Llama 2 Community
1128±18
1,066$0.30 / $0.30N/A
345
330351
Together AI · Apache 2.0
1122±18
1,029$0.20 / $0.20N/A
346
328353
UW · Non-commercial
1118±28
434N/AN/A
347
339353
Meta
Meta · Llama 2 Community
1115±12
2,560$0.15 / $0.154.1K
348
335353
Google · Gemma license
1114±20
832$0.10 / $0.10N/A
349
337353
LMSYS · Llama 2 Community
1112±19
1,066$0.20 / $0.20N/A
350
343353
Alibaba · Qianwen LICENSE
1098±16
1,419$0.10 / $0.10N/A
351
345355
Ai2 · Apache-2.0
1085±19
1,076$0.20 / $0.20N/A
352
345356
Tsinghua · Apache-2.0
1082±21
835N/AN/A
353
342357
Nomic AI · Non-commercial
1081±34
287N/AN/A
354
351360
Tsinghua · Apache-2.0
1048±29
408N/AN/A
355
351360
MosaicML · CC-BY-NC-SA-4.0
1043±24
626N/AN/A
356
352359
UC Berkeley · Non-commercial
1043±20
1,100N/AN/A
357
353360
OpenAssistant · Apache 2.0
1033±21
1,002N/AN/A
358
354361
RWKV · Apache 2.0
1021±23
771N/AN/A
359
354360
Stanford · Non-commercial
1020±22
899N/AN/A
360
355362
Tsinghua · Non-commercial
997±24
732N/AN/A
361
359364
Databricks · MIT
972±27
523N/AN/A
362
360364
Stability
Stability AI · CC-BY-NC-SA-4.0
956±27
497N/AN/A
363
361364
LMSYS · Apache 2.0
945±23
690N/AN/A
364
361364
Meta
Meta · Non-commercial
918±34
371$0.23 / $0.23N/A

Default Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

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

Battle Count for Each Combination of Models (without Ties)

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