Text Arena | Expert

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

Mar 16, 2026
270,149 votes
276 models
Rank Spread
1
15
Anthropic
Anthropic · Proprietary
1551±21
854$5 / $251M
2
112
Anthropic
Anthropic · Proprietary
1538±24
647$5 / $251M
3
125
OpenAI · Proprietary
1520±31
374$2.50 / $151.1M
4
119
Google · Proprietary
1517±19
989$2 / $121M
5
136
OpenAI · Proprietary
1507±32
346$2.50 / $151.1M
6
225
Anthropic
Anthropic · Proprietary
1503±13
2,316$5 / $25200K
7
225
Anthropic
1503±14
2,014$5 / $25200K
8
233
Anthropic
Anthropic · Proprietary
1502±24
628$3 / $151M
9
326
Google · Proprietary
1499±12
2,511$2 / $121M
10
326
Anthropic
1498±12
2,843$3 / $15200K
11
329
Google · Proprietary
1497±14
1,900$0.50 / $31M
12
237
OpenAI · Proprietary
1497±23
653$1.75 / $14128K
13
243
xAI · Proprietary
1496±28
429N/AN/A
14
255
1489±33
282N/AN/A
15
261
1488±36
255N/AN/A
16
344
Bytedance
Bytedance · Proprietary
1487±22
698N/AN/A
17
345
MoonshotAI
Moonshot · Modified MIT
1483±19
975$0.60 / $3N/A
18
347
Z.ai · MIT
1483±22
690$0.72 / $2.30202.8K
19
437
Anthropic
Anthropic · Proprietary
1483±11
2,899$3 / $15200K
20
441
Anthropic
1481±13
2,287$15 / $75200K
21
444
OpenAI · Proprietary
1479±13
2,177$1.25 / $10400K
22
444
xAI · Proprietary
1479±12
2,461$0.20 / $0.50N/A
23
380
1472±36
253N/AN/A
24
754
OpenAI · Proprietary
1472±16
1,499$1.75 / $14400K
25
468
OpenAI · Proprietary
1472±26
513$1.75 / $14128K
26
956
1470±15
1,719$0.50 / $31M
27
961
Qwen Icon
Alibaba · Proprietary
1468±17
1,232$0.78 / $3.90262.1K
28
1156
Anthropic
Anthropic · Proprietary
1466±10
3,858$15 / $75200K
29
1254
Google · Proprietary
1465±9
5,497$1.25 / $101M
30
972
MoonshotAI
Moonshot · Modified MIT
1465±21
780$0.45 / $2.20262.1K
31
480
Qwen Icon
Alibaba · Apache 2.0
1464±28
421$0.11 / $0.60262.1K
32
1067
OpenAI · Proprietary
1463±16
1,424$1.75 / $14400K
33
1172
OpenAI · Proprietary
1460±16
1,603$1.25 / $10400K
34
1472
OpenAI · Proprietary
1457±12
2,575$1.25 / $10400K
35
1472
xAI · Proprietary
1457±12
2,646$0.20 / $0.50N/A
36
1472
MoonshotAI
Moonshot · Modified MIT
1456±13
2,289$1.15 / $8262.1K
37
1088
Qwen Icon
Alibaba · Apache 2.0
1455±27
423$0.26 / $2.08262.1K
38
1088
Qwen Icon
Alibaba · Apache 2.0
1455±26
434$0.20 / $1.56262.1K
39
1186
Qwen Icon
Alibaba · Apache 2.0
1455±22
689$0.39 / $2.34262.1K
40
2178
Qwen Icon
Alibaba · Apache 2.0
1450±10
4,002$0.26 / $1.06N/A
41
2087
Baidu
Baidu · Proprietary
1447±17
1,160N/AN/A
42
1590
Minimax
MiniMax · Modified MIT
1447±21
747$0.25 / $1.20196.6K
43
1590
Baidu
Baidu · Proprietary
1446±23
661N/AN/A
44
2187
DeepSeek · MIT
1445±15
1,708$0.26 / $0.38163.8K
45
2384
Anthropic
Anthropic · Proprietary
1445±12
2,929$1 / $5200K
46
2187
DeepSeek · MIT
1445±14
2,061$0.26 / $0.38163.8K
47
2187
Anthropic
Anthropic · Proprietary
1444±14
1,727$15 / $75200K
48
2188
OpenAI · Proprietary
1444±16
1,421$1.25 / $10128K
49
10106
Baidu
Baidu · Proprietary
1442±36
254N/AN/A
50
1697
Qwen Icon
Alibaba · Apache 2.0
1442±25
560$0.20 / $0.88262.1K
51
2687
OpenAI · Proprietary
1441±11
2,983$2 / $8200K
52
14102
1441±30
373$0.27 / $0.41163.8K
53
2095
Z.ai · MIT
1440±23
680$0.38 / $1.98202.8K
54
2190
Z.ai · MIT
1440±18
1,108$0.60 / $2.20131.1K
55
2690
1437±15
1,578$0.30 / $2.501M
56
2890
Z.ai · MIT
1436±14
1,816$0.39 / $1.90204.8K
57
2892
xAI · Proprietary
1434±14
2,027$3 / $15256K
58
2990
Anthropic
Anthropic · Proprietary
1434±12
2,265$15 / $75200K
59
2895
Anthropic
1433±15
1,676$3 / $151M
60
26102
DeepSeek · MIT
1432±22
727$1.23 / $4.94N/A
61
3095
xAI · Proprietary
1432±13
2,093$0.20 / $0.502M
62
28102
Minimax
MiniMax · MIT
1431±19
1,043$0.27 / $0.95196.6K
63
26107
DeepSeek · MIT
1431±25
542$1.23 / $4.94N/A
64
19118
Google · Proprietary
1429±36
252$0.25 / $1.501M
65
26107
OpenAI · Proprietary
1429±23
608$75 / $150128K
66
3695
OpenAI · Proprietary
1428±9
4,289$5 / $15128K
67
3896
Google · Proprietary
1426±8
5,594$0.30 / $2.501M
68
24116
Qwen Icon
Alibaba · Apache 2.0
1425±31
359$0.26 / $2.60131.1K
69
28113
Meituan · MIT
1424±26
521$0.20 / $0.80131.1K
70
21123
xAI · Proprietary
1423±34
311$3 / $15256K
71
28114
Qwen Icon
Alibaba · Apache 2.0
1422±27
466$0.16 / $1.30262.1K
72
30113
DeepSeek · MIT
1422±24
593$0.27 / $0.41163.8K
73
35110
xAI · Proprietary
1420±21
830$0.20 / $0.502M
74
39107
Mistral · Apache 2.0
1419±14
1,973$0.50 / $1.50N/A
75
30118
Arcee AI
Arcee AI · Apache 2.0
1419±26
472N/AN/A
76
35113
1419±22
679$0.09 / $0.29262.1K
77
30121
Qwen Icon
Alibaba · Proprietary
1418±27
440$0.78 / $3.90262.1K
78
35117
MoonshotAI
Moonshot · Modified MIT
1418±25
555$0.60 / $2.50262.1K
79
38108
1418±16
1,398N/AN/A
80
35122
Qwen Icon
Alibaba · Proprietary
1416±26
470N/AN/A
81
38114
DeepSeek · MIT
1415±19
909$0.45 / $2.15163.8K
82
45113
MoonshotAI
Moonshot · Modified MIT
1414±16
1,518$0.60 / $2.50131.1K
83
39116
Stepfun
StepFun · Apache 2.0
1413±20
859$0.10 / $0.30256K
84
48114
1411±15
1,557$0.09 / $0.29262.1K
85
55110
Mistral · Proprietary
1410±10
3,794$2.70 / $8.1032K
86
54117
Anthropic
1407±14
1,907$3 / $15200K
87
54121
xAI · Proprietary
1406±15
1,573$3 / $15131.1K
88
48124
Microsoft AI · Proprietary
1405±21
768N/AN/A
89
60118
OpenAI · Proprietary
1405±13
2,282$1.10 / $4.40200K
90
61118
OpenAI · Proprietary
1404±12
2,543$2 / $81M
91
36134
1403±36
244N/AN/A
92
35136
Tencent
Tencent · Proprietary
1403±39
211N/AN/A
93
35139
Z.ai · MIT
1402±41
197$0.60 / $1.8065.5K
94
55126
OpenAI · Proprietary
1402±19
1,112$0.25 / $2400K
95
55126
xAI · Proprietary
1400±19
946$0.30 / $0.50131.1K
96
61126
OpenAI · Proprietary
1400±17
1,330$15 / $60200K
97
61123
Anthropic
Anthropic · Proprietary
1399±13
2,102$3 / $151M
98
59129
DeepSeek · MIT
1398±20
848$0.70 / $2.5064K
99
40136
Nvidia
Nvidia · NVIDIA Open Model
1398±34
289N/AN/A
100
38139
Qwen Icon
Alibaba · Apache 2.0
1397±38
236$0.08 / $0.2441K
101
61130
OpenAI · Proprietary
1396±20
847$1.10 / $4.40200K
102
64126
Qwen Icon
Alibaba · Apache 2.0
1396±14
1,938$0.46 / $1.82131.1K
103
61129
Qwen Icon
Alibaba · Apache 2.0
1395±19
986$0.09 / $1.10131.1K
104
64126
DeepSeek · MIT
1394±12
2,334$3 / $4.5032.8K
105
64133
Qwen Icon
Alibaba · Apache 2.0
1392±17
1,144$0.09 / $0.30262.1K
106
68134
Z.ai · MIT
1388±16
1,368$0.13 / $0.85131.1K
107
71133
1386±12
2,481$0.10 / $0.401M
108
65135
Z.ai · MIT
1386±20
804$0.06 / $0.40202.8K
109
71134
Anthropic
Anthropic · Proprietary
1386±13
2,166$3 / $15200K
110
64138
Qwen Icon
Alibaba · Apache 2.0
1385±24
608$0.10 / $0.78131.1K
111
69134
Qwen Icon
Alibaba · Apache 2.0
1384±16
1,354$0.46 / $1.82131.1K
112
74134
OpenAI · Proprietary
1383±13
2,051$0.40 / $1.601M
113
86135
Mistral · Proprietary
1379±14
1,823$0.40 / $2131.1K
114
82136
OpenAI · Proprietary
1379±14
1,982$15 / $60N/A
115
78138
Qwen Icon
Alibaba · Apache 2.0
1378±16
1,382$0.40 / $1.60262.1K
116
88140
xAI · Proprietary
1373±17
1,218$0.30 / $0.50131.1K
117
71154
Qwen Icon
Alibaba · Proprietary
1370±30
358$0.40 / $1.20131.1K
118
92142
Minimax
MiniMax · Apache 2.0
1369±15
1,634$0.40 / $2.201M
119
86148
1369±24
631N/AN/A
120
97142
Qwen Icon
Alibaba · Proprietary
1368±14
1,695N/AN/A
121
97143
1366±15
1,626$0.10 / $0.401M
122
100140
Anthropic
Anthropic · Proprietary
1366±9
5,071$6 / $30200K
123
99142
OpenAI · Proprietary
1365±11
2,906$1.10 / $4.40200K
124
97147
Qwen Icon
Alibaba · Apache 2.0
1363±17
1,216$0.15 / $0.4032.8K
125
91154
Amazon · Proprietary
1363±22
700$0.30 / $2.501M
126
80158
AntGroup
Ant Group · MIT
1363±31
332N/AN/A
127
78160
AntGroup
Ant Group · MIT
1361±33
328N/AN/A
128
69173
Nvidia
1359±41
185$0.10 / $0.40131.1K
129
100154
OpenAI · Apache 2.0
1359±17
1,294$0.04 / $0.19131.1K
130
86167
Stepfun
StepFun · Apache 2.0
1357±35
256$0.57 / $1.4265.5K
131
89166
OpenAI · Proprietary
1356±34
319$0.05 / $0.40400K
132
107154
Google · Proprietary
1354±13
2,215$0.10 / $0.401M
133
100161
Tencent
Tencent · Proprietary
1352±24
599N/AN/A
134
114154
OpenAI · Proprietary
1350±11
3,191$1.10 / $4.40N/A
135
92175
PrimeIntellect
Prime Intellect · MIT
1350±35
311$0.20 / $1.10131.1K
136
112160
DeepSeek · DeepSeek
1346±16
1,236$1.14 / $4.56N/A
137
112160
Qwen Icon
Alibaba · Apache 2.0
1345±16
1,353$0.08 / $0.2841K
138
109163
Nvidia
Nvidia · NVIDIA Open Model
1344±20
930$0.06 / $0.24262.1K
139
122161
Cohere
Cohere · CC-BY-NC-4.0
1338±11
2,799$2.50 / $10256K
140
122161
Anthropic
Anthropic · Proprietary
1338±11
4,314$6 / $30200K
141
102188
Minimax
MiniMax · Apache 2.0
1337±36
249$0.26 / $1196.6K
142
124163
Google · Proprietary
1334±11
3,319$3.50 / $10.502.1M
143
121175
Mistral · Apache 2.0
1333±19
882$0.10 / $0.3032K
144
118181
AllenAI
Ai2 · Apache 2.0
1333±23
738$0.20 / $0.6065.5K
145
124172
Google · Gemma
1332±13
2,269$0.03 / $0.11128K
146
124175
01.AI
01 AI · Proprietary
1330±14
1,533N/AN/A
147
124178
1328±16
1,237$0.07 / $0.301M
148
118193
Stepfun
StepFun · Proprietary
1324±31
310N/AN/A
149
129182
1322±13
2,040$0.63 / $1.80131.1K
150
116196
Tencent
Tencent · Proprietary
1321±36
228N/AN/A
151
124188
Qwen Icon
Alibaba · Proprietary
1321±21
664N/AN/A
152
122192
AllenAI
Ai2 · Apache 2.0
1321±27
492$0.15 / $0.5065.5K
153
130182
Meta
Meta · Llama 3.1 Community
1319±11
3,123$4 / $432.8K
154
123194
OpenAI · Apache 2.0
1318±28
488$0.03 / $0.14131.1K
155
136188
Google · Proprietary
1314±12
3,896$3.50 / $10.502.1M
156
139188
Anthropic
Anthropic · Proprietary
1312±9
10,374$15 / $75200K
157
124199
OpenAI · Proprietary
1312±31
328$0.10 / $0.401M
158
138188
xAI · Proprietary
1312±11
3,541$2 / $10131.1K
159
122207
AllenAI
Ai2 · Apache 2.0
1311±38
268$0.15 / $0.5065.5K
160
136191
NexusFlow · NexusFlow
1310±15
1,469N/AN/A
161
140188
Anthropic
Anthropic · Proprietary
1309±10
3,551$0.80 / $4200K
162
141188
OpenAI · Proprietary
1308±10
5,887$5 / $15128K
163
140191
OpenAI · Proprietary
1308±12
2,349$2.50 / $10128K
164
129202
Zhipu · Proprietary
1308±29
354N/AN/A
165
138194
1307±15
1,655$0.10 / $0.3032K
166
140191
Meta
Meta · Llama 3.1 Community
1306±13
2,128$4 / $432.8K
167
138194
1306±16
1,538$0.40 / $0.708.2K
168
130201
DeepSeek · DeepSeek
1305±26
441N/AN/A
169
129209
Tencent
Tencent · Proprietary
1305±33
294N/AN/A
170
142195
Zhipu AI · Proprietary
1301±15
1,608$0.44 / $1.76204.8K
171
129214
IBM · Apache 2.0
1298±38
270N/AN/A
172
146196
Mistral · Mistral Research
1298±12
2,505$2 / $6131.1K
173
142201
Qwen Icon
Alibaba · Qwen
1298±18
1,011$1.60 / $6.4032.8K
174
145204
NexusFlow · CC-BY-NC-4.0
1295±19
867N/AN/A
175
140211
Stepfun
StepFun · Proprietary
1294±26
496N/AN/A
176
147201
DeepSeek · DeepSeek
1294±15
1,523N/AN/A
177
149197
Meta
Meta · Llama-3.3
1293±11
2,920$0.10 / $0.32131.1K
178
149199
Qwen Icon
Alibaba · Qwen
1293±12
2,397$1.20 / $1.20N/A
179
149198
OpenAI · Proprietary
1293±11
5,195$10 / $30128K
180
140212
Nvidia
1292±27
453$1.20 / $1.20131.1K
181
149201
xAI · Proprietary
1292±11
2,759$2 / $10131.1K
182
149202
Google · Proprietary
1291±14
2,449N/AN/A
183
133218
Tencent
Tencent · Proprietary
1289±39
207N/AN/A
184
146214
Reka AI · Proprietary
1287±25
458N/AN/A
185
145214
Mistral · Proprietary
1286±27
565$2 / $540K
186
156207
OpenAI · Proprietary
1285±12
4,240$10 / $30128K
187
159209
OpenAI · Proprietary
1283±11
3,552$0.15 / $0.60128K
188
146218
AI21 Labs · Jamba Open
1282±29
331$2 / $8256K
189
161211
Google · Proprietary
1279±13
2,116$0.07 / $0.301M
190
156214
Google · Gemma
1277±18
1,097$0.02 / $0.0432.8K
191
164213
OpenAI · Proprietary
1276±12
4,454$10 / $30128K
192
149226
Qwen Icon
Alibaba · Apache 2.0
1274±33
267$0.87 / $0.8732K
193
165218
Amazon · Proprietary
1271±16
1,387$0.80 / $3.20300K
194
145236
Google · Gemma
1270±42
186$0.04 / $0.13131.1K
195
160223
Reka AI · Proprietary
1270±23
493N/AN/A
196
171214
Meta
Meta · Llama 3.1 Community
1270±11
2,924$0.40 / $0.40131.1K
197
168218
Mistral · MRL
1268±15
1,510$2 / $6131.1K
198
175218
Anthropic
Anthropic · Proprietary
1267±12
5,614$3 / $15200K
199
169223
Azure
Microsoft · MIT
1265±17
1,124$0.06 / $0.1416.4K
200
178218
Google · Proprietary
1262±12
3,194$0.07 / $0.301M
201
167227
DeepSeek · DeepSeek License
1261±21
769$0.14 / $0.28128K
202
178224
Cohere
Cohere · CC-BY-NC-4.0
1260±14
1,764N/AN/A
203
177225
Amazon · Proprietary
1259±17
1,138$0.06 / $0.24300K
204
180226
OpenAI · Proprietary
1257±15
2,160$30 / $608.2K
205
177232
Mistral · Apache 2.0
1256±21
754$0.05 / $0.0832.8K
206
156241
Google · Gemma
1256±41
208$0.04 / $0.08131.1K
207
182226
Qwen Icon
Alibaba · Qianwen LICENSE
1255±14
1,763$0.90 / $0.9032.8K
208
178232
Nvidia
Nvidia · NVIDIA Open Model
1255±19
1,027N/AN/A
209
186225
Google · Gemma license
1253±10
4,025$0.65 / $0.658.2K
210
180238
Zhipu AI · Proprietary
1248±25
514N/AN/A
211
171241
Nvidia
1247±33
265N/AN/A
212
191232
Anthropic
Anthropic · Proprietary
1247±11
6,336$0.25 / $1.25200K
213
191235
OpenAI · Proprietary
1245±13
3,617$30 / $608.2K
214
182239
Cohere
Cohere · CC-BY-NC-4.0
1245±25
524$2.50 / $10128K
215
191238
Amazon · Proprietary
1241±17
1,094$0.04 / $0.14128K
216
197236
Meta
Meta · Llama 3 Community
1238±11
7,958$0.51 / $0.748.2K
217
197238
Google · Proprietary
1237±13
2,111$0.07 / $0.301M
218
197238
Cohere
Cohere · CC-BY-NC-4.0
1236±12
4,031$2.50 / $10128K
219
185244
Mistral · MRL
1234±30
332$0.10 / $0.10131.1K
220
202239
Google · Gemma license
1230±12
2,847$0.03 / $0.098.2K
221
184251
IBM · Apache 2.0
1230±35
237N/AN/A
222
200241
Qwen Icon
Alibaba · Qianwen LICENSE
1229±15
1,846N/AN/A
223
191248
Princeton · MIT
1228±29
369$0.03 / $0.098.2K
224
197245
Cohere
Cohere · CC-BY-NC-4.0
1226±24
600N/AN/A
225
199245
Cohere
Cohere · CC-BY-NC-4.0
1225±22
604$0.15 / $0.60128K
226
206242
Qwen Icon
Alibaba · Qianwen LICENSE
1223±16
1,411N/AN/A
227
206241
Mistral · Proprietary
1222±14
2,940$4 / $1232K
228
206245
Mistral · Proprietary
1220±17
1,357$2.70 / $8.1032K
229
205249
Reka AI · Proprietary
1219±21
830N/AN/A
230
209247
Qwen Icon
Alibaba · Qianwen LICENSE
1217±18
1,176N/AN/A
231
209250
01.AI
01 AI · Apache-2.0
1216±18
1,049N/AN/A
232
206251
InternLM
InternLM · Other
1216±22
604$0 / $032.8K
233
197258
IBM · Apache 2.0
1212±36
225N/AN/A
234
212249
Mistral · Apache 2.0
1212±14
2,582$0.90 / $0.9065.5K
235
212251
Reka AI · Proprietary
1210±17
1,325N/AN/A
236
206258
AI21 Labs · Jamba Open
1208±31
332$0.20 / $0.40256K
237
216251
Cohere
Cohere · CC-BY-NC-4.0
1208±14
2,830$0.15 / $0.60128K
238
209257
OpenAI · Proprietary
1206±28
437$1 / $216.4K
239
218251
Meta
Meta · Llama 3 Community
1204±12
5,360$0.03 / $0.048.2K
240
218254
Azure
Microsoft · MIT
1200±18
1,091$0.17 / $0.68N/A
241
210261
IBM · Apache 2.0
1198±31
345N/AN/A
242
223254
Meta
Meta · Llama 3.1 Community
1194±12
2,589$0.02 / $0.0516.4K
243
224258
Mistral · Apache 2.0
1190±13
3,240$0.63 / $0.6332K
244
227258
OpenAI · Proprietary
1189±13
3,207$0.50 / $1.5016.4K
245
222261
Qwen Icon
Alibaba · Qianwen LICENSE
1188±20
944$0.30 / $0.30N/A
246
227261
Databricks · DBRX LICENSE
1183±16
1,678$0.60 / $0.6032.8K
247
231268
Meta
Meta · Llama 3.2
1173±25
499$0.05 / $0.3480K
248
232268
Google · Proprietary
1171±24
694$0.35 / $1.0532.8K
249
228270
IBM · Apache 2.0
1171±29
407N/AN/A
250
237266
Nexusflow · Apache-2.0
1169±20
952N/AN/A
251
223273
HuggingFace
HuggingFace · Apache 2.0
1165±40
219N/AN/A
252
240266
Google · Gemma license
1165±13
2,525N/AN/A
253
237268
Google · Gemma license
1165±18
1,247$0.03 / $0.098.2K
254
239270
Azure
Microsoft · MIT
1160±19
895$0.15 / $0.60N/A
255
239271
OpenChat
OpenChat · Apache-2.0
1157±23
611N/AN/A
256
244271
Snowflake
Snowflake · Apache 2.0
1157±17
1,722N/AN/A
257
229274
OpenChat
OpenChat · Apache-2.0
1156±42
194$0.20 / $0.20N/A
258
237274
Qwen Icon
Alibaba · Apache 2.0
1152±36
232$0.15 / $0.4032.8K
259
244273
01.AI
01 AI · Yi License
1150±25
559$0.90 / $0.904.1K
260
244273
1143±26
486$0.13 / $0.524.1K
261
239276
Qwen Icon
Alibaba · Qianwen LICENSE
1142±37
231$0.20 / $0.20N/A
262
247274
LMSYS · Non-commercial
1139±27
484$0 / $02K
263
247274
Azure
Microsoft · MIT
1135±19
936$0.13 / $0.52N/A
264
247274
Mistral · Apache-2.0
1134±21
798$0.20 / $0.2032.8K
265
247276
UC Berkeley · CC-BY-NC-4.0
1132±31
318N/AN/A
266
249274
Meta
Meta · Llama 2 Community
1132±17
1,356$0.70 / $2.804.1K
267
247276
Meta
Meta · Llama 2 Community
1128±28
411$0.15 / $0.154.1K
268
249276
Meta
Meta · Llama 2 Community
1123±25
539$0.25 / $0.254.1K
269
252276
Google · Gemma license
1113±31
340$0.05 / $0.088.2K
270
254276
LMSYS · Llama 2 Community
1110±31
321$0.30 / $0.30N/A
271
256276
Google · Gemma license
1107±26
578N/AN/A
272
252276
HuggingFace
HuggingFace · MIT
1107±38
201$0.15 / $0.1516.4K
273
256276
Qwen Icon
Alibaba · Qianwen LICENSE
1100±31
356$0.10 / $0.10N/A
274
265276
Azure
Microsoft · MIT
1091±20
1,095$0.13 / $0.52N/A
275
265276
Meta
Meta · Llama 3.2
1078±28
487$0.03 / $0.2060K
276
259276
Mistral · Apache 2.0
1077±40
183$0.07 / $0.284.1K

Default Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

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

Confidence Intervals on Model Strength (via Bootstrapping)

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