For frontier AI news

Leaderboard Overview

See how leading models stack up across text, image, vision, and beyond. This page gives you a snapshot of each Arena, you can explore deeper insights in their dedicated tabs. Learn more about it here.

Arena Overview

Scroll to the right to see full stats of each model

First Place
Second Place
Third Place
gemini-3-pro
1
1
1
1
1
1
1
1
grok-4.1-thinking
1
2
1
1
2
3
6
2
Anthropicclaude-opus-4-5-20251101
2
1
1
1
2
1
1
1
Anthropicclaude-opus-4-5-20251101-thinking-32k
3
1
1
-
2
1
1
1
gpt-5.1-high
3
2
4
1
2
3
3
2
grok-4.1
3
2
4
4
3
10
8
2
Anthropicclaude-sonnet-4-5-20250929-thinking-32k
5
2
1
1
2
2
1
2
gemini-2.5-pro
5
7
12
1
2
4
6
3
Anthropicclaude-opus-4-1-20250805-thinking-16k
6
2
1
4
2
2
1
2
Anthropicclaude-sonnet-4-5-20250929
6
4
2
4
2
3
3
1
Anthropicclaude-opus-4-1-20250805
8
5
4
4
3
3
6
2
gpt-4.5-preview-2025-02-27
8
14
14
8
2
8
8
2
gpt-5.1
8
11
5
7
9
9
6
2
chatgpt-4o-latest-20250326
10
12
15
18
8
13
11
2
gpt-5-high
10
12
12
4
18
13
23
17
MoonshotAIkimi-k2-thinking-turbo
11
12
8
4
8
10
11
13
o3-2025-04-16
11
14
18
1
21
23
31
18
Qwen Iconqwen3-max-preview
11
11
8
2
13
9
9
7
grok-4-1-fast-reasoning
14
13
10
-
10
14
27
14
deepseek-v3.2-exp
15
12
10
7
9
11
8
13
glm-4.6
15
12
14
4
10
11
11
18
gpt-5-chat
16
12
15
8
16
13
11
7
Qwen Iconqwen3-max-2025-09-23
16
12
10
2
10
13
11
5
Anthropicclaude-opus-4-20250514-thinking-16k
18
12
5
7
4
6
6
14
deepseek-v3.1-terminus
18
23
23
7
4
17
14
25
deepseek-v3.2-exp-thinking
18
13
10
4
11
12
11
17
Baiduernie-5.0-preview-1022
18
23
28
4
4
14
14
15
grok-4-fast
18
18
14
4
15
14
12
14
MoonshotAIkimi-k2-0905-preview
18
18
12
7
16
37
32
22
Qwen Iconqwen3-235b-a22b-instruct-2507
18
12
12
7
22
13
11
14
deepseek-r1-0528
19
19
13
14
15
30
29
25
deepseek-v3.1
19
20
23
7
13
17
16
24
deepseek-v3.1-terminus-thinking
19
12
10
2
14
10
7
14
deepseek-v3.1-thinking
19
15
14
7
10
12
8
18
MoonshotAIkimi-k2-0711-preview
19
22
15
22
28
46
43
18
Qwen Iconqwen3-vl-235b-a22b-instruct
19
13
12
7
29
13
14
15
Anthropicclaude-opus-4-20250514
25
20
15
16
10
14
10
17
gpt-4.1-2025-04-14
25
25
22
49
13
26
20
17
glm-4.5
26
21
18
7
27
14
19
25
grok-3-preview-02-24
26
26
32
41
13
17
14
22
grok-4-0709
26
39
40
4
14
28
24
20
mistral-medium-2508
26
24
22
14
27
28
32
20
gemini-2.5-flash
30
40
55
13
14
21
23
34
gemini-2.5-flash-preview-09-2025
30
35
49
4
16
16
21
26
Anthropicclaude-haiku-4-5-20251001
37
19
9
16
21
13
11
18
grok-4-fast-reasoning
37
40
33
7
20
37
29
25
longcat-flash-chat
39
25
10
4
64
30
45
35
o1-2024-12-17
40
39
40
13
23
20
27
47
Qwen Iconqwen3-next-80b-a3b-instruct
40
27
25
7
75
42
42
26
Anthropicclaude-sonnet-4-20250514-thinking-32k
43
24
12
14
15
14
11
20
Qwen Iconqwen3-235b-a22b-no-thinking
43
39
29
19
37
44
33
25
Tencenthunyuan-vision-1.5-thinking
44
25
22
-
16
17
28
18
Qwen Iconqwen3-235b-a22b-thinking-2507
44
28
25
8
23
29
29
26
deepseek-r1
45
34
25
8
28
30
41
22
gpt-5-mini-high
45
46
42
7
67
44
60
55
Qwen Iconqwen3-vl-235b-a22b-thinking
45
32
15
7
51
37
28
39
deepseek-v3-0324
48
48
49
49
16
46
48
26
mai-1-preview
48
49
40
14
41
47
43
36
o4-mini-2025-04-16
49
48
43
7
64
54
66
52
Anthropicclaude-sonnet-4-20250514
51
39
27
30
22
37
21
26
Tencenthunyuan-t1-20250711
51
48
67
7
15
37
41
35
Anthropicclaude-3-7-sonnet-20250219-thinking-32k
52
39
24
35
16
17
18
34
o1-preview
52
58
56
35
37
44
53
40
Qwen Iconqwen3-coder-480b-a35b-instruct
54
41
18
38
41
42
32
35
mistral-medium-2505
56
58
43
70
42
60
48
30
Qwen Iconqwen3-30b-a3b-instruct-2507
57
46
34
26
72
52
53
50
Tencenthunyuan-turbos-20250416
58
62
73
66
33
65
51
36
gpt-4.1-mini-2025-04-14
59
56
40
68
57
51
51
39
gemini-2.5-flash-lite-preview-09-2025-no-thinking
60
62
75
46
37
53
41
55
gemini-2.5-flash-lite-preview-06-17-thinking
63
69
78
49
30
49
52
62
Qwen Iconqwen3-235b-a22b
64
63
40
14
68
63
54
60
Qwen Iconqwen2.5-max
67
69
71
57
53
68
51
60
Anthropicclaude-3-5-sonnet-20241022
68
58
43
78
37
55
48
44
Anthropicclaude-3-7-sonnet-20250219
68
58
46
67
28
44
31
35
glm-4.5-air
68
64
47
17
70
58
54
62
Qwen Iconqwen3-next-80b-a3b-thinking
70
67
46
13
71
61
62
77
Minimaxminimax-m1
71
70
56
14
73
74
63
71
gemma-3-27b-it
74
79
100
89
56
78
69
68
grok-3-mini-high
74
74
77
16
67
58
54
73
o3-mini-high
74
54
38
13
79
58
61
77
deepseek-v3
76
90
77
97
54
78
60
58
gemini-2.0-flash-001
76
80
99
68
57
74
69
71
grok-3-mini-beta
76
78
77
46
64
65
63
77
amazon-nova-experimental-chat-10-20
79
71
56
7
92
53
69
93
glm-4.5v
79
74
59
35
74
74
83
62
Tencenthunyuan-turbos-20250226
79
71
52
89
77
64
60
68
mistral-small-2506
79
75
58
72
72
79
71
63
gemini-2.0-flash-lite-preview-02-05
81
90
118
87
57
85
83
85
gpt-oss-120b
81
80
77
27
105
87
96
87
Nvidiallama-3.1-nemotron-ultra-253b-v1
81
66
63
13
53
59
69
68
amazon-nova-experimental-chat-10-09
82
79
71
-
75
83
79
68
Coherecommand-a-03-2025
82
79
77
97
67
79
66
68
gemini-1.5-pro-002
82
90
104
82
47
80
77
87
AntGroupling-flash-2.0
82
78
52
46
105
88
89
87
Minimaxminimax-m2
82
76
78
35
92
78
77
58
Qwen Iconqwen3-32b
82
74
50
7
76
78
62
77
Stepfunstep-3
82
71
62
28
77
71
74
77
Qwen Iconqwen-plus-0125
83
82
77
82
72
79
62
68
gemma-3-12b-it
84
95
130
82
56
85
63
68
glm-4-plus-0111
84
105
123
97
70
92
80
79
Tencenthunyuan-turbo-0110
84
80
76
102
77
88
69
78
Nvidianvidia-llama-3.3-nemotron-super-49b-v1.5
84
79
66
7
72
81
77
77
o3-mini
84
79
63
38
92
78
75
83
gpt-4o-2024-05-13
88
104
98
101
67
92
93
83
Anthropicclaude-3-5-sonnet-20240620
89
81
75
81
91
83
83
77
gpt-5-nano-high
89
82
77
53
127
83
88
83
Metallama-3.1-405b-instruct-bf16
92
97
86
97
93
101
96
82
Stepfunstep-2-16k-exp-202412
92
94
79
88
55
93
79
93
gemini-advanced-0514
95
111
124
101
58
97
98
93
gpt-4o-2024-08-06
95
111
100
98
73
97
89
87
o1-mini
95
83
77
65
108
85
86
93
grok-2-2024-08-13
97
113
103
110
79
101
92
93
Metallama-3.1-405b-instruct-fp8
97
103
99
95
90
101
105
85
Nvidiallama-3.3-nemotron-49b-super-v1
97
74
77
-
79
79
75
77
Qwen Iconqwq-32b
97
84
77
54
96
88
89
93
Tencenthunyuan-large-2025-02-10
101
97
78
97
79
89
43
87
01.AIyi-lightning
103
97
90
97
93
101
94
85
Metallama-4-maverick-17b-128e-instruct
105
99
86
89
85
97
90
87
Qwen Iconqwen3-30b-a3b
107
94
77
64
101
97
87
93
deepseek-v2.5-1210
110
104
78
102
77
95
85
85
gpt-4-turbo-2024-04-09
113
120
118
106
74
112
108
100
gpt-4.1-nano-2025-04-14
113
99
78
111
79
102
89
93
Metallama-4-scout-17b-16e-instruct
113
108
99
92
97
108
93
93
Anthropicclaude-3-5-haiku-20241022
114
97
78
118
95
101
88
93
Anthropicclaude-3-opus-20240229
114
111
112
97
105
101
98
93
gemini-1.5-pro-001
114
111
115
108
75
101
85
95
gpt-oss-20b
114
111
83
75
144
131
117
122
mercury
114
101
77
-
115
117
90
87
AntGroupring-flash-2.0
114
85
75
53
124
88
88
126
Stepfunstep-1o-turbo-202506
114
104
99
92
95
97
76
85
gemma-3n-e4b-it
115
120
149
124
92
133
105
122
glm-4-plus
117
114
107
112
99
108
96
95
Metallama-3.3-70b-instruct
117
114
121
106
105
125
119
93
Qwen Iconqwen-max-0919
117
114
104
106
101
104
93
106
Qwen Iconqwen2.5-plus-1127
118
108
99
97
108
114
109
102
Tencenthunyuan-standard-2025-02-10
119
114
116
98
99
125
83
95
gpt-4o-mini-2024-07-18
120
127
115
124
97
125
101
106
athene-v2-chat
123
105
93
97
141
104
101
109
gpt-4-0125-preview
123
134
139
104
108
129
127
126
gpt-4-1106-preview
123
125
125
102
104
122
135
120
mistral-large-2407
123
114
109
113
103
117
131
122
gemini-1.5-flash-002
125
138
148
112
93
125
101
136
gemma-3-4b-it
133
146
161
124
98
142
90
126
athene-70b-0725
135
122
107
137
117
143
140
121
deepseek-v2.5
135
114
97
112
127
125
107
126
grok-2-mini-2024-08-13
135
139
130
127
119
136
107
123
magistral-medium-2506
135
104
77
102
96
101
88
93
mistral-large-2411
138
124
117
118
115
123
129
123
mistral-small-3.1-24b-instruct-2503
140
114
99
116
117
117
96
124
Tencenthunyuan-large-vision
141
127
92
97
93
114
92
126
Nvidiallama-3.1-nemotron-70b-instruct
141
119
126
113
102
133
143
117
Qwen Iconqwen2.5-72b-instruct
141
118
104
104
141
125
105
121
jamba-1.5-large
150
151
147
144
124
145
157
146
Metallama-3.1-70b-instruct
150
145
138
131
137
145
142
126
Nvidiallama-3.1-nemotron-51b-instruct
150
147
143
116
111
146
149
126
llama-3.1-tulu-3-70b
150
153
144
123
130
138
143
124
reka-core-20240904
150
153
145
146
115
148
144
146
amazon-nova-pro-v1.0
151
140
121
128
157
144
133
137
gemma-2-27b-it
151
156
153
156
99
146
139
137
gpt-4-0314
151
135
140
118
138
141
154
145
gemini-1.5-flash-001
153
151
150
144
131
151
135
146
Anthropicclaude-3-sonnet-20240229
154
156
149
144
149
148
147
136
gemma-2-9b-it-simpo
154
156
170
173
99
157
138
137
Coherecommand-r-plus-08-2024
156
165
170
159
121
156
144
156
Nvidianemotron-4-340b-instruct
156
155
151
141
153
154
143
152
glm-4-0520
159
155
150
144
145
155
155
150
gpt-4-0613
160
151
150
127
130
145
155
153
Metallama-3-70b-instruct
160
156
153
142
140
156
169
146
mistral-small-24b-instruct-2501
160
152
148
132
160
156
147
157
reka-flash-20240904
160
158
156
159
141
159
155
162
Qwen Iconqwen2.5-coder-32b-instruct
161
126
108
120
171
146
140
154
Coherec4ai-aya-expanse-32b
166
158
159
160
161
160
143
169
deepseek-coder-v2
168
149
118
124
173
157
143
167
gemma-2-9b-it
168
173
175
170
138
166
159
159
Coherecommand-r-plus
169
175
175
172
157
168
160
167
Qwen Iconqwen2-72b-instruct
169
158
157
124
164
167
160
163
amazon-nova-lite-v1.0
171
158
151
148
164
165
155
170
Anthropicclaude-3-haiku-20240307
171
165
156
161
171
166
159
163
gemini-1.5-flash-8b-001
171
169
175
161
156
169
158
175
olmo-2-0325-32b-instruct
171
156
156
147
153
167
155
149
Azurephi-4
174
156
151
132
172
163
157
164
Coherecommand-r-08-2024
175
168
170
174
169
170
157
176
amazon-nova-micro-v1.0
181
178
163
161
176
184
169
179
jamba-1.5-mini
181
182
175
182
169
184
186
179
ministral-8b-2410
181
169
170
164
160
184
157
176
mistral-large-2402
181
167
159
151
172
170
173
172
Tencenthunyuan-standard-256k
182
155
149
127
170
157
144
173
gemini-pro-dev-api
183
185
195
180
173
184
183
185
Qwen Iconqwen1.5-110b-chat
183
178
171
165
177
184
183
176
Qwen Iconqwen1.5-72b-chat
183
182
175
174
181
184
179
176
reka-flash-21b-20240226-online
183
182
171
168
182
186
187
179
Coherecommand-r
185
194
196
199
177
189
183
184
gemini-pro
185
182
178
176
177
181
-
176
llama-3.1-tulu-3-8b
185
184
175
164
172
183
173
184
mixtral-8x22b-instruct-v0.1
185
181
174
162
181
184
187
188
reka-flash-21b-20240226
185
185
177
178
187
191
187
184
Coherec4ai-aya-expanse-8b
186
185
178
176
177
184
167
182
mistral-medium
186
184
178
166
177
184
187
184
gpt-3.5-turbo-0125
187
189
175
180
182
184
187
183
Metallama-3-8b-instruct
189
191
189
183
177
193
190
183
HuggingFacezephyr-orpo-141b-A35b-v0.1
192
189
185
173
184
188
192
196
granite-3.1-8b-instruct
194
179
153
172
182
185
169
196
01.AIyi-1.5-34b-chat
197
189
190
169
198
193
189
185
Metallama-3.1-8b-instruct
199
190
179
183
189
192
187
184
Qwen Iconqwen1.5-32b-chat
199
190
178
176
209
197
185
184
gpt-3.5-turbo-1106
200
185
177
176
202
189
199
194
Azurephi-3-medium-4k-instruct
203
195
201
168
206
201
199
210
dbrx-instruct-preview
204
191
189
180
196
197
202
194
gemma-2-2b-it
204
212
218
208
184
206
204
203
InternLMinternlm2_5-20b-chat
204
185
188
170
209
198
189
196
mixtral-8x7b-instruct-v0.1
204
197
198
184
200
201
204
201
Qwen Iconqwen1.5-14b-chat
204
204
196
202
207
205
196
199
deepseek-llm-67b-chat
206
212
201
202
206
209
189
201
Azurewizardlm-70b
206
214
217
202
173
208
191
194
granite-3.0-8b-instruct
210
197
190
176
206
202
187
205
granite-3.1-2b-instruct
210
185
178
170
195
199
175
202
OpenChatopenchat-3.5
210
212
214
218
177
212
192
201
OpenChatopenchat-3.5-0106
210
212
201
208
206
212
205
203
01.AIyi-34b-chat
210
212
215
210
200
212
205
201
openhermes-2.5-mistral-7b
211
212
217
208
194
211
211
205
Snowflakesnowflake-arctic-instruct
211
212
204
206
206
212
223
206
tulu-2-dpo-70b
211
208
204
210
202
201
193
205
gemma-1.1-7b-it
212
210
207
208
206
212
209
215
nous-hermes-2-mixtral-8x7b-dpo
213
233
218
228
206
230
219
207
Azurephi-3-small-8k-instruct
213
212
215
180
209
212
211
218
starling-lm-7b-beta
213
207
198
206
219
212
206
204
vicuna-33b
213
220
218
223
189
217
218
207
Metallama-2-70b-chat
214
222
226
215
222
220
219
212
starling-lm-7b-alpha
214
216
212
218
207
217
211
210
Metallama-3.2-3b-instruct
217
216
220
201
204
214
209
203
Qwen Iconqwq-32b-preview
221
213
218
159
213
209
194
201
Nvidiallama2-70b-steerlm-chat
222
222
231
218
209
219
237
212
dolphin-2.2.1-mistral-7b
223
215
-
210
200
216
-
222
solar-10.7b-instruct-v1.0
224
218
217
222
203
228
-
214
falcon-180b-chat
228
225
-
-
184
212
-
215
granite-3.0-2b-instruct
228
212
209
193
227
220
211
214
mpt-30b-chat
228
215
218
223
204
216
-
205
mistral-7b-instruct-v0.2
230
222
218
218
227
228
221
222
Azurewizardlm-13b
230
238
232
242
206
227
205
220
Metallama-2-13b-chat
231
233
230
226
235
231
213
228
Azurephi-3-mini-4k-instruct-june-2024
231
214
217
179
234
228
229
229
Qwen Iconqwen-14b-chat
231
225
215
215
222
228
213
225
Qwen Iconqwen1.5-7b-chat
231
222
206
218
237
225
204
212
vicuna-13b
232
235
230
236
213
231
212
228
Metacodellama-34b-instruct
233
233
229
224
237
232
226
235
palm-2
233
225
232
222
236
231
212
230
gemma-7b-it
235
222
226
222
227
234
225
247
HuggingFacezephyr-7b-alpha
235
231
218
-
216
231
-
230
guanaco-33b
237
239
243
228
204
251
-
231
Azurephi-3-mini-128k-instruct
237
235
234
212
238
235
241
242
HuggingFacezephyr-7b-beta
237
238
233
234
207
242
226
230
Metacodellama-70b-instruct
238
213
-
-
-
230
-
-
Azurephi-3-mini-4k-instruct
241
225
218
210
241
231
232
242
HuggingFacesmollm2-1.7b-instruct
243
218
220
199
232
230
212
234
stripedhyena-nous-7b
243
246
243
231
233
239
236
233
vicuna-7b
249
247
239
244
234
249
205
242
gemma-1.1-2b-it
251
233
226
226
234
238
226
245
Metallama-2-7b-chat
251
251
254
234
241
252
240
235
Metallama-3.2-1b-instruct
251
242
234
218
235
244
231
234
mistral-7b-instruct
251
238
234
234
234
244
229
233
gemma-2b-it
258
242
237
240
238
252
232
249
olmo-7b-instruct
261
259
249
242
263
262
-
245
Qwen Iconqwen1.5-4b-chat
261
251
243
232
256
252
237
242
gpt4all-13b-snoozy
262
257
-
254
238
259
-
247
koala-13b
262
264
259
256
256
263
-
261
alpaca-13b
263
266
265
256
233
263
-
258
chatglm3-6b
263
262
255
247
257
261
245
247
mpt-7b-chat
263
264
258
256
249
263
-
259
RWKVRWKV-4-Raven-14B
266
265
260
256
263
269
-
264
chatglm2-6b
269
263
261
256
262
267
-
262
oasst-pythia-12b
269
265
261
256
262
268
-
265
chatglm-6b
272
266
262
256
271
268
-
268
dolly-v2-12b
272
270
268
256
267
272
-
272
fastchat-t5-3b
272
273
270
262
267
269
-
268
Metallama-13b
272
273
271
262
271
274
-
271
Stabilitystablelm-tuned-alpha-7b
274
273
263
264
272
274
-
271