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
3
2
3
3
1
3
2
grok-4.1-thinking
2
10
4
6
9
10
13
15
gemini-3-flash
3
6
5
8
2
3
6
7
Anthropicclaude-opus-4-5-20251101-thinking-32k
4
2
1
1
4
4
1
1
grok-4.1
5
19
9
13
19
14
17
13
Anthropicclaude-opus-4-5-20251101
6
1
3
4
7
2
2
3
gemini-3-flash (thinking-minimal)
7
11
7
10
5
9
10
8
gpt-5.1-high
8
8
11
14
6
11
9
10
gemini-2.5-pro
9
12
14
27
11
5
11
11
Anthropicclaude-sonnet-4-5-20250929-thinking-32k
10
4
6
2
8
8
4
4
Anthropicclaude-opus-4-1-20250805-thinking-16k
11
9
8
5
13
7
5
5
Anthropicclaude-sonnet-4-5-20250929
12
7
10
7
24
6
7
6
Baiduernie-5.0-preview-1203
13
26
16
31
52
15
26
34
gpt-4.5-preview-2025-02-27
14
43
37
43
44
13
15
22
Anthropicclaude-opus-4-1-20250805
15
17
12
9
18
12
8
9
glm-4.7
16
33
17
15
12
19
19
14
chatgpt-4o-latest-20250326
17
48
19
34
59
17
21
30
gpt-5.2
18
-
13
17
-
22
16
17
gpt-5.2-high
19
5
15
12
1
39
14
18
gpt-5-high
20
18
23
23
15
46
34
50
gpt-5.1
21
13
18
18
43
20
20
19
o3-2025-04-16
22
22
32
44
10
44
47
57
grok-4-1-fast-reasoning
23
25
33
51
50
27
49
48
MoonshotAIkimi-k2-thinking-turbo
24
16
21
16
14
35
23
28
Baiduernie-5.0-preview-1103
25
42
36
32
42
21
51
38
gpt-5-chat
26
21
25
40
40
42
30
31
Qwen Iconqwen3-max-2025-09-23
27
44
26
19
17
32
31
32
glm-4.6
28
23
31
39
25
28
27
33
Qwen Iconqwen3-max-preview
29
-
28
36
-
-
18
20
deepseek-v3.2-exp
30
41
24
26
32
25
29
23
Anthropicclaude-opus-4-20250514-thinking-16k
31
24
20
11
29
16
12
12
Qwen Iconqwen3-235b-a22b-instruct-2507
32
20
22
25
22
45
25
25
deepseek-v3.2-exp-thinking
33
29
29
22
23
36
28
35
grok-4-fast-chat
34
47
49
48
27
52
48
43
deepseek-v3.2
35
32
27
29
20
33
22
24
deepseek-v3.2-thinking
36
39
35
33
31
26
32
29
deepseek-r1-0528
37
53
43
37
66
41
57
60
MoonshotAIkimi-k2-0905-preview
38
50
40
30
37
51
63
64
deepseek-v3.1
39
37
45
55
36
38
45
39
MoonshotAIkimi-k2-0711-preview
40
55
46
41
73
62
74
70
deepseek-v3.1-thinking
41
38
39
46
28
23
24
16
deepseek-v3.1-terminus
42
-
54
65
65
24
56
52
Qwen Iconqwen3-vl-235b-a22b-instruct
43
31
34
35
48
66
36
41
deepseek-v3.1-terminus-thinking
44
-
30
42
38
53
33
27
mistral-large-3
45
54
38
28
35
67
40
51
gpt-4.1-2025-04-14
46
63
50
50
87
29
52
42
Anthropicclaude-opus-4-20250514
47
40
41
38
60
18
37
21
mistral-medium-2508
48
56
47
52
55
48
50
53
grok-3-preview-02-24
49
61
53
60
85
30
42
37
grok-4-0709
50
36
57
67
16
34
54
49
glm-4.5
51
27
44
49
33
56
39
45
gemini-2.5-flash
52
46
63
82
47
31
43
46
gemini-2.5-flash-preview-09-2025
53
28
56
80
30
47
46
47
Anthropicclaude-haiku-4-5-20251001
54
30
42
20
69
58
38
36
grok-4-fast-reasoning
55
52
68
64
46
55
62
59
o1-2024-12-17
56
67
64
72
49
50
44
55
Qwen Iconqwen3-next-80b-a3b-instruct
57
64
55
57
26
105
66
67
longcat-flash-chat
58
49
51
21
21
91
58
74
Qwen Iconqwen3-235b-a22b-no-thinking
59
70
58
58
67
65
68
61
Anthropicclaude-sonnet-4-20250514-thinking-32k
60
35
48
24
54
37
35
26
Qwen Iconqwen3-235b-a22b-thinking-2507
61
15
59
61
56
63
60
65
Xiaomimimo-v2-flash (non-thinking)
62
45
52
62
71
57
53
54
deepseek-r1
63
69
61
59
45
60
55
66
Qwen Iconqwen3-vl-235b-a22b-thinking
64
34
60
53
41
82
67
63
deepseek-v3-0324
65
73
71
79
86
40
73
72
gpt-5-mini-high
66
60
72
75
39
94
72
87
Tencenthunyuan-vision-1.5-thinking
67
-
62
66
-
68
61
68
o4-mini-2025-04-16
68
57
73
74
34
84
79
94
mai-1-preview
69
62
74
76
64
73
75
69
Anthropicclaude-sonnet-4-20250514
70
68
65
56
76
49
59
44
o1-preview
71
83
81
85
77
69
71
83
Anthropicclaude-3-7-sonnet-20250219-thinking-32k
72
58
66
54
80
43
41
40
Qwen Iconqwen3-coder-480b-a35b-instruct
73
81
67
47
84
70
64
62
Tencenthunyuan-t1-20250711
74
66
77
97
58
54
70
75
Minimaxminimax-m2.1-preview
75
14
69
45
53
90
65
56
mistral-medium-2505
76
82
78
73
104
72
82
73
Qwen Iconqwen3-30b-a3b-instruct-2507
77
76
70
63
81
98
80
79
gpt-4.1-mini-2025-04-14
78
80
75
68
102
80
77
76
Tencenthunyuan-turbos-20250416
79
101
85
101
106
71
91
84
gemini-2.5-flash-lite-preview-09-2025-no-thinking
80
75
83
100
89
75
83
77
gemini-2.5-flash-lite-preview-06-17-thinking
81
89
90
114
90
61
76
80
Qwen Iconqwen3-235b-a22b
82
79
82
69
62
95
87
81
Qwen Iconqwen2.5-max
83
91
88
94
92
76
88
78
Anthropicclaude-3-5-sonnet-20241022
84
92
79
71
107
64
78
71
Anthropicclaude-3-7-sonnet-20250219
85
78
80
77
98
59
69
58
glm-4.5-air
86
74
84
78
70
96
84
82
Qwen Iconqwen3-next-80b-a3b-thinking
87
77
87
81
63
103
86
90
Minimaxminimax-m1
88
85
89
84
61
100
94
91
gemma-3-27b-it
89
110
106
139
115
78
98
95
o3-mini-high
90
72
76
70
51
108
81
89
grok-3-mini-high
91
65
92
107
72
93
85
85
amazon-nova-experimental-chat-11-10
92
51
86
83
79
132
89
97
gemini-2.0-flash-001
93
103
108
134
101
79
95
96
deepseek-v3
94
106
119
108
123
77
100
88
grok-3-mini-beta
95
84
98
112
88
85
90
92
mistral-small-2506
96
112
93
88
108
99
103
99
PrimeIntellectintellect-3
97
90
96
90
68
119
106
105
glm-4.5v
98
59
95
93
94
109
102
117
gpt-oss-120b
99
96
107
104
78
148
113
140
gemini-2.0-flash-lite-preview-02-05
100
114
120
157
113
81
111
112
Coherecommand-a-03-2025
101
107
102
106
125
88
101
93
gemini-1.5-pro-002
102
111
118
145
110
74
104
102
o3-mini
103
93
99
86
82
117
99
100
amazon-nova-experimental-chat-10-20
104
87
97
89
74
147
93
103
Tencenthunyuan-turbos-20250226
105
-
104
95
134
120
96
104
amazon-nova-experimental-chat-10-09
106
-
109
105
-
128
119
122
AntGroupling-flash-2.0
107
97
101
87
100
158
121
135
Minimaxminimax-m2
108
109
100
118
97
135
105
110
Stepfunstep-3
109
100
91
92
91
115
97
107
Nvidiallama-3.1-nemotron-ultra-253b-v1
110
-
94
102
83
89
92
115
gpt-4o-2024-05-13
111
129
128
128
131
86
117
134
Qwen Iconqwen3-32b
112
71
105
91
57
114
112
101
Qwen Iconqwen-plus-0125
113
86
117
117
114
107
108
98
glm-4-plus-0111
114
128
144
165
136
104
124
123
Anthropicclaude-3-5-sonnet-20240620
115
108
112
99
109
118
107
106
Nvidianvidia-llama-3.3-nemotron-super-49b-v1.5
116
88
110
98
75
112
118
118
gemma-3-12b-it
117
159
134
171
118
92
120
108
Tencenthunyuan-turbo-0110
118
-
121
123
157
123
129
116
gpt-5-nano-high
119
99
115
116
103
175
114
132
nova-2-lite
120
94
103
96
112
151
110
113
o1-mini
121
104
113
109
96
149
109
114
Metallama-3.1-405b-instruct-bf16
122
131
124
121
121
122
132
141
gpt-4o-2024-08-06
123
130
142
140
127
97
123
125
Qwen Iconqwq-32b
124
98
114
113
95
130
115
124
grok-2-2024-08-13
125
124
145
142
142
106
135
130
gemini-advanced-0514
126
148
147
161
133
83
128
146
Metallama-3.1-405b-instruct-fp8
127
120
129
131
119
116
131
150
Stepfunstep-2-16k-exp-202412
128
116
127
125
122
87
125
120
01.AIyi-lightning
129
113
125
127
128
127
138
143
Metallama-4-maverick-17b-128e-instruct
130
115
126
122
116
111
130
127
Qwen Iconqwen3-30b-a3b
131
105
122
111
99
144
133
121
Nvidiallama-3.3-nemotron-49b-super-v1
132
-
111
135
-
129
116
129
Tencenthunyuan-large-2025-02-10
133
117
136
132
141
121
126
86
gpt-4-turbo-2024-04-09
134
144
156
154
139
101
144
155
Anthropicclaude-3-5-haiku-20241022
135
125
123
115
152
124
136
119
deepseek-v2.5-1210
136
135
138
119
143
110
127
126
Metallama-4-scout-17b-16e-instruct
137
132
137
137
120
134
147
136
gemini-1.5-pro-001
138
121
141
153
140
102
139
109
Anthropicclaude-3-opus-20240229
139
122
139
147
126
138
137
139
gpt-4.1-nano-2025-04-14
140
123
133
120
160
113
145
137
Stepfunstep-1o-turbo-202506
141
141
131
144
130
137
134
111
AntGroupring-flash-2.0
142
95
116
103
105
170
122
131
Metallama-3.3-70b-instruct
143
142
150
156
138
141
156
159
glm-4-plus
144
136
153
150
149
136
146
144
gemma-3n-e4b-it
145
155
157
175
169
126
161
154
gpt-oss-20b
146
119
148
124
111
184
164
161
Qwen Iconqwen-max-0919
147
137
154
149
144
145
143
142
Nvidianvidia-nemotron-3-nano-30b-a3b-bf16
148
102
135
133
93
177
140
169
gpt-4o-mini-2024-07-18
149
153
162
152
159
131
154
145
Qwen Iconqwen2.5-plus-1127
150
118
143
143
129
156
151
160
mistral-large-2407
151
138
152
148
147
139
149
164
athene-v2-chat
152
127
132
129
124
176
142
148
gpt-4-0125-preview
153
157
164
167
135
150
160
162
gpt-4-1106-preview
154
152
159
162
132
142
152
167
mercury
155
-
146
126
-
183
167
158
Tencenthunyuan-standard-2025-02-10
156
150
161
166
145
155
163
133
gemini-1.5-flash-002
157
156
169
173
146
125
158
147
grok-2-mini-2024-08-13
158
147
166
163
161
159
162
153
deepseek-v2.5
159
143
149
130
148
162
157
156
athene-70b-0725
160
140
160
151
173
160
168
172
mistral-large-2411
161
163
158
155
153
154
153
163
olmo-3-32b-think
162
139
140
136
117
166
148
149
magistral-medium-2506
163
149
130
110
151
140
141
128
mistral-small-3.1-24b-instruct-2503
164
126
151
138
156
157
150
138
gemma-3-4b-it
165
172
177
200
175
153
175
157
Qwen Iconqwen2.5-72b-instruct
166
145
155
146
137
173
155
152
Nvidiallama-3.1-nemotron-70b-instruct
167
146
163
169
158
152
165
179
Tencenthunyuan-large-vision
168
134
167
141
150
143
159
151
Metallama-3.1-70b-instruct
169
162
172
164
168
169
170
170
jamba-1.5-large
170
154
178
178
183
168
176
196
amazon-nova-pro-v1.0
171
160
170
159
166
188
169
165
ibm-granite-h-small
172
133
171
168
155
179
173
171
gemma-2-27b-it
173
175
180
185
185
133
174
168
reka-core-20240904
174
151
183
174
181
161
180
182
gpt-4-0314
175
170
165
170
154
174
166
184
Nvidiallama-3.1-nemotron-51b-instruct
176
176
181
179
165
167
181
188
llama-3.1-tulu-3-70b
177
-
187
181
171
178
171
186
gemini-1.5-flash-001
178
166
174
180
176
165
178
166
Anthropicclaude-3-sonnet-20240229
179
164
179
172
178
180
177
178
gemma-2-9b-it-simpo
180
189
189
204
207
146
187
174
Nvidianemotron-4-340b-instruct
181
174
182
184
177
186
182
176
Coherecommand-r-plus-08-2024
182
180
197
198
188
164
186
181
Metallama-3-70b-instruct
183
182
184
186
174
172
183
200
gpt-4-0613
184
179
173
177
163
163
172
183
mistral-small-24b-instruct-2501
185
171
176
176
172
190
184
180
glm-4-0520
186
177
186
182
180
182
185
191
reka-flash-20240904
187
161
193
193
186
181
190
194
Qwen Iconqwen2.5-coder-32b-instruct
188
158
168
158
164
200
179
175
Coherec4ai-aya-expanse-32b
189
168
191
192
187
189
189
173
gemma-2-9b-it
190
187
199
208
198
171
195
192
deepseek-coder-v2
191
167
175
160
167
201
188
177
Coherecommand-r-plus
192
184
201
209
201
187
197
197
Qwen Iconqwen2-72b-instruct
193
173
188
190
162
192
196
198
Anthropicclaude-3-haiku-20240307
194
178
194
188
190
195
193
193
amazon-nova-lite-v1.0
195
169
190
187
182
193
192
185
gemini-1.5-flash-8b-001
196
183
198
207
191
185
198
190
Azurephi-4
197
165
185
183
170
199
191
189
olmo-2-0325-32b-instruct
198
-
195
197
189
191
201
203
Coherecommand-r-08-2024
199
191
200
196
206
198
200
195
mistral-large-2402
200
193
196
191
184
196
199
204
amazon-nova-micro-v1.0
201
181
204
194
193
204
202
202
jamba-1.5-mini
202
203
207
210
225
197
213
216
ministral-8b-2410
203
185
202
203
199
194
206
199
gemini-pro-dev-api
204
214
212
226
223
202
211
213
Qwen Iconqwen1.5-110b-chat
205
192
203
199
194
210
203
208
Qwen Iconqwen1.5-72b-chat
206
188
206
205
205
213
209
205
Tencenthunyuan-standard-256k
207
-
192
189
179
207
194
187
reka-flash-21b-20240226-online
208
195
208
201
202
218
214
219
mixtral-8x22b-instruct-v0.1
209
200
205
202
192
212
205
217
Coherecommand-r
210
202
226
225
226
206
215
206
reka-flash-21b-20240226
211
201
210
211
211
220
221
218
gpt-3.5-turbo-0125
212
209
215
206
212
214
207
215
Coherec4ai-aya-expanse-8b
213
190
213
216
210
211
212
201
mistral-medium
214
194
209
212
195
209
210
214
Metallama-3-8b-instruct
215
205
222
218
221
205
219
220
gemini-pro
216
-
214
222
215
217
204
-
llama-3.1-tulu-3-8b
217
-
219
217
203
208
208
209
HuggingFacezephyr-orpo-141b-A35b-v0.1
218
217
225
224
214
223
220
230
01.AIyi-1.5-34b-chat
219
198
218
223
200
225
222
221
Metallama-3.1-8b-instruct
220
208
220
215
222
219
217
210
granite-3.1-8b-instruct
221
186
211
195
220
222
216
207
Qwen Iconqwen1.5-32b-chat
222
196
221
213
208
249
224
212
gpt-3.5-turbo-1106
223
204
216
214
209
230
218
228
gemma-2-2b-it
224
218
237
244
231
216
229
227
Azurephi-3-medium-4k-instruct
225
206
227
231
197
231
227
225
mixtral-8x7b-instruct-v0.1
226
210
228
229
224
226
226
231
dbrx-instruct-preview
227
212
224
220
217
224
223
226
Qwen Iconqwen1.5-14b-chat
228
211
230
228
228
240
232
224
InternLMinternlm2_5-20b-chat
229
197
217
221
204
251
225
223
Azurewizardlm-70b
230
-
244
247
233
203
233
232
deepseek-llm-67b-chat
231
-
242
235
236
250
234
233
01.AIyi-34b-chat
232
225
238
240
239
228
239
236
granite-3.0-8b-instruct
233
207
229
227
216
241
231
222
OpenChatopenchat-3.5-0106
234
223
236
232
234
235
236
237
OpenChatopenchat-3.5
235
222
243
242
249
215
240
229
granite-3.1-2b-instruct
236
199
223
219
213
232
228
211
gemma-1.1-7b-it
237
219
232
234
235
233
238
239
Snowflakesnowflake-arctic-instruct
238
221
235
233
230
237
241
255
tulu-2-dpo-70b
239
-
234
236
241
234
230
235
openhermes-2.5-mistral-7b
240
-
239
249
240
227
242
249
vicuna-33b
241
228
248
246
251
221
245
254
starling-lm-7b-beta
242
216
231
230
232
255
243
238
Azurephi-3-small-8k-instruct
243
220
233
241
219
247
237
241
Metallama-2-70b-chat
244
232
249
252
243
254
247
250
starling-lm-7b-alpha
245
231
247
239
245
243
246
243
Metallama-3.2-3b-instruct
246
213
246
253
229
236
244
242
nous-hermes-2-mixtral-8x7b-dpo
247
-
267
255
259
242
263
258
Qwen Iconqwq-32b-preview
248
224
245
254
196
256
235
234
Nvidiallama2-70b-steerlm-chat
249
-
259
269
253
253
252
271
granite-3.0-2b-instruct
250
215
240
238
227
261
250
244
solar-10.7b-instruct-v1.0
251
-
250
251
256
239
257
-
dolphin-2.2.1-mistral-7b
252
-
254
-
247
245
251
-
mpt-30b-chat
253
-
253
259
260
248
248
-
mistral-7b-instruct-v0.2
254
230
252
250
244
257
255
253
Azurewizardlm-13b
255
-
273
267
269
238
256
245
falcon-180b-chat
256
-
268
-
-
229
249
-
Qwen Iconqwen1.5-7b-chat
257
227
258
237
250
273
254
240
Azurephi-3-mini-4k-instruct-june-2024
258
226
241
243
218
262
253
261
Metallama-2-13b-chat
259
234
262
261
255
264
262
248
vicuna-13b
260
236
265
260
265
252
259
247
Qwen Iconqwen-14b-chat
261
-
261
245
248
259
258
256
palm-2
262
-
260
265
254
270
260
251
Metacodellama-34b-instruct
263
-
264
263
257
271
265
264
gemma-7b-it
264
235
256
257
252
260
266
259
HuggingFacezephyr-7b-beta
265
238
270
266
264
244
271
260
Azurephi-3-mini-128k-instruct
266
241
266
264
242
269
268
269
Azurephi-3-mini-4k-instruct
267
229
257
248
238
277
261
262
HuggingFacezephyr-7b-alpha
268
-
269
258
-
258
267
-
guanaco-33b
269
-
277
275
267
246
279
-
stripedhyena-nous-7b
270
-
275
274
262
265
272
270
Metacodellama-70b-instruct
271
-
251
-
-
-
270
-
HuggingFacesmollm2-1.7b-instruct
272
-
255
262
237
274
264
252
vicuna-7b
273
-
276
272
271
268
275
246
gemma-1.1-2b-it
274
239
263
256
258
266
269
257
Metallama-3.2-1b-instruct
275
242
271
268
246
272
273
263
mistral-7b-instruct
276
243
272
270
266
263
274
265
Metallama-2-7b-chat
277
233
278
277
261
276
276
268
gemma-2b-it
278
-
274
271
268
275
278
266
Qwen Iconqwen1.5-4b-chat
279
240
279
273
263
280
277
267
olmo-7b-instruct
280
237
280
276
270
284
282
-
koala-13b
281
-
283
280
277
281
283
-
alpaca-13b
282
-
288
286
274
267
284
-
gpt4all-13b-snoozy
283
-
281
-
273
278
280
-
mpt-7b-chat
284
-
284
279
275
279
285
-
chatglm3-6b
285
-
282
278
272
282
281
272
RWKVRWKV-4-Raven-14B
286
-
287
281
276
286
289
-
chatglm2-6b
287
-
285
284
279
285
287
-
oasst-pythia-12b
288
-
286
282
280
283
286
-
chatglm-6b
289
-
289
283
278
289
288
-
fastchat-t5-3b
290
-
292
288
282
287
290
-
dolly-v2-12b
291
-
290
287
281
288
291
-
Metallama-13b
292
-
293
289
283
290
292
-
Stabilitystablelm-tuned-alpha-7b
293
-
291
285
284
291
293
-