Ranking de MIR 2026
24 de enero de 2026
210preguntas
7anuladas
Comparar con:
Ir a métrica:
Menú de métricas
Netas obtenidas
Puntuación MIR: (3 × aciertos - fallos) / 3
1
Gemini 3 Flash Preview
198.66 pts
2
o3
198.66 pts
3
GPT-5
198.66 pts
4
GPT-5.1 Chat
197.33 pts
5
GPT-5 Codex
197.33 pts
6
GPT-5.1-Codex-Max
197.33 pts
7
Nano Banana Pro (Gemini 3 Pro Image Preview)
197.33 pts
8
Gemini 3 Pro Preview
197.33 pts
9
Gemini 2.5 Pro Preview 05-06
197.33 pts
10
o1
197.33 pts
11
GPT-5.2 Pro
197.33 pts
12
o3 Deep Research
197.33 pts
13
GPT-5 Image
196.00 pts
14
Claude Opus 4.5
196.00 pts
15
Claude Opus 4.6
196.00 pts
16
Gemini 2.5 Pro Preview 06-05
196.00 pts
17
Gemini 2.5 Pro
196.00 pts
18
Claude Opus 4.1
196.00 pts
19
o3 Pro
196.00 pts
20
o1-pro
196.00 pts
21
GPT-5.1
195.00 pts
22
GPT-5.1-Codex
194.66 pts
23
o4 Mini
194.66 pts
24
o4 Mini Deep Research
194.66 pts
25
Switchpoint Router
194.00 pts
26
GPT-5 Chat
193.33 pts
27
GPT-5.2-Codex
193.33 pts
28
GPT-5.2
193.33 pts
29
ChatGPT-4o
193.33 pts
30
Gemini 2.5 Flash Image (Nano Banana)
192.66 pts
31
Grok 4
192.66 pts
32
Gemini 2.5 Flash Preview 09-2025
192.33 pts
33
o4 Mini High
192.33 pts
34
Llama 4 Maverick
192.00 pts
35
GPT-5 Mini
192.00 pts
36
GPT-5 Image Mini
192.00 pts
37
GPT-4.1
192.00 pts
38
GPT-5.2 Chat
192.00 pts
39
Claude 3.7 Sonnet (thinking)
192.00 pts
40
Qwen Plus 0728 (thinking)
191.00 pts
41
Grok 4.1 Fast
190.66 pts
42
GPT-5.1-Codex-Mini
190.66 pts
43
Kimi K2.5
190.66 pts
44
GPT-4o (2024-05-13)
190.66 pts
45
Claude Sonnet 4.5
190.66 pts
46
GLM 4.7
190.33 pts
47
Auto Router
190.00 pts
48
Claude Opus 4
190.00 pts
49
Aion-1.0
189.66 pts
50
Seed 1.6
189.33 pts
51
Claude Sonnet 4
189.33 pts
52
DeepSeek V3.2 Speciale
189.00 pts
53
Grok 3
188.66 pts
54
Mistral Large 3 2512
188.33 pts
55
Qwen3 235B A22B Thinking 2507
188.33 pts
56
Mistral Large 2407
188.33 pts
57
Claude 3.7 Sonnet
188.33 pts
58
Qwen3 VL 235B A22B Thinking
188.00 pts
59
R1 0528
187.66 pts
60
R1
187.00 pts
61
Mistral Large
187.00 pts
62
GPT-4o (2024-11-20)
187.00 pts
63
Grok 3 Beta
187.00 pts
64
Step 3.5 Flash
186.66 pts
65
o3 Mini High
186.66 pts
66
Qwen3 Max
186.33 pts
67
Llama 3.3 Nemotron Super 49B V1.5
186.00 pts
68
DeepSeek V3.1 Terminus
186.00 pts
69
Sonar Deep Research
186.00 pts
70
DeepSeek V3.1 Terminus (exacto)
185.66 pts
71
Qwen3 235B A22B
185.66 pts
72
Qwen3 Next 80B A3B Thinking
185.66 pts
73
Grok 4 Fast
185.33 pts
74
Qwen3 235B A22B Instruct 2507
184.66 pts
75
Gemini 2.5 Flash
184.66 pts
76
GLM 4.5
184.66 pts
77
Kimi K2 Thinking
184.66 pts
78
Gemini 2.0 Flash
184.33 pts
79
DeepSeek V3.2
184.33 pts
80
o3 Mini
184.33 pts
81
Claude 3.5 Sonnet
184.33 pts
82
gpt-oss-120b (exacto)
184.00 pts
83
GLM 4.6 (exacto)
184.00 pts
84
gpt-oss-120b
183.00 pts
85
GPT-3.5 Turbo (older v0613)
183.00 pts
86
GPT-4.1 Mini
182.66 pts
87
Qwen-Plus
182.66 pts
88
GLM 4.6
182.00 pts
89
DeepSeek V3.2 Exp
181.66 pts
90
Mistral Medium 3.1
181.33 pts
91
DeepSeek V3.1
180.66 pts
92
Grok 3 Mini Beta
180.66 pts
93
GPT-4o
180.66 pts
94
GPT-5 Nano
180.33 pts
95
Qwen3 Next 80B A3B Instruct
180.33 pts
96
KAT-Coder-Pro V1
180.00 pts
97
Qwen3 VL 235B A22B Instruct
180.00 pts
98
DeepSeek V3.1 Nex N1
180.00 pts
99
MiniMax M2.1
180.00 pts
100
Cogito v2.1 671B
179.66 pts
101
Palmyra X5
179.66 pts
102
Qwen3 VL 32B Instruct
179.33 pts
103
GPT-4o Search Preview
178.66 pts
104
DeepSeek V3 0324
178.66 pts
105
Sonar Pro Search
178.66 pts
106
DeepSeek V3
178.33 pts
107
Devstral Medium
178.33 pts
108
Devstral 2 2512
178.00 pts
109
Mistral Medium 3
177.66 pts
110
Grok 3 Mini
177.33 pts
111
Qwen Plus 0728
177.00 pts
112
Kimi K2 0711
176.66 pts
113
GPT-4o (2024-08-06)
176.66 pts
114
Qwen3 32B
176.33 pts
115
Qwen3 VL 30B A3B Thinking
176.33 pts
116
Qwen VL Max
176.33 pts
117
Tongyi DeepResearch 30B A3B
175.66 pts
118
Qwen3 Coder 480B A35B (exacto)
175.66 pts
119
MiniMax M2
175.66 pts
120
Gemini 2.5 Flash Lite Preview 09-2025
175.33 pts
121
GLM 4.6V
175.00 pts
122
Llama 3.1 Nemotron 70B Instruct
174.66 pts
123
Sonar Reasoning Pro
174.66 pts
124
Gemini 2.0 Flash Lite
173.66 pts
125
Qwen3 Coder Plus
173.66 pts
126
Llama 4 Scout
173.33 pts
127
Solar Pro 3
173.00 pts
128
Hermes 4 405B
173.00 pts
129
GLM 4.5V
173.00 pts
130
Kimi K2 0905
173.00 pts
131
Llama 3.1 Nemotron Ultra 253B v1
172.33 pts
132
Kimi K2 0905 (exacto)
171.66 pts
133
GPT-4 Turbo
171.66 pts
134
Qwen3 30B A3B Thinking 2507
171.33 pts
135
Claude Haiku 4.5
171.33 pts
136
GPT-4 Turbo Preview
171.00 pts
137
gpt-oss-safeguard-20b
170.00 pts
138
Inflection 3 Pi
170.00 pts
139
Qwen3 Coder 480B A35B
169.66 pts
140
ERNIE 4.5 VL 424B A47B
169.33 pts
141
Sonar Pro
169.33 pts
142
Qwen3 VL 30B A3B Instruct
169.00 pts
143
Aion-1.0-Mini
168.33 pts
144
Qwen3 Coder Next
168.33 pts
145
Seed 1.6 Flash
168.00 pts
146
Nova Premier 1.0
168.00 pts
147
GPT-4 Turbo (older v1106)
167.66 pts
148
Grok Code Fast 1
167.00 pts
149
Gemini 2.5 Flash Lite
166.66 pts
150
Sonar
166.66 pts
151
Cogito V2 Preview Llama 405B
166.33 pts
152
Llama 3.3 70B Instruct
166.00 pts
153
Mistral Small Creative
166.00 pts
154
Llama 3.3 Euryale 70B
166.00 pts
155
GPT-4
166.00 pts
156
MiMo-V2-Flash
165.66 pts
157
Qwen3 30B A3B Instruct 2507
165.66 pts
158
Trinity Large Preview
165.33 pts
159
GLM 4.5 Air
165.33 pts
160
MiniMax M1
164.66 pts
161
Mistral Large 2411
164.66 pts
162
Inflection 3 Productivity
164.66 pts
163
Jamba Large 1.7
164.33 pts
164
GPT-4 (older v0314)
164.33 pts
165
Mistral Small 3.2 24B
164.00 pts
166
ERNIE 4.5 300B A47B
164.00 pts
167
Nova Pro 1.0
164.00 pts
168
Qwen2.5 VL 72B Instruct
163.66 pts
169
Qwen2.5 72B Instruct
163.33 pts
170
MiMo-V2-Flash
163.33 pts
171
R1 Distill Llama 70B
163.33 pts
172
Hermes 4 70B
163.00 pts
173
Step3
162.66 pts
174
Saba
162.00 pts
175
Mercury Coder
161.33 pts
176
Mercury
161.33 pts
177
Kimi Dev 72B
161.33 pts
178
Pixtral Large 2411
160.33 pts
179
Hermes 3 405B Instruct
160.00 pts
180
GPT-4o-mini Search Preview
159.66 pts
181
Nemotron 3 Nano 30B A3B
158.66 pts
182
GLM 4.7 Flash
158.00 pts
183
GLM 4 32B
157.66 pts
184
Nova 2 Lite
157.33 pts
185
Mixtral 8x22B Instruct
157.00 pts
186
gpt-oss-20b
156.66 pts
187
Qwen3 14B
156.66 pts
188
Llama 3.1 70B Instruct
156.66 pts
189
MiniMax M2-her
156.66 pts
190
Mistral Small 3
156.33 pts
191
Cydonia 24B V4.1
156.33 pts
192
Nemotron Nano 12B 2 VL
155.66 pts
193
Llama 3.1 70B Hanami x1
155.66 pts
194
Qwen-Max
155.66 pts
195
Qwen VL Plus
155.00 pts
196
Mistral Small 3.1 24B
154.66 pts
197
Cogito V2 Preview Llama 70B
154.66 pts
198
QwQ 32B
154.66 pts
199
GPT-4o-mini (2024-07-18)
154.00 pts
200
Command A
154.00 pts
201
Gemma 3 27B
153.33 pts
202
Claude 3.5 Haiku
153.33 pts
203
Ministral 3 8B 2512
153.00 pts
204
Devstral Small 1.1
153.00 pts
205
Ministral 3 14B 2512
152.33 pts
206
Qwen3 VL 8B Thinking
152.33 pts
207
Llama 3 70B Instruct
152.00 pts
208
Qwen3 Coder Flash
152.00 pts
209
GPT-4o-mini
150.33 pts
210
Qwen3 Coder 30B A3B Instruct
149.66 pts
211
Voxtral Small 24B 2507
148.00 pts
212
Relace Search
146.00 pts
213
Trinity Mini
145.66 pts
214
Llama 3 Euryale 70B v2.1
144.66 pts
215
Olmo 3.1 32B Think
144.33 pts
216
Nemotron Nano 9B V2
143.33 pts
217
Qwen3 8B
141.66 pts
218
Qwen-Turbo
141.33 pts
219
Qwen3 VL 8B Instruct
140.33 pts
220
Skyfall 36B V2
139.33 pts
221
GPT-4.1 Nano
138.00 pts
222
Free Models Router
137.66 pts
223
Qwen2.5 VL 32B Instruct
137.66 pts
224
Nova Micro 1.0
137.33 pts
225
Llama 3.1 Euryale 70B v2.2
133.66 pts
226
Olmo 3 32B Think
133.66 pts
227
R1 Distill Qwen 32B
130.66 pts
228
Claude 3 Haiku
129.66 pts
229
Nova Lite 1.0
127.00 pts
230
ERNIE 4.5 21B A3B Thinking
126.66 pts
231
Gemma 3 12B
125.33 pts
232
SorcererLM 8x22B
124.00 pts
233
ERNIE 4.5 21B A3B
121.00 pts
234
Ministral 3 3B 2512
120.00 pts
235
GPT-3.5 Turbo 16k
119.33 pts
236
ERNIE 4.5 VL 28B A3B
118.66 pts
237
Gemma 2 27B
118.33 pts
238
Phi 4
117.33 pts
239
Qwen2.5 Coder 32B Instruct
115.00 pts
240
Mixtral 8x7B Instruct
115.00 pts
241
Gemma 2 9B
111.00 pts
242
Gemma 3n 4B
110.33 pts
243
Pixtral 12B
110.33 pts
244
GPT-3.5 Turbo
110.33 pts
245
Mistral Nemo
109.00 pts
246
Command R (08-2024)
108.00 pts
247
Command R+ (08-2024)
107.66 pts
248
Qwen2.5 7B Instruct
107.00 pts
249
Molmo2 8B
106.33 pts
250
Hunyuan A13B Instruct
106.00 pts
251
Olmo 3.1 32B Instruct
103.00 pts
252
Jamba Mini 1.7
101.33 pts
253
GPT-3.5 Turbo Instruct
100.66 pts
254
Ministral 8B
99.33 pts
255
Olmo 3 7B Think
93.66 pts
256
LFM2-8B-A1B
91.66 pts
257
Llama 3 8B Lunaris
89.33 pts
258
Gemma 3 4B
84.00 pts
259
Codestral 2508
81.66 pts
260
Goliath 120B
76.33 pts
261
Mistral 7B Instruct v0.2
76.00 pts
262
Mistral 7B Instruct v0.3
75.66 pts
263
Llama 3 8B Instruct
73.00 pts
264
Mistral 7B Instruct
72.00 pts
265
UnslopNemo 12B
71.66 pts
266
Ministral 3B
69.33 pts
267
Qwen2.5-VL 7B Instruct
67.66 pts
268
Mistral Tiny
67.00 pts
269
Command R7B (12-2024)
65.66 pts
270
Hermes 2 Pro - Llama-3 8B
65.00 pts
271
Llama 3.1 8B Instruct
63.33 pts
272
Granite 4.0 Micro
62.66 pts
273
Llama 3.2 3B Instruct
62.33 pts
274
Rocinante 12B
61.66 pts
275
Hermes 3 70B Instruct
57.66 pts
276
Olmo 3 7B Instruct
56.33 pts
277
Mistral 7B Instruct v0.1
52.00 pts
278
Llama 3.2 11B Vision Instruct
52.00 pts
279
Rnj 1 Instruct
51.33 pts
280
Lumimaid v0.2 8B
50.33 pts
281
Weaver (alpha)
44.66 pts
282
Morph V3 Large
40.66 pts
283
Aion-RP 1.0 (8B)
40.33 pts
284
ReMM SLERP 13B
38.33 pts
285
MythoMax 13B
33.33 pts
286
Noromaid 20B
28.66 pts
287
Llama 3.2 1B Instruct
24.66 pts
288
Morph V3 Fast
11.33 pts
289
Llemma 7b
9.33 pts
290
CodeLLaMa 7B Instruct Solidity
0.00 pts
Media:154.02 pts
(290 modelos)
Menú de métricas
Aciertos obtenidos
Número total de respuestas correctas
1
Gemini 3 Flash Preview
199
2
o3
199
3
GPT-5
199
4
GPT-5.1 Chat
198
5
GPT-5 Codex
198
6
GPT-5.1-Codex-Max
198
7
Nano Banana Pro (Gemini 3 Pro Image Preview)
198
8
Gemini 3 Pro Preview
198
9
Gemini 2.5 Pro Preview 05-06
198
10
o1
198
11
GPT-5.2 Pro
198
12
o3 Deep Research
198
13
GPT-5 Image
197
14
Claude Opus 4.5
197
15
Claude Opus 4.6
197
16
Gemini 2.5 Pro Preview 06-05
197
17
Gemini 2.5 Pro
197
18
Claude Opus 4.1
197
19
o3 Pro
197
20
o1-pro
197
21
GPT-5.1
196
22
GPT-5.1-Codex
196
23
o4 Mini
196
24
o4 Mini Deep Research
196
25
Switchpoint Router
195
26
GPT-5 Chat
195
27
GPT-5.2-Codex
195
28
GPT-5.2
195
29
ChatGPT-4o
195
30
Gemini 2.5 Flash Image (Nano Banana)
194
31
Grok 4
194
32
Gemini 2.5 Flash Preview 09-2025
194
33
o4 Mini High
194
34
Llama 4 Maverick
194
35
GPT-5 Mini
194
36
GPT-5 Image Mini
194
37
GPT-4.1
194
38
GPT-5.2 Chat
194
39
Claude 3.7 Sonnet (thinking)
194
40
Qwen Plus 0728 (thinking)
193
41
Grok 4.1 Fast
193
42
GPT-5.1-Codex-Mini
193
43
GPT-4o (2024-05-13)
193
44
Claude Sonnet 4.5
193
45
Kimi K2.5
192
46
GLM 4.7
192
47
Auto Router
192
48
Claude Opus 4
192
49
Aion-1.0
192
50
Seed 1.6
192
51
Claude Sonnet 4
192
52
DeepSeek V3.2 Speciale
191
53
Grok 3
191
54
Mistral Large 3 2512
191
55
Qwen3 235B A22B Thinking 2507
191
56
Mistral Large 2407
191
57
Claude 3.7 Sonnet
191
58
Qwen3 VL 235B A22B Thinking
191
59
R1 0528
190
60
R1
190
61
Mistral Large
190
62
GPT-4o (2024-11-20)
190
63
Grok 3 Beta
190
64
o3 Mini High
190
65
Step 3.5 Flash
189
66
Qwen3 Max
189
67
Llama 3.3 Nemotron Super 49B V1.5
189
68
DeepSeek V3.1 Terminus
189
69
Sonar Deep Research
189
70
DeepSeek V3.1 Terminus (exacto)
189
71
Qwen3 235B A22B
189
72
Qwen3 Next 80B A3B Thinking
189
73
Grok 4 Fast
189
74
Qwen3 235B A22B Instruct 2507
188
75
Gemini 2.5 Flash
188
76
GLM 4.5
188
77
Gemini 2.0 Flash
188
78
DeepSeek V3.2
188
79
o3 Mini
188
80
Claude 3.5 Sonnet
188
81
gpt-oss-120b (exacto)
188
82
Kimi K2 Thinking
187
83
GLM 4.6 (exacto)
187
84
gpt-oss-120b
187
85
GPT-3.5 Turbo (older v0613)
187
86
GPT-4.1 Mini
187
87
Qwen-Plus
186
88
GLM 4.6
186
89
Mistral Medium 3.1
186
90
DeepSeek V3.2 Exp
185
91
DeepSeek V3.1
185
92
Grok 3 Mini Beta
185
93
Qwen3 Next 80B A3B Instruct
185
94
KAT-Coder-Pro V1
185
95
Qwen3 VL 235B A22B Instruct
185
96
GPT-5 Nano
184
97
DeepSeek V3.1 Nex N1
184
98
Palmyra X5
184
99
Qwen3 VL 32B Instruct
184
100
DeepSeek V3 0324
184
101
GPT-4o
183
102
MiniMax M2.1
183
103
Cogito v2.1 671B
183
104
GPT-4o Search Preview
183
105
Sonar Pro Search
183
106
DeepSeek V3
183
107
Devstral Medium
183
108
Devstral 2 2512
183
109
Mistral Medium 3
183
110
Grok 3 Mini
182
111
Qwen Plus 0728
182
112
Kimi K2 0711
182
113
Qwen3 32B
182
114
Qwen3 VL 30B A3B Thinking
182
115
Qwen VL Max
182
116
Tongyi DeepResearch 30B A3B
181
117
Qwen3 Coder 480B A35B (exacto)
181
118
MiniMax M2
181
119
Gemini 2.5 Flash Lite Preview 09-2025
181
120
GLM 4.6V
180
121
Llama 3.1 Nemotron 70B Instruct
180
122
Llama 4 Scout
180
123
GPT-4o (2024-08-06)
179
124
Sonar Reasoning Pro
179
125
Gemini 2.0 Flash Lite
179
126
Qwen3 Coder Plus
179
127
Solar Pro 3
179
128
GLM 4.5V
179
129
Llama 3.1 Nemotron Ultra 253B v1
179
130
Hermes 4 405B
178
131
GPT-4 Turbo
178
132
Qwen3 30B A3B Thinking 2507
178
133
Claude Haiku 4.5
178
134
Kimi K2 0905
177
135
GPT-4 Turbo Preview
177
136
gpt-oss-safeguard-20b
177
137
Qwen3 Coder 480B A35B
177
138
ERNIE 4.5 VL 424B A47B
177
139
Sonar Pro
177
140
Kimi K2 0905 (exacto)
176
141
Inflection 3 Pi
176
142
Qwen3 VL 30B A3B Instruct
176
143
Qwen3 Coder Next
176
144
Seed 1.6 Flash
176
145
Aion-1.0-Mini
175
146
Nova Premier 1.0
175
147
Gemini 2.5 Flash Lite
175
148
GPT-4 Turbo (older v1106)
174
149
Grok Code Fast 1
174
150
Sonar
174
151
Mistral Small Creative
174
152
MiMo-V2-Flash
174
153
Cogito V2 Preview Llama 405B
173
154
GPT-4
173
155
Qwen3 30B A3B Instruct 2507
173
156
Trinity Large Preview
173
157
Mistral Large 2411
173
158
ERNIE 4.5 300B A47B
173
159
Llama 3.3 70B Instruct
172
160
GLM 4.5 Air
172
161
Inflection 3 Productivity
172
162
Jamba Large 1.7
172
163
GPT-4 (older v0314)
172
164
Mistral Small 3.2 24B
172
165
Nova Pro 1.0
172
166
Qwen2.5 VL 72B Instruct
172
167
MiMo-V2-Flash
172
168
R1 Distill Llama 70B
172
169
Step3
172
170
Llama 3.3 Euryale 70B
171
171
MiniMax M1
171
172
Qwen2.5 72B Instruct
171
173
Hermes 4 70B
170
174
Saba
170
175
Mercury Coder
170
176
Mercury
170
177
Pixtral Large 2411
170
178
Kimi Dev 72B
169
179
GPT-4o-mini Search Preview
169
180
Nemotron 3 Nano 30B A3B
169
181
Hermes 3 405B Instruct
168
182
GLM 4.7 Flash
168
183
GLM 4 32B
167
184
Mixtral 8x22B Instruct
167
185
gpt-oss-20b
167
186
Nova 2 Lite
166
187
Qwen3 14B
166
188
Llama 3.1 70B Instruct
166
189
Cydonia 24B V4.1
166
190
Nemotron Nano 12B 2 VL
166
191
Qwen-Max
166
192
Qwen VL Plus
166
193
QwQ 32B
166
194
MiniMax M2-her
165
195
Mistral Small 3
165
196
Mistral Small 3.1 24B
165
197
Gemma 3 27B
165
198
Cogito V2 Preview Llama 70B
164
199
GPT-4o-mini (2024-07-18)
164
200
Command A
164
201
Claude 3.5 Haiku
164
202
Ministral 3 8B 2512
164
203
Ministral 3 14B 2512
164
204
Qwen3 VL 8B Thinking
164
205
Qwen3 Coder Flash
164
206
Llama 3.1 70B Hanami x1
163
207
Llama 3 70B Instruct
163
208
Devstral Small 1.1
162
209
GPT-4o-mini
162
210
Qwen3 Coder 30B A3B Instruct
162
211
Voxtral Small 24B 2507
160
212
Relace Search
159
213
Llama 3 Euryale 70B v2.1
157
214
Trinity Mini
156
215
Nemotron Nano 9B V2
155
216
Qwen3 8B
155
217
Qwen-Turbo
154
218
Qwen3 VL 8B Instruct
154
219
Olmo 3.1 32B Think
153
220
GPT-4.1 Nano
153
221
Free Models Router
152
222
Qwen2.5 VL 32B Instruct
152
223
Skyfall 36B V2
151
224
Nova Micro 1.0
151
225
R1 Distill Qwen 32B
147
226
Claude 3 Haiku
146
227
Llama 3.1 Euryale 70B v2.2
145
228
Olmo 3 32B Think
145
229
ERNIE 4.5 21B A3B Thinking
145
230
Nova Lite 1.0
144
231
Gemma 3 12B
144
232
SorcererLM 8x22B
142
233
ERNIE 4.5 21B A3B
139
234
Ministral 3 3B 2512
139
235
GPT-3.5 Turbo 16k
138
236
ERNIE 4.5 VL 28B A3B
138
237
Phi 4
137
238
Gemma 2 27B
135
239
Qwen2.5 Coder 32B Instruct
134
240
GPT-3.5 Turbo
132
241
Mixtral 8x7B Instruct
131
242
Gemma 3n 4B
130
243
Command R (08-2024)
130
244
Pixtral 12B
129
245
Mistral Nemo
128
246
Command R+ (08-2024)
127
247
Qwen2.5 7B Instruct
127
248
Molmo2 8B
127
249
Gemma 2 9B
126
250
Olmo 3.1 32B Instruct
125
251
Jamba Mini 1.7
124
252
GPT-3.5 Turbo Instruct
124
253
Hunyuan A13B Instruct
123
254
Ministral 8B
122
255
Olmo 3 7B Think
120
256
LFM2-8B-A1B
118
257
Llama 3 8B Lunaris
112
258
Gemma 3 4B
112
259
Codestral 2508
108
260
Mistral 7B Instruct v0.2
105
261
Mistral 7B Instruct v0.3
104
262
Goliath 120B
101
263
Mistral 7B Instruct
101
264
Llama 3 8B Instruct
99
265
Ministral 3B
97
266
Mistral Tiny
97
267
Command R7B (12-2024)
97
268
Granite 4.0 Micro
96
269
Hermes 2 Pro - Llama-3 8B
92
270
Llama 3.2 3B Instruct
91
271
UnslopNemo 12B
89
272
Qwen2.5-VL 7B Instruct
88
273
Olmo 3 7B Instruct
88
274
Llama 3.1 8B Instruct
86
275
Lumimaid v0.2 8B
86
276
Rocinante 12B
82
277
Rnj 1 Instruct
81
278
Mistral 7B Instruct v0.1
80
279
Hermes 3 70B Instruct
76
280
Weaver (alpha)
72
281
ReMM SLERP 13B
68
282
Llama 3.2 11B Vision Instruct
66
283
MythoMax 13B
64
284
Noromaid 20B
62
285
Aion-RP 1.0 (8B)
60
286
Morph V3 Large
51
287
Llama 3.2 1B Instruct
44
288
Morph V3 Fast
30
289
Llemma 7b
17
290
CodeLLaMa 7B Instruct Solidity
3
Total:47350
Media:163.27
(290 modelos)
Menú de métricas
Fallos cometidos
Número total de respuestas incorrectas
1
Gemini 3 Flash Preview
1
2
o3
1
3
GPT-5
1
4
GPT-5.1 Chat
2
5
GPT-5 Codex
2
6
GPT-5.1-Codex-Max
2
7
Nano Banana Pro (Gemini 3 Pro Image Preview)
2
8
Gemini 3 Pro Preview
2
9
Gemini 2.5 Pro Preview 05-06
2
10
o1
2
11
GPT-5.2 Pro
2
12
o3 Deep Research
2
13
GPT-5 Image
3
14
Claude Opus 4.5
3
15
Claude Opus 4.6
3
16
Gemini 2.5 Pro Preview 06-05
3
17
Gemini 2.5 Pro
3
18
Claude Opus 4.1
3
19
o3 Pro
3
20
o1-pro
3
21
GPT-5.1
3
22
Switchpoint Router
3
23
GPT-5.1-Codex
4
24
o4 Mini
4
25
o4 Mini Deep Research
4
26
Gemini 2.5 Flash Image (Nano Banana)
4
27
Grok 4
4
28
Kimi K2.5
4
29
GPT-5 Chat
5
30
GPT-5.2-Codex
5
31
GPT-5.2
5
32
ChatGPT-4o
5
33
Gemini 2.5 Flash Preview 09-2025
5
34
o4 Mini High
5
35
GLM 4.7
5
36
Llama 4 Maverick
6
37
GPT-5 Mini
6
38
GPT-5 Image Mini
6
39
GPT-4.1
6
40
GPT-5.2 Chat
6
41
Claude 3.7 Sonnet (thinking)
6
42
Qwen Plus 0728 (thinking)
6
43
Auto Router
6
44
Claude Opus 4
6
45
DeepSeek V3.2 Speciale
6
46
Grok 4.1 Fast
7
47
GPT-5.1-Codex-Mini
7
48
GPT-4o (2024-05-13)
7
49
Claude Sonnet 4.5
7
50
Aion-1.0
7
51
Grok 3
7
52
R1 0528
7
53
Step 3.5 Flash
7
54
Kimi K2 Thinking
7
55
GPT-4o
7
56
GPT-4o (2024-08-06)
7
57
Seed 1.6
8
58
Claude Sonnet 4
8
59
Mistral Large 3 2512
8
60
Qwen3 235B A22B Thinking 2507
8
61
Mistral Large 2407
8
62
Claude 3.7 Sonnet
8
63
Qwen3 Max
8
64
Qwen3 VL 235B A22B Thinking
9
65
R1
9
66
Mistral Large
9
67
GPT-4o (2024-11-20)
9
68
Grok 3 Beta
9
69
Llama 3.3 Nemotron Super 49B V1.5
9
70
DeepSeek V3.1 Terminus
9
71
Sonar Deep Research
9
72
GLM 4.6 (exacto)
9
73
MiniMax M2.1
9
74
o3 Mini High
10
75
DeepSeek V3.1 Terminus (exacto)
10
76
Qwen3 235B A22B
10
77
Qwen3 Next 80B A3B Thinking
10
78
Qwen3 235B A22B Instruct 2507
10
79
Gemini 2.5 Flash
10
80
GLM 4.5
10
81
Qwen-Plus
10
82
DeepSeek V3.2 Exp
10
83
Cogito v2.1 671B
10
84
Grok 4 Fast
11
85
Gemini 2.0 Flash
11
86
DeepSeek V3.2
11
87
o3 Mini
11
88
Claude 3.5 Sonnet
11
89
GPT-5 Nano
11
90
gpt-oss-120b (exacto)
12
91
gpt-oss-120b
12
92
GPT-3.5 Turbo (older v0613)
12
93
GLM 4.6
12
94
DeepSeek V3.1 Nex N1
12
95
Kimi K2 0905
12
96
GPT-4.1 Mini
13
97
DeepSeek V3.1
13
98
Grok 3 Mini Beta
13
99
Palmyra X5
13
100
GPT-4o Search Preview
13
101
Sonar Pro Search
13
102
Sonar Reasoning Pro
13
103
Kimi K2 0905 (exacto)
13
104
Mistral Medium 3.1
14
105
Qwen3 Next 80B A3B Instruct
14
106
Qwen3 VL 32B Instruct
14
107
DeepSeek V3
14
108
Devstral Medium
14
109
Grok 3 Mini
14
110
KAT-Coder-Pro V1
15
111
Qwen3 VL 235B A22B Instruct
15
112
Devstral 2 2512
15
113
Qwen Plus 0728
15
114
GLM 4.6V
15
115
Hermes 4 405B
15
116
Llama 3.3 Euryale 70B
15
117
DeepSeek V3 0324
16
118
Mistral Medium 3
16
119
Kimi K2 0711
16
120
Tongyi DeepResearch 30B A3B
16
121
Qwen3 Coder 480B A35B (exacto)
16
122
MiniMax M2
16
123
Llama 3.1 Nemotron 70B Instruct
16
124
Gemini 2.0 Flash Lite
16
125
Qwen3 Coder Plus
16
126
Qwen3 32B
17
127
Qwen3 VL 30B A3B Thinking
17
128
Qwen VL Max
17
129
Gemini 2.5 Flash Lite Preview 09-2025
17
130
Solar Pro 3
18
131
GLM 4.5V
18
132
GPT-4 Turbo Preview
18
133
Inflection 3 Pi
18
134
Llama 3.3 70B Instruct
18
135
GPT-4 Turbo
19
136
GPT-4 Turbo (older v1106)
19
137
MiniMax M1
19
138
Llama 4 Scout
20
139
Llama 3.1 Nemotron Ultra 253B v1
20
140
Qwen3 30B A3B Thinking 2507
20
141
Claude Haiku 4.5
20
142
Aion-1.0-Mini
20
143
Cogito V2 Preview Llama 405B
20
144
GLM 4.5 Air
20
145
gpt-oss-safeguard-20b
21
146
Qwen3 VL 30B A3B Instruct
21
147
Nova Premier 1.0
21
148
Grok Code Fast 1
21
149
GPT-4
21
150
Hermes 4 70B
21
151
CodeLLaMa 7B Instruct Solidity
21
152
Qwen3 Coder 480B A35B
22
153
Sonar
22
154
Qwen3 30B A3B Instruct 2507
22
155
Inflection 3 Productivity
22
156
Llama 3.1 70B Hanami x1
22
157
ERNIE 4.5 VL 424B A47B
23
158
Sonar Pro
23
159
Qwen3 Coder Next
23
160
Trinity Large Preview
23
161
Jamba Large 1.7
23
162
GPT-4 (older v0314)
23
163
Qwen2.5 72B Instruct
23
164
Kimi Dev 72B
23
165
Llemma 7b
23
166
Seed 1.6 Flash
24
167
Mistral Small Creative
24
168
Mistral Small 3.2 24B
24
169
Nova Pro 1.0
24
170
Saba
24
171
Hermes 3 405B Instruct
24
172
Gemini 2.5 Flash Lite
25
173
MiMo-V2-Flash
25
174
Mistral Large 2411
25
175
Qwen2.5 VL 72B Instruct
25
176
MiniMax M2-her
25
177
MiMo-V2-Flash
26
178
R1 Distill Llama 70B
26
179
Mercury Coder
26
180
Mercury
26
181
Nova 2 Lite
26
182
Mistral Small 3
26
183
Olmo 3.1 32B Think
26
184
ERNIE 4.5 300B A47B
27
185
Devstral Small 1.1
27
186
Step3
28
187
GPT-4o-mini Search Preview
28
188
GLM 4 32B
28
189
Qwen3 14B
28
190
Llama 3.1 70B Instruct
28
191
Cogito V2 Preview Llama 70B
28
192
Pixtral Large 2411
29
193
Cydonia 24B V4.1
29
194
GLM 4.7 Flash
30
195
Mixtral 8x22B Instruct
30
196
GPT-4o-mini (2024-07-18)
30
197
Command A
30
198
Nemotron 3 Nano 30B A3B
31
199
gpt-oss-20b
31
200
Nemotron Nano 12B 2 VL
31
201
Qwen-Max
31
202
Mistral Small 3.1 24B
31
203
Trinity Mini
31
204
Morph V3 Large
31
205
Claude 3.5 Haiku
32
206
Qwen VL Plus
33
207
Ministral 3 8B 2512
33
208
Llama 3 70B Instruct
33
209
QwQ 32B
34
210
Llama 3.1 Euryale 70B v2.2
34
211
Olmo 3 32B Think
34
212
Gemma 3 27B
35
213
Ministral 3 14B 2512
35
214
Qwen3 VL 8B Thinking
35
215
GPT-4o-mini
35
216
Nemotron Nano 9B V2
35
217
Skyfall 36B V2
35
218
Qwen3 Coder Flash
36
219
Voxtral Small 24B 2507
36
220
Qwen3 Coder 30B A3B Instruct
37
221
Llama 3 Euryale 70B v2.1
37
222
Qwen-Turbo
38
223
Relace Search
39
224
Qwen3 8B
40
225
Qwen3 VL 8B Instruct
41
226
Nova Micro 1.0
41
227
Llama 3.2 11B Vision Instruct
42
228
Free Models Router
43
229
Qwen2.5 VL 32B Instruct
43
230
GPT-4.1 Nano
45
231
Gemma 2 9B
45
232
Mixtral 8x7B Instruct
48
233
R1 Distill Qwen 32B
49
234
Claude 3 Haiku
49
235
Gemma 2 27B
50
236
Nova Lite 1.0
51
237
Hunyuan A13B Instruct
51
238
UnslopNemo 12B
52
239
SorcererLM 8x22B
54
240
ERNIE 4.5 21B A3B
54
241
ERNIE 4.5 21B A3B Thinking
55
242
Hermes 3 70B Instruct
55
243
Gemma 3 12B
56
244
GPT-3.5 Turbo 16k
56
245
Pixtral 12B
56
246
Morph V3 Fast
56
247
Ministral 3 3B 2512
57
248
Qwen2.5 Coder 32B Instruct
57
249
Mistral Nemo
57
250
ERNIE 4.5 VL 28B A3B
58
251
Command R+ (08-2024)
58
252
Llama 3.2 1B Instruct
58
253
Phi 4
59
254
Gemma 3n 4B
59
255
Aion-RP 1.0 (8B)
59
256
Qwen2.5 7B Instruct
60
257
Qwen2.5-VL 7B Instruct
61
258
Rocinante 12B
61
259
Molmo2 8B
62
260
GPT-3.5 Turbo
65
261
Command R (08-2024)
66
262
Olmo 3.1 32B Instruct
66
263
Jamba Mini 1.7
68
264
Ministral 8B
68
265
Llama 3 8B Lunaris
68
266
Llama 3.1 8B Instruct
68
267
GPT-3.5 Turbo Instruct
70
268
Goliath 120B
74
269
Llama 3 8B Instruct
78
270
Olmo 3 7B Think
79
271
LFM2-8B-A1B
79
272
Codestral 2508
79
273
Hermes 2 Pro - Llama-3 8B
81
274
Weaver (alpha)
82
275
Ministral 3B
83
276
Gemma 3 4B
84
277
Mistral 7B Instruct v0.1
84
278
Mistral 7B Instruct v0.3
85
279
Llama 3.2 3B Instruct
86
280
Mistral 7B Instruct v0.2
87
281
Mistral 7B Instruct
87
282
Rnj 1 Instruct
89
283
ReMM SLERP 13B
89
284
Mistral Tiny
90
285
MythoMax 13B
92
286
Command R7B (12-2024)
94
287
Olmo 3 7B Instruct
95
288
Granite 4.0 Micro
100
289
Noromaid 20B
100
290
Lumimaid v0.2 8B
107
Total:8062
Media:27.8
(290 modelos)
Menú de métricas
Porcentaje de aciertos
Proporción de respuestas correctas sobre el total
1
Gemini 3 Flash Preview
99.5%
2
o3
99.5%
3
GPT-5
99.5%
4
GPT-5.1 Chat
99.0%
5
GPT-5 Codex
99.0%
6
GPT-5.1-Codex-Max
99.0%
7
Nano Banana Pro (Gemini 3 Pro Image Preview)
99.0%
8
Gemini 3 Pro Preview
99.0%
9
Gemini 2.5 Pro Preview 05-06
99.0%
10
o1
99.0%
11
GPT-5.2 Pro
99.0%
12
o3 Deep Research
99.0%
13
GPT-5 Image
98.5%
14
Claude Opus 4.5
98.5%
15
Claude Opus 4.6
98.5%
16
Gemini 2.5 Pro Preview 06-05
98.5%
17
Gemini 2.5 Pro
98.5%
18
Claude Opus 4.1
98.5%
19
o3 Pro
98.5%
20
o1-pro
98.5%
21
GPT-5.1
98.0%
22
GPT-5.1-Codex
98.0%
23
o4 Mini
98.0%
24
o4 Mini Deep Research
98.0%
25
Switchpoint Router
97.5%
26
GPT-5 Chat
97.5%
27
GPT-5.2-Codex
97.5%
28
GPT-5.2
97.5%
29
ChatGPT-4o
97.5%
30
Gemini 2.5 Flash Image (Nano Banana)
97.0%
31
Grok 4
97.0%
32
Gemini 2.5 Flash Preview 09-2025
97.0%
33
o4 Mini High
97.0%
34
Llama 4 Maverick
97.0%
35
GPT-5 Mini
97.0%
36
GPT-5 Image Mini
97.0%
37
GPT-4.1
97.0%
38
GPT-5.2 Chat
97.0%
39
Claude 3.7 Sonnet (thinking)
97.0%
40
Qwen Plus 0728 (thinking)
96.5%
41
Grok 4.1 Fast
96.5%
42
GPT-5.1-Codex-Mini
96.5%
43
GPT-4o (2024-05-13)
96.5%
44
Claude Sonnet 4.5
96.5%
45
Kimi K2.5
96.0%
46
GLM 4.7
96.0%
47
Auto Router
96.0%
48
Claude Opus 4
96.0%
49
Aion-1.0
96.0%
50
Seed 1.6
96.0%
51
Claude Sonnet 4
96.0%
52
DeepSeek V3.2 Speciale
95.5%
53
Grok 3
95.5%
54
Mistral Large 3 2512
95.5%
55
Qwen3 235B A22B Thinking 2507
95.5%
56
Mistral Large 2407
95.5%
57
Claude 3.7 Sonnet
95.5%
58
Qwen3 VL 235B A22B Thinking
95.5%
59
R1 0528
95.0%
60
R1
95.0%
61
Mistral Large
95.0%
62
GPT-4o (2024-11-20)
95.0%
63
Grok 3 Beta
95.0%
64
o3 Mini High
95.0%
65
Step 3.5 Flash
94.5%
66
Qwen3 Max
94.5%
67
Llama 3.3 Nemotron Super 49B V1.5
94.5%
68
DeepSeek V3.1 Terminus
94.5%
69
Sonar Deep Research
94.5%
70
DeepSeek V3.1 Terminus (exacto)
94.5%
71
Qwen3 235B A22B
94.5%
72
Qwen3 Next 80B A3B Thinking
94.5%
73
Grok 4 Fast
94.5%
74
Qwen3 235B A22B Instruct 2507
94.0%
75
Gemini 2.5 Flash
94.0%
76
GLM 4.5
94.0%
77
Gemini 2.0 Flash
94.0%
78
DeepSeek V3.2
94.0%
79
o3 Mini
94.0%
80
Claude 3.5 Sonnet
94.0%
81
gpt-oss-120b (exacto)
94.0%
82
Kimi K2 Thinking
93.5%
83
GLM 4.6 (exacto)
93.5%
84
gpt-oss-120b
93.5%
85
GPT-3.5 Turbo (older v0613)
93.5%
86
GPT-4.1 Mini
93.5%
87
Qwen-Plus
93.0%
88
GLM 4.6
93.0%
89
Mistral Medium 3.1
93.0%
90
DeepSeek V3.2 Exp
92.5%
91
DeepSeek V3.1
92.5%
92
Grok 3 Mini Beta
92.5%
93
Qwen3 Next 80B A3B Instruct
92.5%
94
KAT-Coder-Pro V1
92.5%
95
Qwen3 VL 235B A22B Instruct
92.5%
96
GPT-5 Nano
92.0%
97
DeepSeek V3.1 Nex N1
92.0%
98
Palmyra X5
92.0%
99
Qwen3 VL 32B Instruct
92.0%
100
DeepSeek V3 0324
92.0%
101
GPT-4o
91.5%
102
MiniMax M2.1
91.5%
103
Cogito v2.1 671B
91.5%
104
GPT-4o Search Preview
91.5%
105
Sonar Pro Search
91.5%
106
DeepSeek V3
91.5%
107
Devstral Medium
91.5%
108
Devstral 2 2512
91.5%
109
Mistral Medium 3
91.5%
110
Grok 3 Mini
91.0%
111
Qwen Plus 0728
91.0%
112
Kimi K2 0711
91.0%
113
Qwen3 32B
91.0%
114
Qwen3 VL 30B A3B Thinking
91.0%
115
Qwen VL Max
91.0%
116
Tongyi DeepResearch 30B A3B
90.5%
117
Qwen3 Coder 480B A35B (exacto)
90.5%
118
MiniMax M2
90.5%
119
Gemini 2.5 Flash Lite Preview 09-2025
90.5%
120
GLM 4.6V
90.0%
121
Llama 3.1 Nemotron 70B Instruct
90.0%
122
Llama 4 Scout
90.0%
123
GPT-4o (2024-08-06)
89.5%
124
Sonar Reasoning Pro
89.5%
125
Gemini 2.0 Flash Lite
89.5%
126
Qwen3 Coder Plus
89.5%
127
Solar Pro 3
89.5%
128
GLM 4.5V
89.5%
129
Llama 3.1 Nemotron Ultra 253B v1
89.5%
130
Hermes 4 405B
89.0%
131
GPT-4 Turbo
89.0%
132
Qwen3 30B A3B Thinking 2507
89.0%
133
Claude Haiku 4.5
89.0%
134
Kimi K2 0905
88.5%
135
GPT-4 Turbo Preview
88.5%
136
gpt-oss-safeguard-20b
88.5%
137
Qwen3 Coder 480B A35B
88.5%
138
ERNIE 4.5 VL 424B A47B
88.5%
139
Sonar Pro
88.5%
140
Kimi K2 0905 (exacto)
88.0%
141
Inflection 3 Pi
88.0%
142
Qwen3 VL 30B A3B Instruct
88.0%
143
Qwen3 Coder Next
88.0%
144
Seed 1.6 Flash
88.0%
145
Aion-1.0-Mini
87.5%
146
Nova Premier 1.0
87.5%
147
Gemini 2.5 Flash Lite
87.5%
148
GPT-4 Turbo (older v1106)
87.0%
149
Grok Code Fast 1
87.0%
150
Sonar
87.0%
151
Mistral Small Creative
87.0%
152
MiMo-V2-Flash
87.0%
153
Cogito V2 Preview Llama 405B
86.5%
154
GPT-4
86.5%
155
Qwen3 30B A3B Instruct 2507
86.5%
156
Trinity Large Preview
86.5%
157
Mistral Large 2411
86.5%
158
ERNIE 4.5 300B A47B
86.5%
159
Llama 3.3 70B Instruct
86.0%
160
GLM 4.5 Air
86.0%
161
Inflection 3 Productivity
86.0%
162
Jamba Large 1.7
86.0%
163
GPT-4 (older v0314)
86.0%
164
Mistral Small 3.2 24B
86.0%
165
Nova Pro 1.0
86.0%
166
Qwen2.5 VL 72B Instruct
86.0%
167
MiMo-V2-Flash
86.0%
168
R1 Distill Llama 70B
86.0%
169
Step3
86.0%
170
Llama 3.3 Euryale 70B
85.5%
171
MiniMax M1
85.5%
172
Qwen2.5 72B Instruct
85.5%
173
Hermes 4 70B
85.0%
174
Saba
85.0%
175
Mercury Coder
85.0%
176
Mercury
85.0%
177
Pixtral Large 2411
85.0%
178
Kimi Dev 72B
84.5%
179
GPT-4o-mini Search Preview
84.5%
180
Nemotron 3 Nano 30B A3B
84.5%
181
Hermes 3 405B Instruct
84.0%
182
GLM 4.7 Flash
84.0%
183
GLM 4 32B
83.5%
184
Mixtral 8x22B Instruct
83.5%
185
gpt-oss-20b
83.5%
186
Nova 2 Lite
83.0%
187
Qwen3 14B
83.0%
188
Llama 3.1 70B Instruct
83.0%
189
Cydonia 24B V4.1
83.0%
190
Nemotron Nano 12B 2 VL
83.0%
191
Qwen-Max
83.0%
192
Qwen VL Plus
83.0%
193
QwQ 32B
83.0%
194
MiniMax M2-her
82.5%
195
Mistral Small 3
82.5%
196
Mistral Small 3.1 24B
82.5%
197
Gemma 3 27B
82.5%
198
Cogito V2 Preview Llama 70B
82.0%
199
GPT-4o-mini (2024-07-18)
82.0%
200
Command A
82.0%
201
Claude 3.5 Haiku
82.0%
202
Ministral 3 8B 2512
82.0%
203
Ministral 3 14B 2512
82.0%
204
Qwen3 VL 8B Thinking
82.0%
205
Qwen3 Coder Flash
82.0%
206
Llama 3.1 70B Hanami x1
81.5%
207
Llama 3 70B Instruct
81.5%
208
Devstral Small 1.1
81.0%
209
GPT-4o-mini
81.0%
210
Qwen3 Coder 30B A3B Instruct
81.0%
211
Voxtral Small 24B 2507
80.0%
212
Relace Search
79.5%
213
Llama 3 Euryale 70B v2.1
78.5%
214
Trinity Mini
78.0%
215
Nemotron Nano 9B V2
77.5%
216
Qwen3 8B
77.5%
217
Qwen-Turbo
77.0%
218
Qwen3 VL 8B Instruct
77.0%
219
Olmo 3.1 32B Think
76.5%
220
GPT-4.1 Nano
76.5%
221
Free Models Router
76.0%
222
Qwen2.5 VL 32B Instruct
76.0%
223
Skyfall 36B V2
75.5%
224
Nova Micro 1.0
75.5%
225
R1 Distill Qwen 32B
73.5%
226
Claude 3 Haiku
73.0%
227
Llama 3.1 Euryale 70B v2.2
72.5%
228
Olmo 3 32B Think
72.5%
229
ERNIE 4.5 21B A3B Thinking
72.5%
230
Nova Lite 1.0
72.0%
231
Gemma 3 12B
72.0%
232
SorcererLM 8x22B
71.0%
233
ERNIE 4.5 21B A3B
69.5%
234
Ministral 3 3B 2512
69.5%
235
GPT-3.5 Turbo 16k
69.0%
236
ERNIE 4.5 VL 28B A3B
69.0%
237
Phi 4
68.5%
238
Gemma 2 27B
67.5%
239
Qwen2.5 Coder 32B Instruct
67.0%
240
GPT-3.5 Turbo
66.0%
241
Mixtral 8x7B Instruct
65.5%
242
Gemma 3n 4B
65.0%
243
Command R (08-2024)
65.0%
244
Pixtral 12B
64.5%
245
Mistral Nemo
64.0%
246
Command R+ (08-2024)
63.5%
247
Qwen2.5 7B Instruct
63.5%
248
Molmo2 8B
63.5%
249
Gemma 2 9B
63.0%
250
Olmo 3.1 32B Instruct
62.5%
251
Jamba Mini 1.7
62.0%
252
GPT-3.5 Turbo Instruct
62.0%
253
Hunyuan A13B Instruct
61.5%
254
Ministral 8B
61.0%
255
Olmo 3 7B Think
60.0%
256
LFM2-8B-A1B
59.0%
257
Llama 3 8B Lunaris
56.0%
258
Gemma 3 4B
56.0%
259
Codestral 2508
54.0%
260
Mistral 7B Instruct v0.2
52.5%
261
Mistral 7B Instruct v0.3
52.0%
262
Goliath 120B
50.5%
263
Mistral 7B Instruct
50.5%
264
Llama 3 8B Instruct
49.5%
265
Ministral 3B
48.5%
266
Mistral Tiny
48.5%
267
Command R7B (12-2024)
48.5%
268
Granite 4.0 Micro
48.0%
269
Hermes 2 Pro - Llama-3 8B
46.0%
270
Llama 3.2 3B Instruct
45.5%
271
UnslopNemo 12B
44.5%
272
Qwen2.5-VL 7B Instruct
44.0%
273
Olmo 3 7B Instruct
44.0%
274
Llama 3.1 8B Instruct
43.0%
275
Lumimaid v0.2 8B
43.0%
276
Rocinante 12B
41.0%
277
Rnj 1 Instruct
40.5%
278
Mistral 7B Instruct v0.1
40.0%
279
Hermes 3 70B Instruct
38.0%
280
Weaver (alpha)
36.0%
281
ReMM SLERP 13B
34.0%
282
Llama 3.2 11B Vision Instruct
33.0%
283
MythoMax 13B
32.0%
284
Noromaid 20B
31.0%
285
Aion-RP 1.0 (8B)
30.0%
286
Morph V3 Large
25.5%
287
Llama 3.2 1B Instruct
22.0%
288
Morph V3 Fast
15.0%
289
Llemma 7b
8.5%
290
CodeLLaMa 7B Instruct Solidity
1.5%
Media:81.6%
(290 modelos)
Menú de métricas
Tiempo promedio de respuesta
Tiempo promedio que tarda el modelo en responder a cada pregunta
1
Ministral 3B
1.2s
2
Mistral 7B Instruct v0.3
1.8s
3
Ministral 8B
1.8s
4
Morph V3 Large
1.8s
5
Mistral 7B Instruct
1.9s
6
Voxtral Small 24B 2507
1.9s
7
Mercury
2.0s
8
Mistral 7B Instruct v0.2
2.0s
9
Mercury Coder
2.0s
10
LFM2-8B-A1B
2.1s
11
Codestral 2508
2.1s
12
Mistral Tiny
2.2s
13
Gemma 2 9B
2.3s
14
gpt-oss-safeguard-20b
2.4s
15
Nova Micro 1.0
2.5s
16
GPT-3.5 Turbo
2.6s
17
GPT-3.5 Turbo 16k
2.6s
18
Llama 3.2 1B Instruct
2.7s
19
GPT-5.1-Codex
2.7s
20
Gemini 2.0 Flash
3.0s
21
Gemini 2.5 Flash Lite
3.1s
22
Mixtral 8x22B Instruct
3.1s
23
Gemini 2.5 Flash Lite Preview 09-2025
3.1s
24
GPT-5.1-Codex-Mini
3.1s
25
Claude 3 Haiku
3.1s
26
GPT-5.1 Chat
3.2s
27
Ministral 3 3B 2512
3.2s
28
Devstral Small 1.1
3.3s
29
Gemini 2.0 Flash Lite
3.3s
30
Morph V3 Fast
3.4s
31
Command R7B (12-2024)
3.4s
32
Saba
3.4s
33
GPT-4.1 Nano
3.4s
34
Devstral Medium
3.5s
35
Nova Lite 1.0
3.5s
36
GPT-4o (2024-05-13)
3.6s
37
Jamba Mini 1.7
3.6s
38
GPT-5 Chat
3.6s
39
ChatGPT-4o
3.7s
40
Qwen3 Coder 480B A35B (exacto)
3.8s
41
GPT-3.5 Turbo Instruct
3.8s
42
Nova Pro 1.0
3.9s
43
GPT-5 Codex
3.9s
44
Lumimaid v0.2 8B
4.1s
45
Gemini 3 Flash Preview
4.2s
46
Pixtral 12B
4.2s
47
Hermes 2 Pro - Llama-3 8B
4.3s
48
GPT-4o-mini Search Preview
4.4s
49
Llama 3 8B Lunaris
4.4s
50
Relace Search
4.5s
51
Gemini 2.5 Flash
4.6s
52
GPT-4o (2024-11-20)
4.6s
53
Gemini 2.5 Flash Preview 09-2025
4.6s
54
Aion-1.0-Mini
4.7s
55
Hermes 4 70B
4.8s
56
Ministral 3 8B 2512
4.8s
57
Mistral Medium 3
4.9s
58
Cogito v2.1 671B
5.1s
59
Sonar Pro
5.4s
60
Gemma 2 27B
5.4s
61
Skyfall 36B V2
5.5s
62
Sonar
5.5s
63
o3 Mini High
5.7s
64
GPT-4o-mini
5.7s
65
o3 Mini
5.8s
66
GPT-4o-mini (2024-07-18)
5.8s
67
Claude Haiku 4.5
5.8s
68
GPT-4.1 Mini
5.9s
69
Rnj 1 Instruct
5.9s
70
Qwen2.5-VL 7B Instruct
5.9s
71
Llama 4 Maverick
6.1s
72
Llama 4 Scout
6.2s
73
Mistral Medium 3.1
6.3s
74
Mistral Nemo
6.3s
75
GPT-4o (2024-08-06)
6.5s
76
GPT-4o
6.6s
77
Ministral 3 14B 2512
6.6s
78
Qwen3 Coder Flash
6.6s
79
gpt-oss-20b
6.7s
80
Mistral Small 3.1 24B
6.7s
81
GPT-3.5 Turbo (older v0613)
6.8s
82
Claude 3.5 Haiku
6.8s
83
Kimi K2 0905 (exacto)
6.9s
84
Nova 2 Lite
7.0s
85
Mixtral 8x7B Instruct
7.0s
86
GLM 4 32B
7.0s
87
Hunyuan A13B Instruct
7.1s
88
Qwen3 Next 80B A3B Instruct
7.1s
89
KAT-Coder-Pro V1
7.2s
90
o4 Mini
7.2s
91
o3
7.3s
92
Seed 1.6 Flash
7.4s
93
ERNIE 4.5 21B A3B
7.4s
94
Palmyra X5
7.4s
95
MiniMax M2-her
7.5s
96
GPT-4.1
7.6s
97
Molmo2 8B
7.6s
98
Mistral Small Creative
7.6s
99
Cogito V2 Preview Llama 70B
7.6s
100
Qwen-Turbo
7.7s
101
Command A
7.7s
102
GPT-5.1-Codex-Max
7.7s
103
Mistral Large 2411
8.0s
104
Qwen VL Plus
8.0s
105
Mistral Small 3.2 24B
8.1s
106
Mistral Small 3
8.3s
107
Hermes 4 405B
8.4s
108
Aion-RP 1.0 (8B)
8.5s
109
Grok 4 Fast
8.5s
110
Cydonia 24B V4.1
8.6s
111
gpt-oss-120b
8.6s
112
GPT-5.2 Chat
8.7s
113
Inflection 3 Productivity
8.8s
114
Step 3.5 Flash
8.9s
115
Nemotron Nano 9B V2
9.0s
116
Llama 3 Euryale 70B v2.1
9.1s
117
Inflection 3 Pi
9.1s
118
o4 Mini High
9.1s
119
Rocinante 12B
9.1s
120
Sonar Pro Search
9.3s
121
Command R (08-2024)
9.5s
122
UnslopNemo 12B
9.6s
123
Devstral 2 2512
9.6s
124
Claude 3.5 Sonnet
9.7s
125
Qwen2.5 7B Instruct
9.9s
126
Llama 3.1 70B Instruct
9.9s
127
GPT-4 Turbo (older v1106)
9.9s
128
GPT-4
10.1s
129
Claude 3.7 Sonnet
10.2s
130
Claude Sonnet 4
10.3s
131
GPT-5.2-Codex
10.3s
132
Grok 4.1 Fast
10.3s
133
gpt-oss-120b (exacto)
10.3s
134
o1
10.4s
135
GPT-4 Turbo
10.5s
136
Trinity Mini
10.6s
137
Nova Premier 1.0
10.6s
138
Qwen Plus 0728
10.7s
139
Grok Code Fast 1
10.7s
140
Qwen-Plus
10.8s
141
SorcererLM 8x22B
10.9s
142
Kimi K2 0711
10.9s
143
Qwen-Max
10.9s
144
Mistral Large 2407
11.0s
145
Mistral Large 3 2512
11.1s
146
Pixtral Large 2411
11.2s
147
Trinity Large Preview
11.2s
148
Gemma 3 27B
11.3s
149
Llama 3 8B Instruct
11.4s
150
Mistral Large
11.5s
151
Qwen3 Coder 480B A35B
11.6s
152
Qwen3 Coder 30B A3B Instruct
11.7s
153
Gemma 3n 4B
11.7s
154
DeepSeek V3
11.7s
155
GPT-5.2
11.9s
156
Olmo 3.1 32B Instruct
12.0s
157
Gemma 3 4B
12.1s
158
Sonar Reasoning Pro
12.2s
159
Llama 3.1 Nemotron Ultra 253B v1
12.2s
160
Nemotron Nano 12B 2 VL
12.3s
161
GPT-4o Search Preview
12.4s
162
Phi 4
12.6s
163
GPT-4 Turbo Preview
12.6s
164
Qwen3 Coder Plus
12.7s
165
GPT-4 (older v0314)
12.7s
166
Claude Sonnet 4.5
12.8s
167
ReMM SLERP 13B
12.8s
168
Gemma 3 12B
12.9s
169
Qwen2.5 72B Instruct
13.0s
170
MythoMax 13B
13.0s
171
Command R+ (08-2024)
13.0s
172
Weaver (alpha)
13.2s
173
Cogito V2 Preview Llama 405B
13.3s
174
ERNIE 4.5 VL 28B A3B
13.3s
175
GPT-5 Mini
13.4s
176
Claude Opus 4.5
13.4s
177
GPT-5 Image Mini
13.5s
178
Llama 3 70B Instruct
13.7s
179
Noromaid 20B
13.9s
180
Qwen3 VL 32B Instruct
14.3s
181
Llama 3.1 Nemotron 70B Instruct
14.4s
182
Llama 3.3 70B Instruct
14.6s
183
R1 Distill Llama 70B
14.6s
184
Grok 3 Mini
14.6s
185
Grok 3 Beta
14.7s
186
Grok 3 Mini Beta
14.7s
187
Claude Opus 4.6
14.7s
188
Kimi K2 0905
14.7s
189
ERNIE 4.5 300B A47B
14.8s
190
Grok 3
14.9s
191
Qwen2.5 Coder 32B Instruct
15.0s
192
Granite 4.0 Micro
15.0s
193
Qwen3 VL 8B Instruct
15.2s
194
DeepSeek V3.1 Terminus (exacto)
15.2s
195
Gemini 2.5 Flash Image (Nano Banana)
15.2s
196
Olmo 3 7B Think
15.3s
197
Qwen2.5 VL 72B Instruct
15.3s
198
Qwen3 VL 30B A3B Instruct
15.4s
199
Jamba Large 1.7
15.5s
200
Switchpoint Router
15.6s
201
Qwen3 VL 235B A22B Instruct
15.7s
202
MiniMax M2
15.7s
203
Qwen3 30B A3B Instruct 2507
15.9s
204
GPT-5.1
16.0s
205
DeepSeek V3 0324
16.1s
206
MiMo-V2-Flash
16.1s
207
DeepSeek V3.1 Terminus
16.3s
208
Llama 3.3 Nemotron Super 49B V1.5
16.4s
209
Auto Router
16.4s
210
MiniMax M2.1
16.4s
211
Qwen3 Max
16.6s
212
Qwen3 30B A3B Thinking 2507
16.9s
213
Qwen3 Next 80B A3B Thinking
17.0s
214
GLM 4.5 Air
17.4s
215
ERNIE 4.5 VL 424B A47B
17.6s
216
Olmo 3 7B Instruct
17.6s
217
GPT-5 Image
17.8s
218
Tongyi DeepResearch 30B A3B
18.0s
219
GPT-5
18.0s
220
R1 0528
18.2s
221
GPT-5 Nano
18.5s
222
Qwen VL Max
18.5s
223
Qwen3 Coder Next
19.1s
224
Llama 3.3 Euryale 70B
19.1s
225
Qwen3 14B
19.8s
226
Free Models Router
20.2s
227
Qwen3 32B
20.6s
228
MiniMax M1
20.8s
229
Qwen3 235B A22B
21.4s
230
Qwen3 235B A22B Instruct 2507
21.5s
231
Llama 3.2 3B Instruct
21.9s
232
Nano Banana Pro (Gemini 3 Pro Image Preview)
22.6s
233
Llama 3.1 Euryale 70B v2.2
22.8s
234
Goliath 120B
23.1s
235
Mistral 7B Instruct v0.1
23.2s
236
Gemini 3 Pro Preview
23.5s
237
Nemotron 3 Nano 30B A3B
23.7s
238
Gemini 2.5 Pro Preview 05-06
24.2s
239
Gemini 2.5 Pro Preview 06-05
24.3s
240
Gemini 2.5 Pro
24.4s
241
Aion-1.0
24.8s
242
GLM 4.6
24.9s
243
DeepSeek V3.1 Nex N1
25.2s
244
Hermes 3 405B Instruct
26.2s
245
GLM 4.5
26.4s
246
Qwen Plus 0728 (thinking)
26.5s
247
Qwen3 VL 30B A3B Thinking
26.6s
248
Grok 4
27.6s
249
CodeLLaMa 7B Instruct Solidity
27.9s
250
Claude Opus 4
28.4s
251
Solar Pro 3
29.1s
252
Llama 3.1 8B Instruct
29.1s
253
Kimi K2 Thinking
29.5s
254
ERNIE 4.5 21B A3B Thinking
30.0s
255
DeepSeek V3.2
30.0s
256
MiMo-V2-Flash
30.0s
257
Claude Opus 4.1
30.0s
258
GLM 4.5V
30.1s
259
Claude 3.7 Sonnet (thinking)
30.3s
260
DeepSeek V3.2 Exp
30.6s
261
Llama 3.1 70B Hanami x1
31.2s
262
o1-pro
31.5s
263
GPT-5.2 Pro
31.8s
264
Qwen2.5 VL 32B Instruct
33.3s
265
Qwen3 VL 235B A22B Thinking
34.7s
266
o3 Pro
35.0s
267
R1 Distill Qwen 32B
36.4s
268
Seed 1.6
37.5s
269
Qwen3 VL 8B Thinking
38.2s
270
Qwen3 8B
39.2s
271
Kimi Dev 72B
40.0s
272
GLM 4.6V
40.4s
273
DeepSeek V3.1
40.8s
274
Sonar Deep Research
42.6s
275
Olmo 3.1 32B Think
42.7s
276
R1
43.7s
277
Olmo 3 32B Think
44.0s
278
Kimi K2.5
44.1s
279
GLM 4.6 (exacto)
44.5s
280
GLM 4.7
49.2s
281
Step3
50.5s
282
Llama 3.2 11B Vision Instruct
50.6s
283
DeepSeek V3.2 Speciale
57.4s
284
QwQ 32B
64.7s
285
Llemma 7b
72.4s
286
o4 Mini Deep Research
81.7s
287
Qwen3 235B A22B Thinking 2507
85.4s
288
GLM 4.7 Flash
103.8s
289
Hermes 3 70B Instruct
173.8s
290
o3 Deep Research
218.3s
Media:16.2s
(290 modelos)
Menú de métricas
Coste promedio por pregunta
Coste medio en USD por pregunta evaluada
1
LFM2-8B-A1B
$0.0000
2
Ministral 3B
$0.0000
3
Mistral Nemo
$0.0000
4
Gemma 3n 4B
$0.0000
5
Llama 3 8B Lunaris
$0.0000
6
Gemma 2 9B
$0.0000
7
Llama 3.2 3B Instruct
$0.0001
8
Llama 3 8B Instruct
$0.0001
9
Gemma 3 4B
$0.0001
10
Granite 4.0 Micro
$0.0001
11
MythoMax 13B
$0.0001
12
Command R7B (12-2024)
$0.0001
13
Ministral 8B
$0.0001
14
Qwen2.5 7B Instruct
$0.0001
15
GLM 4 32B
$0.0001
16
Mistral Small 3
$0.0001
17
Nova Micro 1.0
$0.0001
18
Llama 3.2 1B Instruct
$0.0001
19
Pixtral 12B
$0.0001
20
Llama 3.1 8B Instruct
$0.0001
21
Phi 4
$0.0001
22
Voxtral Small 24B 2507
$0.0001
23
Ministral 3 3B 2512
$0.0001
24
Hermes 2 Pro - Llama-3 8B
$0.0001
25
Nova Lite 1.0
$0.0001
26
Gemma 3 12B
$0.0001
27
Qwen-Turbo
$0.0001
28
GPT-4o-mini Search Preview
$0.0001
29
Mistral 7B Instruct v0.1
$0.0001
30
Mistral Small 3.2 24B
$0.0002
31
Gemini 2.0 Flash Lite
$0.0002
32
Gemma 3 27B
$0.0002
33
Mistral 7B Instruct v0.3
$0.0002
34
Rnj 1 Instruct
$0.0002
35
ERNIE 4.5 21B A3B
$0.0002
36
gpt-oss-120b (exacto)
$0.0002
37
Mistral 7B Instruct v0.2
$0.0002
38
Llama 3.2 11B Vision Instruct
$0.0002
39
Mistral 7B Instruct
$0.0002
40
Ministral 3 8B 2512
$0.0002
41
Qwen2.5-VL 7B Instruct
$0.0002
42
GPT-4.1 Nano
$0.0002
43
gpt-oss-20b
$0.0002
44
Gemini 2.0 Flash
$0.0002
45
Molmo2 8B
$0.0002
46
Lumimaid v0.2 8B
$0.0002
47
Olmo 3 7B Instruct
$0.0002
48
Hermes 4 70B
$0.0002
49
Mistral Tiny
$0.0002
50
Devstral Small 1.1
$0.0002
51
Nemotron Nano 9B V2
$0.0002
52
Qwen3 Coder 30B A3B Instruct
$0.0002
53
Ministral 3 14B 2512
$0.0003
54
Qwen2.5 Coder 32B Instruct
$0.0003
55
Llama 4 Scout
$0.0003
56
Qwen2.5 72B Instruct
$0.0003
57
gpt-oss-120b
$0.0003
58
Saba
$0.0003
59
Command R (08-2024)
$0.0003
60
gpt-oss-safeguard-20b
$0.0003
61
Jamba Mini 1.7
$0.0003
62
Qwen3 14B
$0.0003
63
Qwen3 30B A3B Instruct 2507
$0.0003
64
Mistral Small 3.1 24B
$0.0003
65
Trinity Mini
$0.0003
66
UnslopNemo 12B
$0.0003
67
Rocinante 12B
$0.0004
68
MiMo-V2-Flash
$0.0004
69
Qwen3 8B
$0.0004
70
Hunyuan A13B Instruct
$0.0004
71
DeepSeek V3.2 Exp
$0.0004
72
Gemini 2.5 Flash Lite
$0.0004
73
GPT-4o Search Preview
$0.0004
74
KAT-Coder-Pro V1
$0.0004
75
Seed 1.6 Flash
$0.0004
76
Cydonia 24B V4.1
$0.0004
77
Gemma 2 27B
$0.0004
78
DeepSeek V3.2
$0.0004
79
Llama 3.3 70B Instruct
$0.0004
80
GPT-4o-mini
$0.0004
81
GPT-4o-mini (2024-07-18)
$0.0004
82
Llama 3.1 70B Instruct
$0.0004
83
Gemini 2.5 Flash Lite Preview 09-2025
$0.0005
84
Mistral Small Creative
$0.0005
85
Qwen3 235B A22B Instruct 2507
$0.0005
86
Codestral 2508
$0.0005
87
Mercury Coder
$0.0005
88
Mercury
$0.0005
89
Llama 3 70B Instruct
$0.0005
90
Olmo 3.1 32B Instruct
$0.0005
91
Qwen3 32B
$0.0005
92
Llama 4 Maverick
$0.0006
93
ReMM SLERP 13B
$0.0006
94
DeepSeek V3 0324
$0.0006
95
Qwen2.5 VL 72B Instruct
$0.0006
96
Qwen VL Plus
$0.0006
97
Mixtral 8x7B Instruct
$0.0006
98
DeepSeek V3.1 Terminus (exacto)
$0.0006
99
Llama 3.3 Nemotron Super 49B V1.5
$0.0006
100
DeepSeek V3
$0.0006
101
Skyfall 36B V2
$0.0006
102
ERNIE 4.5 VL 28B A3B
$0.0006
103
ERNIE 4.5 300B A47B
$0.0006
104
Nemotron 3 Nano 30B A3B
$0.0007
105
Claude 3 Haiku
$0.0007
106
Grok 4 Fast
$0.0007
107
Olmo 3 7B Think
$0.0007
108
GPT-3.5 Turbo
$0.0007
109
Qwen3 30B A3B Thinking 2507
$0.0007
110
Qwen3 VL 30B A3B Instruct
$0.0007
111
Aion-1.0-Mini
$0.0007
112
DeepSeek V3.1
$0.0007
113
Tongyi DeepResearch 30B A3B
$0.0007
114
Grok 4.1 Fast
$0.0007
115
Qwen3 VL 8B Instruct
$0.0007
116
Qwen2.5 VL 32B Instruct
$0.0008
117
Cogito V2 Preview Llama 70B
$0.0008
118
DeepSeek V3.1 Terminus
$0.0008
119
Hermes 3 405B Instruct
$0.0008
120
GPT-5 Nano
$0.0008
121
Llama 3.3 Euryale 70B
$0.0008
122
ERNIE 4.5 21B A3B Thinking
$0.0008
123
Grok 3 Mini
$0.0009
124
QwQ 32B
$0.0009
125
Qwen3 VL 235B A22B Instruct
$0.0009
126
GPT-5.1-Codex-Mini
$0.0009
127
Grok 3 Mini Beta
$0.0009
128
GPT-4.1 Mini
$0.0009
129
Aion-RP 1.0 (8B)
$0.0009
130
GLM 4.5 Air
$0.0010
131
DeepSeek V3.1 Nex N1
$0.0010
132
Qwen3 Next 80B A3B Instruct
$0.0010
133
Llama 3.1 Euryale 70B v2.2
$0.0010
134
Devstral Medium
$0.0010
135
MiniMax M2-her
$0.0011
136
Mistral Medium 3
$0.0011
137
Weaver (alpha)
$0.0011
138
Mistral Large 3 2512
$0.0011
139
Qwen3 235B A22B
$0.0011
140
Cogito v2.1 671B
$0.0011
141
ERNIE 4.5 VL 424B A47B
$0.0011
142
Qwen3 Coder 480B A35B
$0.0012
143
Qwen Plus 0728
$0.0012
144
R1 Distill Qwen 32B
$0.0012
145
Qwen-Plus
$0.0012
146
Nemotron Nano 12B 2 VL
$0.0012
147
Llama 3.1 Nemotron Ultra 253B v1
$0.0012
148
Qwen3 Coder Next
$0.0012
149
Qwen3 Coder Flash
$0.0013
150
Qwen3 Coder 480B A35B (exacto)
$0.0013
151
R1 Distill Llama 70B
$0.0013
152
GLM 4.7 Flash
$0.0013
153
MiniMax M2.1
$0.0014
154
Morph V3 Large
$0.0014
155
Llama 3 Euryale 70B v2.1
$0.0014
156
Kimi Dev 72B
$0.0014
157
Llama 3.1 Nemotron 70B Instruct
$0.0014
158
GPT-3.5 Turbo (older v0613)
$0.0014
159
Hermes 4 405B
$0.0015
160
DeepSeek V3.2 Speciale
$0.0015
161
Noromaid 20B
$0.0015
162
Qwen3 VL 32B Instruct
$0.0015
163
GPT-3.5 Turbo Instruct
$0.0015
164
Kimi K2 0711
$0.0015
165
Nova Pro 1.0
$0.0015
166
Mistral Medium 3.1
$0.0016
167
MiniMax M2
$0.0016
168
CodeLLaMa 7B Instruct Solidity
$0.0016
169
GLM 4.5V
$0.0017
170
Gemini 3 Flash Preview
$0.0017
171
Olmo 3.1 32B Think
$0.0017
172
Olmo 3 32B Think
$0.0018
173
GLM 4.6V
$0.0018
174
Claude 3.5 Haiku
$0.0020
175
Qwen3 VL 30B A3B Thinking
$0.0020
176
GPT-5 Mini
$0.0021
177
GLM 4.6
$0.0021
178
Grok Code Fast 1
$0.0021
179
Gemini 2.5 Flash
$0.0023
180
Relace Search
$0.0025
181
MiniMax M1
$0.0025
182
Gemini 2.5 Flash Preview 09-2025
$0.0026
183
Nova 2 Lite
$0.0026
184
Kimi K2 0905
$0.0027
185
Qwen3 235B A22B Thinking 2507
$0.0027
186
Hermes 3 70B Instruct
$0.0027
187
Switchpoint Router
$0.0028
188
Seed 1.6
$0.0028
189
Qwen VL Max
$0.0028
190
GLM 4.6 (exacto)
$0.0029
191
GLM 4.5
$0.0029
192
Step3
$0.0029
193
Gemini 2.5 Flash Image (Nano Banana)
$0.0029
194
Cogito V2 Preview Llama 405B
$0.0029
195
Llama 3.1 70B Hanami x1
$0.0031
196
GPT-5.1-Codex
$0.0031
197
Mixtral 8x22B Instruct
$0.0032
198
GPT-5.1 Chat
$0.0033
199
Llemma 7b
$0.0034
200
Qwen3 Coder Plus
$0.0037
201
Qwen3 Next 80B A3B Thinking
$0.0037
202
Kimi K2 0905 (exacto)
$0.0038
203
R1
$0.0040
204
GPT-5 Image Mini
$0.0040
205
Palmyra X5
$0.0041
206
Claude Haiku 4.5
$0.0041
207
Mistral Large 2411
$0.0042
208
R1 0528
$0.0043
209
Mistral Large 2407
$0.0044
210
Mistral Large
$0.0044
211
GPT-5 Codex
$0.0045
212
Command A
$0.0045
213
Pixtral Large 2411
$0.0045
214
GPT-4.1
$0.0045
215
Qwen3 Max
$0.0046
216
Command R+ (08-2024)
$0.0047
217
Qwen-Max
$0.0048
218
GPT-4o
$0.0049
219
GPT-4o (2024-08-06)
$0.0049
220
Inflection 3 Productivity
$0.0050
221
Inflection 3 Pi
$0.0050
222
GPT-5 Chat
$0.0054
223
SorcererLM 8x22B
$0.0055
224
Nova Premier 1.0
$0.0055
225
Qwen3 VL 235B A22B Thinking
$0.0057
226
o3 Mini High
$0.0057
227
o3 Mini
$0.0058
228
GLM 4.7
$0.0059
229
Goliath 120B
$0.0060
230
Sonar
$0.0063
231
Qwen3 VL 8B Thinking
$0.0064
232
o4 Mini
$0.0065
233
Kimi K2.5
$0.0067
234
GPT-4o (2024-11-20)
$0.0071
235
GPT-5.2 Chat
$0.0080
236
Jamba Large 1.7
$0.0082
237
GPT-5.2-Codex
$0.0084
238
Qwen Plus 0728 (thinking)
$0.0085
239
Morph V3 Fast
$0.0091
240
GPT-4o (2024-05-13)
$0.0093
241
Kimi K2 Thinking
$0.0095
242
GPT-5.2
$0.0097
243
o3
$0.0097
244
GPT-5.1
$0.0097
245
o4 Mini High
$0.0098
246
Aion-1.0
$0.0101
247
GPT-5
$0.0102
248
GPT-5.1-Codex-Max
$0.0106
249
ChatGPT-4o
$0.0107
250
Claude Sonnet 4
$0.0110
251
Claude 3.7 Sonnet
$0.0123
252
Claude Sonnet 4.5
$0.0128
253
Grok 3
$0.0129
254
Grok 3 Beta
$0.0130
255
Sonar Pro
$0.0158
256
Auto Router
$0.0162
257
Claude 3.5 Sonnet
$0.0164
258
Sonar Reasoning Pro
$0.0173
259
GPT-5 Image
$0.0176
260
GPT-4 Turbo
$0.0204
261
Grok 4
$0.0214
262
GPT-4 Turbo Preview
$0.0215
263
Claude Opus 4.5
$0.0231
264
Claude Opus 4.6
$0.0244
265
Nano Banana Pro (Gemini 3 Pro Image Preview)
$0.0275
266
Sonar Pro Search
$0.0276
267
Gemini 3 Pro Preview
$0.0287
268
Gemini 2.5 Pro Preview 05-06
$0.0295
269
Gemini 2.5 Pro Preview 06-05
$0.0295
270
Gemini 2.5 Pro
$0.0296
271
Claude 3.7 Sonnet (thinking)
$0.0357
272
GPT-4 (older v0314)
$0.0380
273
GPT-4
$0.0408
274
Claude Opus 4
$0.0523
275
Claude Opus 4.1
$0.0555
276
o3 Pro
$0.1000
277
o1
$0.1109
278
GPT-5.2 Pro
$0.1185
279
o4 Mini Deep Research
$0.1745
280
o3 Deep Research
$0.8741
281
o1-pro
$1.1300
282
Sonar Deep Research
$1.1801
Media:$0.0100
(282 modelos)
Menú de métricas
Confianza promedio
Nivel de confianza medio reportado por el modelo
1
Gemini 3 Flash Preview
100.0%
2
o3
100.0%
3
GPT-5
100.0%
4
GPT-5.2 Pro
100.0%
5
Claude Opus 4.5
100.0%
6
Gemini 2.5 Pro Preview 06-05
100.0%
7
Gemini 2.5 Pro
100.0%
8
o3 Pro
100.0%
9
GPT-5.1
100.0%
10
o4 Mini
100.0%
11
GPT-5.2
100.0%
12
Seed 1.6
100.0%
13
Nano Banana Pro (Gemini 3 Pro Image Preview)
100.0%
14
GPT-5.1-Codex-Mini
100.0%
15
Gemini 2.5 Pro Preview 05-06
100.0%
16
o1-pro
100.0%
17
ChatGPT-4o
100.0%
18
o4 Mini Deep Research
100.0%
19
GPT-5.2-Codex
100.0%
20
GPT-5 Mini
100.0%
21
GPT-5 Chat
99.9%
22
o3 Deep Research
99.9%
23
Grok 4.1 Fast
99.9%
24
Mistral Medium 3.1
99.9%
25
Claude Sonnet 4.5
99.9%
26
gpt-oss-120b (exacto)
99.9%
27
GPT-4.1 Mini
99.9%
28
GPT-5.1 Chat
99.9%
29
o1
99.9%
30
GPT-5 Image
99.9%
31
GPT-5 Image Mini
99.9%
32
GPT-5.2 Chat
99.9%
33
Grok 4 Fast
99.9%
34
Sonar Pro
99.9%
35
Gemini 3 Pro Preview
99.9%
36
Claude 3.7 Sonnet (thinking)
99.9%
37
Claude Opus 4.6
99.9%
38
Claude Sonnet 4
99.9%
39
o3 Mini High
99.9%
40
ERNIE 4.5 VL 424B A47B
99.9%
41
Claude Opus 4.1
99.9%
42
GPT-4.1
99.8%
43
ERNIE 4.5 300B A47B
99.8%
44
QwQ 32B
99.8%
45
Seed 1.6 Flash
99.8%
46
KAT-Coder-Pro V1
99.8%
47
GPT-5.1-Codex-Max
99.8%
48
Qwen3 VL 235B A22B Thinking
99.8%
49
Qwen3 VL 235B A22B Instruct
99.8%
50
GPT-5.1-Codex
99.7%
51
GPT-4o (2024-05-13)
99.7%
52
Qwen3 Coder Flash
99.7%
53
GPT-5 Codex
99.7%
54
Nemotron 3 Nano 30B A3B
99.7%
55
gpt-oss-120b
99.7%
56
Qwen3 VL 8B Thinking
99.6%
57
Llama 4 Maverick
99.6%
58
DeepSeek V3 0324
99.6%
59
o4 Mini High
99.5%
60
Gemini 2.5 Flash Lite
99.5%
61
Mistral Large 3 2512
99.5%
62
DeepSeek V3.2
99.5%
63
o3 Mini
99.5%
64
ERNIE 4.5 21B A3B Thinking
99.5%
65
GPT-4o (2024-08-06)
99.5%
66
Qwen3 235B A22B Thinking 2507
99.5%
67
Qwen VL Max
99.4%
68
Qwen Plus 0728 (thinking)
99.4%
69
Aion-1.0
99.4%
70
Step3
99.4%
71
Claude 3.7 Sonnet
99.4%
72
Gemini 2.5 Flash Preview 09-2025
99.4%
73
Mistral Large 2407
99.4%
74
Gemma 3 12B
99.4%
75
Gemma 3 27B
99.4%
76
Qwen3 VL 30B A3B Thinking
99.4%
77
Qwen3 235B A22B
99.4%
78
Qwen3 Next 80B A3B Instruct
99.4%
79
Claude 3.5 Sonnet
99.3%
80
Qwen VL Plus
99.3%
81
DeepSeek V3.1 Terminus (exacto)
99.3%
82
Gemini 2.0 Flash
99.3%
83
Pixtral Large 2411
99.3%
84
Mistral Medium 3
99.3%
85
R1
99.3%
86
Qwen3 Next 80B A3B Thinking
99.2%
87
GPT-3.5 Turbo (older v0613)
99.2%
88
GPT-4o (2024-11-20)
99.2%
89
Qwen3 Coder Next
99.0%
90
Auto Router
99.0%
91
MiMo-V2-Flash
99.0%
92
GLM 4.5
99.0%
93
gpt-oss-safeguard-20b
99.0%
94
Llama 4 Scout
99.0%
95
Grok 4
99.0%
96
Gemini 2.5 Flash Image (Nano Banana)
99.0%
97
Qwen3 30B A3B Thinking 2507
99.0%
98
DeepSeek V3.1 Terminus
99.0%
99
DeepSeek V3.1
99.0%
100
Claude Opus 4
98.9%
101
Qwen3 235B A22B Instruct 2507
98.9%
102
Gemini 2.5 Flash
98.9%
103
Switchpoint Router
98.9%
104
Llama 3.1 Nemotron Ultra 253B v1
98.9%
105
R1 Distill Llama 70B
98.9%
106
Sonar Deep Research
98.9%
107
Mistral Large
98.9%
108
GLM 4.6
98.9%
109
Kimi K2 0711
98.9%
110
gpt-oss-20b
98.9%
111
Claude Haiku 4.5
98.8%
112
Relace Search
98.8%
113
Llama 3.3 Nemotron Super 49B V1.5
98.8%
114
Qwen3 32B
98.8%
115
Devstral 2 2512
98.7%
116
Gemini 2.5 Flash Lite Preview 09-2025
98.7%
117
Qwen3 Coder 480B A35B
98.7%
118
Mistral Small Creative
98.7%
119
Mistral Large 2411
98.7%
120
Grok 3 Mini Beta
98.6%
121
GPT-4o-mini
98.6%
122
Grok 3 Beta
98.6%
123
Ministral 3 14B 2512
98.6%
124
GLM 4.7
98.6%
125
R1 0528
98.6%
126
MiMo-V2-Flash
98.5%
127
GLM 4.7 Flash
98.5%
128
Qwen Plus 0728
98.5%
129
DeepSeek V3.2 Speciale
98.5%
130
Palmyra X5
98.5%
131
MiniMax M2
98.5%
132
GLM 4.5V
98.5%
133
GPT-4o
98.4%
134
Qwen3 Max
98.4%
135
Qwen3 VL 32B Instruct
98.3%
136
Solar Pro 3
98.3%
137
Qwen-Max
98.3%
138
Mercury
98.3%
139
Tongyi DeepResearch 30B A3B
98.2%
140
GPT-4o-mini Search Preview
98.2%
141
Qwen3 Coder 30B A3B Instruct
98.2%
142
Qwen3 Coder 480B A35B (exacto)
98.2%
143
Voxtral Small 24B 2507
98.1%
144
Devstral Medium
98.1%
145
GLM 4.6 (exacto)
98.1%
146
DeepSeek V3
98.1%
147
DeepSeek V3.1 Nex N1
98.1%
148
Nemotron Nano 12B 2 VL
98.0%
149
Grok 3 Mini
98.0%
150
Kimi K2.5
98.0%
151
Mixtral 8x22B Instruct
98.0%
152
Qwen-Plus
98.0%
153
Mercury Coder
98.0%
154
GPT-3.5 Turbo
98.0%
155
Step 3.5 Flash
97.9%
156
GPT-4o Search Preview
97.9%
157
GPT-4 Turbo
97.8%
158
Olmo 3 7B Think
97.8%
159
Nova Premier 1.0
97.8%
160
Sonar
97.8%
161
Sonar Pro Search
97.7%
162
Ministral 3 8B 2512
97.7%
163
Mistral Small 3.1 24B
97.7%
164
Grok 3
97.7%
165
GPT-4.1 Nano
97.7%
166
Llama 3 70B Instruct
97.6%
167
Qwen3 VL 30B A3B Instruct
97.6%
168
GPT-5 Nano
97.6%
169
Claude 3 Haiku
97.6%
170
Qwen3 30B A3B Instruct 2507
97.5%
171
Qwen2.5 VL 72B Instruct
97.5%
172
Claude 3.5 Haiku
97.5%
173
DeepSeek V3.2 Exp
97.5%
174
GLM 4 32B
97.5%
175
Qwen3 Coder Plus
97.5%
176
R1 Distill Qwen 32B
97.4%
177
Jamba Large 1.7
97.4%
178
Command R (08-2024)
97.4%
179
ERNIE 4.5 VL 28B A3B
97.3%
180
Qwen2.5 VL 32B Instruct
97.3%
181
Mistral Small 3.2 24B
97.3%
182
Qwen3 14B
97.2%
183
GLM 4.6V
97.1%
184
Gemini 2.0 Flash Lite
97.1%
185
Grok Code Fast 1
97.1%
186
LFM2-8B-A1B
97.0%
187
Trinity Large Preview
97.0%
188
Nova Lite 1.0
97.0%
189
Kimi K2 Thinking
97.0%
190
SorcererLM 8x22B
96.9%
191
GPT-3.5 Turbo 16k
96.9%
192
GPT-4 (older v0314)
96.9%
193
GPT-4o-mini (2024-07-18)
96.9%
194
Nova Pro 1.0
96.9%
195
Cogito V2 Preview Llama 405B
96.7%
196
Llama 3.1 Nemotron 70B Instruct
96.5%
197
Gemma 3 4B
96.5%
198
Qwen3 8B
96.5%
199
Jamba Mini 1.7
96.5%
200
Cydonia 24B V4.1
96.5%
201
GPT-4 Turbo Preview
96.5%
202
Granite 4.0 Micro
96.5%
203
GPT-3.5 Turbo Instruct
96.4%
204
GPT-4
96.4%
205
Command A
96.4%
206
Qwen2.5 72B Instruct
96.4%
207
Inflection 3 Productivity
96.3%
208
Hermes 4 405B
96.3%
209
Ministral 3 3B 2512
96.3%
210
Qwen3 VL 8B Instruct
96.3%
211
MiniMax M2.1
96.2%
212
Nova 2 Lite
96.1%
213
Aion-1.0-Mini
96.0%
214
Saba
96.0%
215
Hermes 3 405B Instruct
96.0%
216
Inflection 3 Pi
96.0%
217
GLM 4.5 Air
95.9%
218
Cogito v2.1 671B
95.8%
219
ERNIE 4.5 21B A3B
95.8%
220
Llama 3.1 70B Instruct
95.7%
221
Phi 4
95.7%
222
Lumimaid v0.2 8B
95.6%
223
Sonar Reasoning Pro
95.5%
224
GPT-4 Turbo (older v1106)
95.5%
225
Qwen-Turbo
95.5%
226
Llama 3 Euryale 70B v2.1
95.3%
227
Kimi Dev 72B
95.3%
228
Cogito V2 Preview Llama 70B
95.2%
229
Mistral Small 3
95.1%
230
Free Models Router
95.1%
231
Mistral 7B Instruct v0.2
95.0%
232
Command R7B (12-2024)
94.9%
233
Kimi K2 0905
94.7%
234
Kimi K2 0905 (exacto)
94.7%
235
Nova Micro 1.0
94.6%
236
Devstral Small 1.1
94.5%
237
MiniMax M1
94.5%
238
Olmo 3.1 32B Instruct
94.4%
239
Hermes 4 70B
94.0%
240
Llama 3.3 70B Instruct
93.8%
241
Molmo2 8B
93.7%
242
Mistral 7B Instruct v0.3
93.7%
243
Qwen2.5 Coder 32B Instruct
93.5%
244
Nemotron Nano 9B V2
93.4%
245
MiniMax M2-her
93.3%
246
Trinity Mini
93.3%
247
Ministral 8B
93.2%
248
Mistral Tiny
93.2%
249
Skyfall 36B V2
93.0%
250
Codestral 2508
92.9%
251
Gemma 3n 4B
92.9%
252
Mistral 7B Instruct
92.4%
253
Llama 3.3 Euryale 70B
91.9%
254
Gemma 2 27B
91.9%
255
Command R+ (08-2024)
91.8%
256
Llama 3.1 70B Hanami x1
91.7%
257
Mistral Nemo
91.1%
258
Qwen2.5 7B Instruct
90.3%
259
Mixtral 8x7B Instruct
89.4%
260
Llama 3 8B Lunaris
89.4%
261
Pixtral 12B
88.9%
262
Llama 3.1 Euryale 70B v2.2
88.9%
263
Olmo 3.1 32B Think
87.4%
264
Ministral 3B
86.7%
265
Hunyuan A13B Instruct
86.4%
266
Llama 3.2 3B Instruct
86.0%
267
Olmo 3 32B Think
86.0%
268
Llama 3 8B Instruct
85.5%
269
Olmo 3 7B Instruct
84.9%
270
Gemma 2 9B
84.0%
271
Goliath 120B
83.8%
272
Rnj 1 Instruct
83.7%
273
Hermes 2 Pro - Llama-3 8B
83.6%
274
Mistral 7B Instruct v0.1
82.7%
275
Noromaid 20B
79.4%
276
ReMM SLERP 13B
78.7%
277
Llama 3.1 8B Instruct
78.6%
278
Weaver (alpha)
76.2%
279
MythoMax 13B
76.2%
280
Qwen2.5-VL 7B Instruct
72.2%
281
UnslopNemo 12B
69.0%
282
Rocinante 12B
68.4%
283
Hermes 3 70B Instruct
63.2%
284
Aion-RP 1.0 (8B)
61.5%
285
Llama 3.2 11B Vision Instruct
53.8%
286
Llama 3.2 1B Instruct
50.7%
287
Morph V3 Fast
41.5%
288
Morph V3 Large
41.0%
289
Llemma 7b
19.4%
290
CodeLLaMa 7B Instruct Solidity
16.5%
Media:95.1%
(290 modelos)
Menú de métricas
Coste total
Coste total en USD para evaluar todas las preguntas
1
LFM2-8B-A1B
$0.00
2
Ministral 3B
$0.01
3
Mistral Nemo
$0.01
4
Gemma 3n 4B
$0.01
5
Llama 3 8B Lunaris
$0.01
6
Gemma 2 9B
$0.01
7
Llama 3.2 3B Instruct
$0.01
8
Llama 3 8B Instruct
$0.01
9
Gemma 3 4B
$0.01
10
Granite 4.0 Micro
$0.01
11
MythoMax 13B
$0.01
12
Command R7B (12-2024)
$0.01
13
Ministral 8B
$0.02
14
Qwen2.5 7B Instruct
$0.02
15
GLM 4 32B
$0.02
16
Mistral Small 3
$0.02
17
Nova Micro 1.0
$0.02
18
Llama 3.2 1B Instruct
$0.02
19
Pixtral 12B
$0.02
20
Llama 3.1 8B Instruct
$0.02
21
Phi 4
$0.02
22
Voxtral Small 24B 2507
$0.03
23
Ministral 3 3B 2512
$0.03
24
Hermes 2 Pro - Llama-3 8B
$0.03
25
Nova Lite 1.0
$0.03
26
Gemma 3 12B
$0.03
27
Qwen-Turbo
$0.03
28
GPT-4o-mini Search Preview
$0.03
29
Mistral 7B Instruct v0.1
$0.03
30
Mistral Small 3.2 24B
$0.03
31
Gemini 2.0 Flash Lite
$0.04
32
Gemma 3 27B
$0.04
33
Mistral 7B Instruct v0.3
$0.04
34
Rnj 1 Instruct
$0.04
35
ERNIE 4.5 21B A3B
$0.04
36
gpt-oss-120b (exacto)
$0.04
37
Mistral 7B Instruct v0.2
$0.04
38
Llama 3.2 11B Vision Instruct
$0.04
39
Mistral 7B Instruct
$0.04
40
Ministral 3 8B 2512
$0.04
41
Qwen2.5-VL 7B Instruct
$0.04
42
GPT-4.1 Nano
$0.04
43
gpt-oss-20b
$0.04
44
Gemini 2.0 Flash
$0.04
45
Molmo2 8B
$0.05
46
Lumimaid v0.2 8B
$0.05
47
Olmo 3 7B Instruct
$0.05
48
Hermes 4 70B
$0.05
49
Mistral Tiny
$0.05
50
Devstral Small 1.1
$0.05
51
Nemotron Nano 9B V2
$0.05
52
Qwen3 Coder 30B A3B Instruct
$0.05
53
Ministral 3 14B 2512
$0.05
54
Qwen2.5 Coder 32B Instruct
$0.05
55
Llama 4 Scout
$0.06
56
Qwen2.5 72B Instruct
$0.06
57
gpt-oss-120b
$0.06
58
Saba
$0.06
59
Command R (08-2024)
$0.06
60
gpt-oss-safeguard-20b
$0.06
61
Jamba Mini 1.7
$0.06
62
Qwen3 14B
$0.06
63
Qwen3 30B A3B Instruct 2507
$0.07
64
Mistral Small 3.1 24B
$0.07
65
Trinity Mini
$0.07
66
UnslopNemo 12B
$0.07
67
Rocinante 12B
$0.07
68
MiMo-V2-Flash
$0.08
69
Qwen3 8B
$0.08
70
Hunyuan A13B Instruct
$0.08
71
DeepSeek V3.2 Exp
$0.08
72
Gemini 2.5 Flash Lite
$0.08
73
GPT-4o Search Preview
$0.08
74
KAT-Coder-Pro V1
$0.08
75
Seed 1.6 Flash
$0.08
76
Cydonia 24B V4.1
$0.09
77
Gemma 2 27B
$0.09
78
DeepSeek V3.2
$0.09
79
Llama 3.3 70B Instruct
$0.09
80
GPT-4o-mini
$0.09
81
GPT-4o-mini (2024-07-18)
$0.09
82
Llama 3.1 70B Instruct
$0.09
83
Gemini 2.5 Flash Lite Preview 09-2025
$0.09
84
Mistral Small Creative
$0.10
85
Qwen3 235B A22B Instruct 2507
$0.10
86
Codestral 2508
$0.10
87
Mercury Coder
$0.10
88
Mercury
$0.10
89
Llama 3 70B Instruct
$0.10
90
Olmo 3.1 32B Instruct
$0.11
91
Qwen3 32B
$0.11
92
Llama 4 Maverick
$0.11
93
ReMM SLERP 13B
$0.11
94
DeepSeek V3 0324
$0.11
95
Qwen2.5 VL 72B Instruct
$0.11
96
Qwen VL Plus
$0.12
97
Mixtral 8x7B Instruct
$0.12
98
DeepSeek V3.1 Terminus (exacto)
$0.12
99
Llama 3.3 Nemotron Super 49B V1.5
$0.12
100
DeepSeek V3
$0.12
101
Skyfall 36B V2
$0.12
102
ERNIE 4.5 VL 28B A3B
$0.13
103
ERNIE 4.5 300B A47B
$0.13
104
Nemotron 3 Nano 30B A3B
$0.13
105
Claude 3 Haiku
$0.13
106
Grok 4 Fast
$0.13
107
Olmo 3 7B Think
$0.14
108
GPT-3.5 Turbo
$0.14
109
Qwen3 30B A3B Thinking 2507
$0.14
110
Qwen3 VL 30B A3B Instruct
$0.14
111
Aion-1.0-Mini
$0.14
112
DeepSeek V3.1
$0.14
113
Tongyi DeepResearch 30B A3B
$0.15
114
Grok 4.1 Fast
$0.15
115
Qwen3 VL 8B Instruct
$0.15
116
Qwen2.5 VL 32B Instruct
$0.15
117
Cogito V2 Preview Llama 70B
$0.16
118
DeepSeek V3.1 Terminus
$0.16
119
Hermes 3 405B Instruct
$0.16
120
GPT-5 Nano
$0.16
121
Llama 3.3 Euryale 70B
$0.16
122
ERNIE 4.5 21B A3B Thinking
$0.17
123
Grok 3 Mini
$0.18
124
QwQ 32B
$0.18
125
Qwen3 VL 235B A22B Instruct
$0.18
126
GPT-5.1-Codex-Mini
$0.18
127
Grok 3 Mini Beta
$0.19
128
GPT-4.1 Mini
$0.19
129
Aion-RP 1.0 (8B)
$0.19
130
GLM 4.5 Air
$0.19
131
DeepSeek V3.1 Nex N1
$0.20
132
Qwen3 Next 80B A3B Instruct
$0.20
133
Llama 3.1 Euryale 70B v2.2
$0.20
134
Devstral Medium
$0.20
135
MiniMax M2-her
$0.21
136
Mistral Medium 3
$0.21
137
Weaver (alpha)
$0.22
138
Mistral Large 3 2512
$0.22
139
Qwen3 235B A22B
$0.22
140
Cogito v2.1 671B
$0.23
141
ERNIE 4.5 VL 424B A47B
$0.23
142
Qwen3 Coder 480B A35B
$0.23
143
Qwen Plus 0728
$0.23
144
R1 Distill Qwen 32B
$0.23
145
Qwen-Plus
$0.24
146
Nemotron Nano 12B 2 VL
$0.24
147
Llama 3.1 Nemotron Ultra 253B v1
$0.24
148
Qwen3 Coder Next
$0.24
149
Qwen3 Coder Flash
$0.25
150
Qwen3 Coder 480B A35B (exacto)
$0.25
151
R1 Distill Llama 70B
$0.27
152
GLM 4.7 Flash
$0.27
153
MiniMax M2.1
$0.27
154
Morph V3 Large
$0.27
155
Llama 3 Euryale 70B v2.1
$0.28
156
Kimi Dev 72B
$0.29
157
Llama 3.1 Nemotron 70B Instruct
$0.29
158
GPT-3.5 Turbo (older v0613)
$0.29
159
Hermes 4 405B
$0.29
160
DeepSeek V3.2 Speciale
$0.30
161
Noromaid 20B
$0.30
162
Qwen3 VL 32B Instruct
$0.30
163
GPT-3.5 Turbo Instruct
$0.30
164
Kimi K2 0711
$0.30
165
Nova Pro 1.0
$0.30
166
Mistral Medium 3.1
$0.31
167
MiniMax M2
$0.32
168
CodeLLaMa 7B Instruct Solidity
$0.32
169
GLM 4.5V
$0.33
170
Gemini 3 Flash Preview
$0.34
171
Olmo 3.1 32B Think
$0.35
172
Olmo 3 32B Think
$0.36
173
GLM 4.6V
$0.36
174
Claude 3.5 Haiku
$0.39
175
Qwen3 VL 30B A3B Thinking
$0.40
176
GPT-5 Mini
$0.41
177
GLM 4.6
$0.42
178
Grok Code Fast 1
$0.42
179
Gemini 2.5 Flash
$0.46
180
Relace Search
$0.51
181
MiniMax M1
$0.51
182
Gemini 2.5 Flash Preview 09-2025
$0.51
183
Nova 2 Lite
$0.53
184
Kimi K2 0905
$0.54
185
Qwen3 235B A22B Thinking 2507
$0.54
186
Hermes 3 70B Instruct
$0.55
187
Switchpoint Router
$0.55
188
Seed 1.6
$0.56
189
Qwen VL Max
$0.57
190
GLM 4.6 (exacto)
$0.57
191
GLM 4.5
$0.58
192
Step3
$0.58
193
Gemini 2.5 Flash Image (Nano Banana)
$0.59
194
Cogito V2 Preview Llama 405B
$0.59
195
Llama 3.1 70B Hanami x1
$0.61
196
GPT-5.1-Codex
$0.62
197
Mixtral 8x22B Instruct
$0.63
198
GPT-5.1 Chat
$0.65
199
Llemma 7b
$0.68
200
Qwen3 Coder Plus
$0.74
201
Qwen3 Next 80B A3B Thinking
$0.74
202
Kimi K2 0905 (exacto)
$0.77
203
R1
$0.80
204
GPT-5 Image Mini
$0.80
205
Palmyra X5
$0.82
206
Claude Haiku 4.5
$0.82
207
Mistral Large 2411
$0.84
208
R1 0528
$0.87
209
Mistral Large 2407
$0.87
210
Mistral Large
$0.88
211
GPT-5 Codex
$0.89
212
Command A
$0.89
213
Pixtral Large 2411
$0.90
214
GPT-4.1
$0.90
215
Qwen3 Max
$0.92
216
Command R+ (08-2024)
$0.95
217
Qwen-Max
$0.96
218
GPT-4o
$0.98
219
GPT-4o (2024-08-06)
$0.98
220
Inflection 3 Productivity
$0.99
221
Inflection 3 Pi
$1.00
222
GPT-5 Chat
$1.08
223
SorcererLM 8x22B
$1.09
224
Nova Premier 1.0
$1.10
225
Qwen3 VL 235B A22B Thinking
$1.14
226
o3 Mini High
$1.15
227
o3 Mini
$1.16
228
GLM 4.7
$1.18
229
Goliath 120B
$1.20
230
Sonar
$1.26
231
Qwen3 VL 8B Thinking
$1.29
232
o4 Mini
$1.31
233
Kimi K2.5
$1.35
234
GPT-4o (2024-11-20)
$1.42
235
GPT-5.2 Chat
$1.61
236
Jamba Large 1.7
$1.63
237
GPT-5.2-Codex
$1.67
238
Qwen Plus 0728 (thinking)
$1.70
239
Morph V3 Fast
$1.81
240
GPT-4o (2024-05-13)
$1.87
241
Kimi K2 Thinking
$1.91
242
GPT-5.2
$1.93
243
o3
$1.94
244
GPT-5.1
$1.95
245
o4 Mini High
$1.95
246
Aion-1.0
$2.02
247
GPT-5
$2.05
248
GPT-5.1-Codex-Max
$2.11
249
ChatGPT-4o
$2.14
250
Claude Sonnet 4
$2.20
251
Claude 3.7 Sonnet
$2.46
252
Claude Sonnet 4.5
$2.56
253
Grok 3
$2.58
254
Grok 3 Beta
$2.60
255
Sonar Pro
$3.16
256
Auto Router
$3.25
257
Claude 3.5 Sonnet
$3.29
258
Sonar Reasoning Pro
$3.46
259
GPT-5 Image
$3.52
260
GPT-4 Turbo
$4.08
261
Grok 4
$4.28
262
GPT-4 Turbo Preview
$4.30
263
Claude Opus 4.5
$4.62
264
Claude Opus 4.6
$4.89
265
Nano Banana Pro (Gemini 3 Pro Image Preview)
$5.50
266
Sonar Pro Search
$5.51
267
Gemini 3 Pro Preview
$5.75
268
Gemini 2.5 Pro Preview 05-06
$5.90
269
Gemini 2.5 Pro Preview 06-05
$5.91
270
Gemini 2.5 Pro
$5.92
271
Claude 3.7 Sonnet (thinking)
$7.14
272
GPT-4 (older v0314)
$7.61
273
GPT-4
$8.16
274
Claude Opus 4
$10.46
275
Claude Opus 4.1
$11.10
276
o3 Pro
$19.99
277
o1
$22.18
278
GPT-5.2 Pro
$23.71
279
o4 Mini Deep Research
$34.89
280
o3 Deep Research
$174.81
281
o1-pro
$226.00
282
Sonar Deep Research
$236.01
Total:$966.81
Media:$3.42
(282 modelos)
Menú de métricas
Tokens de razonamiento
Tokens utilizados en el proceso de razonamiento
1
GLM 4.5 Air
2K
2
GPT-5.1 Chat
6K
3
GPT-5.1-Codex
18K
4
GPT-5.2 Chat
20K
5
DeepSeek V3.2
29K
6
DeepSeek V3.1 Terminus
30K
7
GPT-5.2
32K
8
GPT-5.2 Pro
33K
9
GPT-5.1-Codex-Mini
38K
10
Auto Router
39K
11
GPT-5 Codex
44K
12
DeepSeek V3.2 Exp
47K
13
GLM 4.5V
59K
14
GPT-5.2-Codex
69K
15
GPT-5.1
69K
16
o3
71K
17
gpt-oss-120b
71K
18
gpt-oss-120b (exacto)
73K
19
o3 Pro
73K
20
GLM 4.5
74K
21
Free Models Router
82K
22
GLM 4.6
91K
23
o3 Mini High
93K
24
o3 Mini
94K
25
o4 Mini
104K
26
Nemotron Nano 9B V2
109K
27
gpt-oss-safeguard-20b
109K
28
Grok 4 Fast
114K
29
gpt-oss-20b
117K
30
GPT-5 Mini
119K
31
GPT-5 Image Mini
122K
32
MiniMax M1
133K
33
GPT-5 Image
133K
34
GPT-5
135K
35
MiniMax M2.1
137K
36
GLM 4.6 (exacto)
144K
37
R1 Distill Llama 70B
145K
38
o1
146K
39
o1-pro
148K
40
Grok Code Fast 1
149K
41
Qwen3 32B
159K
42
Grok 4
160K
43
Grok 4.1 Fast
161K
44
GPT-5.1-Codex-Max
161K
45
R1 Distill Qwen 32B
165K
46
Kimi Dev 72B
167K
47
R1
170K
48
Seed 1.6
172K
49
Grok 3 Mini
172K
50
Seed 1.6 Flash
176K
51
Grok 3 Mini Beta
177K
52
o4 Mini High
178K
53
Qwen3 14B
178K
54
Qwen3 VL 235B A22B Thinking
180K
55
MiniMax M2
199K
56
Qwen3 8B
202K
57
R1 0528
206K
58
Llama 3.3 Nemotron Super 49B V1.5
210K
59
Step3
210K
60
Qwen3 235B A22B
212K
61
Tongyi DeepResearch 30B A3B
242K
62
Kimi K2 Thinking
247K
63
GLM 4.6V
251K
64
Qwen3 30B A3B Thinking 2507
264K
65
Qwen3 235B A22B Thinking 2507
266K
66
Qwen3 VL 30B A3B Thinking
271K
67
Kimi K2.5
279K
68
Nano Banana Pro (Gemini 3 Pro Image Preview)
280K
69
Claude 3.7 Sonnet (thinking)
282K
70
Qwen Plus 0728 (thinking)
289K
71
Solar Pro 3
295K
72
Nemotron Nano 12B 2 VL
296K
73
QwQ 32B
309K
74
Gemini 3 Pro Preview
319K
75
DeepSeek V3.2 Speciale
324K
76
GPT-5 Nano
324K
77
Step 3.5 Flash
387K
78
Gemini 2.5 Pro Preview 06-05
398K
79
Gemini 2.5 Pro Preview 05-06
401K
80
Gemini 2.5 Pro
401K
81
Trinity Mini
405K
82
GLM 4.7
414K
83
ERNIE 4.5 21B A3B Thinking
425K
84
Qwen3 Next 80B A3B Thinking
438K
85
Nemotron 3 Nano 30B A3B
485K
86
Qwen3 VL 8B Thinking
510K
87
Olmo 3 7B Think
515K
88
GLM 4.7 Flash
536K
89
Olmo 3.1 32B Think
594K
90
Olmo 3 32B Think
618K
91
o4 Mini Deep Research
1.5M
92
o3 Deep Research
1.7M
93
Sonar Deep Research
68.6M
Total:89.8M
Media:966K
(93 modelos)
Menú de métricas
Tokens salientes
Tokens generados en las respuestas
1
Gemma 2 27B
47K
2
GPT-5.1-Codex
50K
3
Aion-1.0-Mini
51K
4
Mistral Nemo
52K
5
GPT-5.1 Chat
54K
6
Voxtral Small 24B 2507
56K
7
Ministral 3B
58K
8
GPT-3.5 Turbo 16k
59K
9
GPT-3.5 Turbo
59K
10
Gemma 2 9B
59K
11
Lumimaid v0.2 8B
61K
12
Hermes 3 405B Instruct
64K
13
Hermes 4 405B
64K
14
Mistral Tiny
64K
15
Nova Premier 1.0
65K
16
Mistral 7B Instruct v0.3
65K
17
Mistral Small 3.1 24B
66K
18
Command A
67K
19
Mistral 7B Instruct v0.2
67K
20
Skyfall 36B V2
68K
21
Ministral 8B
68K
22
Mistral Small 3
69K
23
Mistral 7B Instruct
70K
24
Nova Pro 1.0
70K
25
Aion-RP 1.0 (8B)
70K
26
Cogito V2 Preview Llama 405B
72K
27
Command R7B (12-2024)
72K
28
Command R+ (08-2024)
72K
29
Llama 3 8B Lunaris
72K
30
MythoMax 13B
73K
31
Llama 3 70B Instruct
73K
32
GPT-4o-mini
74K
33
Mistral Small 3.2 24B
74K
34
GPT-4o-mini (2024-07-18)
74K
35
Saba
74K
36
GPT-4o
75K
37
Mixtral 8x22B Instruct
75K
38
GPT-4o (2024-08-06)
75K
39
Claude 3.5 Haiku
75K
40
Inflection 3 Productivity
76K
41
Mistral 7B Instruct v0.1
76K
42
Inflection 3 Pi
77K
43
ReMM SLERP 13B
77K
44
GPT-5 Codex
78K
45
GPT-4 (older v0314)
79K
46
GPT-4.1 Nano
80K
47
GPT-3.5 Turbo Instruct
81K
48
Cogito v2.1 671B
81K
49
Mercury Coder
81K
50
GPT-5.1-Codex-Mini
81K
51
Hermes 4 70B
81K
52
Devstral Medium
82K
53
Mercury
82K
54
Cogito V2 Preview Llama 70B
82K
55
UnslopNemo 12B
82K
56
DeepSeek V3 0324
82K
57
DeepSeek V3
82K
58
Command R (08-2024)
83K
59
Gemini 2.0 Flash
83K
60
Codestral 2508
83K
61
Mixtral 8x7B Instruct
84K
62
Claude 3 Haiku
84K
63
GLM 4 32B
84K
64
KAT-Coder-Pro V1
85K
65
Claude 3.5 Sonnet
87K
66
Nova Lite 1.0
87K
67
Pixtral 12B
87K
68
Mistral Medium 3
88K
69
Llama 3.2 1B Instruct
88K
70
GPT-4
88K
71
Gemma 3 12B
89K
72
GPT-4.1
89K
73
Llama 3 Euryale 70B v2.1
89K
74
Morph V3 Large
90K
75
ERNIE 4.5 300B A47B
91K
76
Kimi K2 0905
91K
77
GPT-4o Search Preview
92K
78
Devstral 2 2512
92K
79
Kimi K2 0905 (exacto)
92K
80
Gemini 2.0 Flash Lite
93K
81
GPT-4o (2024-05-13)
93K
82
Noromaid 20B
94K
83
Hermes 2 Pro - Llama-3 8B
94K
84
GPT-4 Turbo (older v1106)
94K
85
Gemini 3 Flash Preview
95K
86
GPT-4.1 Mini
95K
87
Gemma 3 4B
95K
88
Llama 3.1 70B Instruct
95K
89
Gemma 3 27B
95K
90
GPT-5 Chat
96K
91
Sonar Pro Search
97K
92
Cydonia 24B V4.1
97K
93
Qwen2.5-VL 7B Instruct
99K
94
GPT-4o-mini Search Preview
100K
95
Goliath 120B
100K
96
Mistral Large 2411
100K
97
Trinity Large Preview
100K
98
Qwen2.5 VL 72B Instruct
100K
99
Granite 4.0 Micro
101K
100
GPT-3.5 Turbo (older v0613)
101K
101
GPT-4 Turbo
102K
102
Llama 3.1 Nemotron Ultra 253B v1
103K
103
Llama 3.1 70B Hanami x1
103K
104
GPT-5.2 Chat
104K
105
Llama 4 Scout
105K
106
LFM2-8B-A1B
105K
107
Kimi K2 0711
105K
108
Llama 3.3 70B Instruct
106K
109
ERNIE 4.5 21B A3B
106K
110
Pixtral Large 2411
106K
111
Sonar Pro
107K
112
Jamba Mini 1.7
108K
113
GPT-5.2-Codex
109K
114
Llama 4 Maverick
109K
115
Sonar
109K
116
Nova Micro 1.0
110K
117
GPT-4 Turbo Preview
111K
118
ChatGPT-4o
112K
119
Qwen-Turbo
112K
120
Qwen2.5 7B Instruct
114K
121
SorcererLM 8x22B
114K
122
Hunyuan A13B Instruct
114K
123
Mistral Large 3 2512
115K
124
Qwen3 VL 235B A22B Instruct
115K
125
Mistral Large 2407
115K
126
Mistral Large
116K
127
Qwen2.5 72B Instruct
116K
128
Claude Opus 4
117K
129
Weaver (alpha)
117K
130
Gemma 3n 4B
118K
131
Molmo2 8B
118K
132
Llama 3.3 Euryale 70B
118K
133
GPT-4o (2024-11-20)
119K
134
Palmyra X5
122K
135
Rocinante 12B
122K
136
Claude Sonnet 4
124K
137
DeepSeek V3.1 Terminus (exacto)
124K
138
Qwen2.5 Coder 32B Instruct
125K
139
Claude Opus 4.1
125K
140
Qwen-Max
126K
141
Qwen3 Coder 480B A35B
127K
142
GPT-5.2
127K
143
Devstral Small 1.1
127K
144
Qwen3 Coder 480B A35B (exacto)
128K
145
Qwen3 Coder Plus
128K
146
DeepSeek V3.1
129K
147
Phi 4
129K
148
GPT-5.2 Pro
130K
149
Qwen3 Max
134K
150
DeepSeek V3.2
135K
151
DeepSeek V3.1 Nex N1
136K
152
Mistral Medium 3.1
136K
153
Llama 3.2 3B Instruct
137K
154
Relace Search
137K
155
ERNIE 4.5 VL 424B A47B
139K
156
Llama 3.1 Euryale 70B v2.2
141K
157
Claude 3.7 Sonnet
141K
158
Claude Haiku 4.5
141K
159
Qwen VL Plus
141K
160
Llama 3.1 Nemotron 70B Instruct
142K
161
Switchpoint Router
142K
162
Olmo 3.1 32B Instruct
142K
163
Qwen VL Max
145K
164
MiniMax M2-her
145K
165
DeepSeek V3.2 Exp
145K
166
o3 Mini High
146K
167
Qwen3 Coder 30B A3B Instruct
147K
168
Claude Sonnet 4.5
147K
169
Rnj 1 Instruct
147K
170
Qwen3 Coder Flash
148K
171
DeepSeek V3.1 Terminus
148K
172
o3 Mini
148K
173
o3
148K
174
Ministral 3 14B 2512
149K
175
Llama 3 8B Instruct
151K
176
Qwen3 Next 80B A3B Instruct
152K
177
Gemini 2.5 Flash Image (Nano Banana)
152K
178
gpt-oss-120b (exacto)
154K
179
gpt-oss-120b
154K
180
o3 Pro
154K
181
GLM 4.5V
155K
182
Free Models Router
157K
183
Qwen3 235B A22B Instruct 2507
160K
184
Qwen Plus 0728
161K
185
Ministral 3 8B 2512
162K
186
Claude Opus 4.5
162K
187
Grok 3 Beta
163K
188
Grok 3
163K
189
Qwen-Plus
164K
190
Ministral 3 3B 2512
166K
191
Qwen3 VL 32B Instruct
167K
192
Qwen3 30B A3B Instruct 2507
167K
193
o4 Mini
170K
194
Gemini 2.5 Flash
170K
195
Olmo 3 7B Instruct
172K
196
Claude Opus 4.6
173K
197
Gemini 2.5 Flash Lite
173K
198
R1 Distill Llama 70B
174K
199
Qwen3 VL 30B A3B Instruct
175K
200
Auto Router
177K
201
Jamba Large 1.7
179K
202
GLM 4.6
182K
203
GPT-5.1
183K
204
CodeLLaMa 7B Instruct Solidity
185K
205
MiMo-V2-Flash
188K
206
GPT-5 Image
190K
207
gpt-oss-safeguard-20b
193K
208
Gemini 2.5 Flash Preview 09-2025
193K
209
GPT-5
193K
210
GPT-5 Mini
196K
211
gpt-oss-20b
196K
212
GPT-5 Image Mini
199K
213
GPT-5.1-Codex-Max
200K
214
Nova 2 Lite
200K
215
ERNIE 4.5 VL 28B A3B
200K
216
R1 Distill Qwen 32B
201K
217
Gemini 2.5 Flash Lite Preview 09-2025
202K
218
o1
202K
219
Aion-1.0
205K
220
Qwen2.5 VL 32B Instruct
205K
221
o1-pro
207K
222
MiniMax M1
214K
223
MiniMax M2.1
215K
224
GLM 4.5 Air
217K
225
Kimi Dev 72B
222K
226
Nemotron Nano 9B V2
224K
227
Qwen3 VL 8B Instruct
225K
228
Grok 4 Fast
230K
229
MiMo-V2-Flash
232K
230
Qwen3 14B
238K
231
Qwen3 Coder Next
238K
232
Qwen3 32B
240K
233
o4 Mini High
244K
234
GLM 4.5
248K
235
GLM 4.6 (exacto)
249K
236
Sonar Reasoning Pro
250K
237
Seed 1.6 Flash
251K
238
Grok 4.1 Fast
257K
239
Llama 3.2 11B Vision Instruct
261K
240
Grok 4
264K
241
Seed 1.6
267K
242
Qwen3 VL 235B A22B Thinking
268K
243
MiniMax M2
270K
244
Grok Code Fast 1
275K
245
Llama 3.3 Nemotron Super 49B V1.5
275K
246
Qwen3 235B A22B
276K
247
Qwen3 8B
284K
248
R1
292K
249
Llama 3.1 8B Instruct
293K
250
Mistral Small Creative
307K
251
Tongyi DeepResearch 30B A3B
323K
252
R1 0528
329K
253
Grok 3 Mini
335K
254
Qwen3 30B A3B Thinking 2507
337K
255
Grok 3 Mini Beta
338K
256
Nemotron Nano 12B 2 VL
347K
257
Step3
369K
258
Kimi K2 Thinking
372K
259
GLM 4.6V
374K
260
QwQ 32B
377K
261
Qwen3 VL 30B A3B Thinking
377K
262
Qwen3 235B A22B Thinking 2507
382K
263
GPT-5 Nano
393K
264
DeepSeek V3.2 Speciale
403K
265
Qwen Plus 0728 (thinking)
415K
266
Trinity Mini
432K
267
Kimi K2.5
439K
268
Nano Banana Pro (Gemini 3 Pro Image Preview)
442K
269
Claude 3.7 Sonnet (thinking)
452K
270
Gemini 3 Pro Preview
463K
271
Solar Pro 3
465K
272
Llemma 7b
484K
273
Step 3.5 Flash
513K
274
Qwen3 Next 80B A3B Thinking
521K
275
Nemotron 3 Nano 30B A3B
528K
276
GLM 4.7
541K
277
ERNIE 4.5 21B A3B Thinking
572K
278
Gemini 2.5 Pro Preview 05-06
577K
279
Gemini 2.5 Pro Preview 06-05
578K
280
Gemini 2.5 Pro
579K
281
Qwen3 VL 8B Thinking
601K
282
Olmo 3 7B Think
612K
283
GLM 4.7 Flash
653K
284
Olmo 3.1 32B Think
659K
285
Olmo 3 32B Think
683K
286
Morph V3 Fast
1.4M
287
o4 Mini Deep Research
1.6M
288
Hermes 3 70B Instruct
1.7M
289
o3 Deep Research
1.9M
290
Sonar Deep Research
68.9M
Total:124.8M
Media:430K
(290 modelos)