Ranking de MIR 2024
20 de enero de 2024
210preguntas
5anuladas
Comparar con:
Ir a métrica:
Menú de métricas
Netas obtenidas
Puntuación MIR: (3 × aciertos - fallos) / 3
1
Sonar Deep Research
193.66 pts
2
Gemini 3 Flash Preview
193.33 pts
3
GPT-5 Mini
193.33 pts
4
Qwen3 235B A22B Thinking 2507
193.33 pts
5
GPT-5 Chat
193.33 pts
6
GPT-5.1
193.33 pts
7
Gemini 2.5 Pro
193.33 pts
8
Gemini 2.5 Pro Preview 05-06
193.33 pts
9
o3 Pro
193.33 pts
10
o3 Deep Research
193.33 pts
11
DeepSeek V3.2 Speciale
192.33 pts
12
GPT-5.1-Codex-Mini
192.00 pts
13
GPT-5.1 Chat
192.00 pts
14
R1 0528
192.00 pts
15
o4 Mini
192.00 pts
16
GPT-5.2-Codex
192.00 pts
17
Claude Sonnet 4.5
192.00 pts
18
Claude 3.5 Sonnet
192.00 pts
19
Gemini 2.5 Pro Preview 06-05
192.00 pts
20
Gemini 3 Pro Preview
192.00 pts
21
GPT-5.2 Pro
192.00 pts
22
o3
191.00 pts
23
GPT-5 Codex
190.66 pts
24
GPT-5.2 Chat
190.66 pts
25
GPT-5.2
190.66 pts
26
o4 Mini High
190.66 pts
27
Grok 3
190.66 pts
28
o1
190.66 pts
29
Gemini 2.5 Flash
190.33 pts
30
Gemini 2.5 Flash Preview 09-2025
189.66 pts
31
GPT-5 Image Mini
189.66 pts
32
Mistral Large 3 2512
189.33 pts
33
GPT-5.1-Codex
189.33 pts
34
GPT-4.1
189.33 pts
35
Aion-1.0
189.33 pts
36
GPT-5
189.33 pts
37
GPT-5.1-Codex-Max
189.33 pts
38
Auto Router
189.33 pts
39
Grok 4
189.33 pts
40
Claude Opus 4.5
189.33 pts
41
DeepSeek V3.2
188.33 pts
42
R1
188.33 pts
43
Claude 3.7 Sonnet (thinking)
188.33 pts
44
Gemini 2.0 Flash
188.00 pts
45
Switchpoint Router
188.00 pts
46
Mistral Large
188.00 pts
47
GPT-4o (2024-11-20)
188.00 pts
48
GPT-4o (2024-05-13)
188.00 pts
49
ChatGPT-4o
188.00 pts
50
Claude 3.7 Sonnet
188.00 pts
51
GPT-5 Image
188.00 pts
52
Nano Banana Pro (Gemini 3 Pro Image Preview)
188.00 pts
53
o1-pro
188.00 pts
54
DeepSeek V3 0324
187.66 pts
55
Kimi K2.5
187.33 pts
56
GPT-4o Search Preview
187.00 pts
57
Qwen3 235B A22B
187.00 pts
58
GLM 4.7
187.00 pts
59
Qwen3 VL 235B A22B Instruct
186.66 pts
60
Mistral Medium 3.1
186.66 pts
61
Qwen Plus 0728 (thinking)
186.66 pts
62
Claude Sonnet 4
186.66 pts
63
o4 Mini Deep Research
186.66 pts
Mejor humano
186.66 pts
64
GPT-5 Nano
186.00 pts
65
Llama 4 Maverick
185.66 pts
66
DeepSeek V3.1 Terminus
185.66 pts
67
GPT-3.5 Turbo (older v0613)
185.66 pts
68
GLM 4.5
185.33 pts
69
Qwen3 Max
185.33 pts
70
Qwen3 VL 235B A22B Thinking
185.33 pts
71
Grok 3 Beta
185.33 pts
72
Claude Opus 4
185.33 pts
73
Claude Opus 4.1
185.33 pts
74
DeepSeek V3.2 Exp
185.00 pts
75
Qwen-Plus
185.00 pts
76
GPT-4o (2024-08-06)
185.00 pts
77
Gemini 2.5 Flash Image (Nano Banana)
184.66 pts
78
Claude Opus 4.6
184.66 pts
79
DeepSeek V3
184.33 pts
80
GPT-4.1 Mini
184.33 pts
81
Qwen Plus 0728
184.33 pts
82
Mistral Large 2407
184.00 pts
83
DeepSeek V3.1 Terminus (exacto)
183.33 pts
84
Seed 1.6
183.00 pts
85
GLM 4.6 (exacto)
183.00 pts
86
Mistral Medium 3
182.66 pts
87
Kimi K2 Thinking
182.66 pts
88
Grok 3 Mini Beta
182.33 pts
89
GLM 4.6
182.33 pts
90
DeepSeek V3.1
182.00 pts
91
Grok 3 Mini
182.00 pts
92
Qwen3 Next 80B A3B Thinking
182.00 pts
93
o3 Mini High
182.00 pts
94
GPT-4o
181.66 pts
95
o3 Mini
181.33 pts
96
Qwen3 VL 32B Instruct
180.33 pts
97
gpt-oss-120b
180.00 pts
98
Grok 4 Fast
180.00 pts
99
Qwen3 VL 30B A3B Thinking
180.00 pts
100
GPT-4 Turbo
180.00 pts
101
Sonar Pro Search
179.66 pts
102
Devstral 2 2512
179.33 pts
103
Qwen3 Coder 480B A35B (exacto)
179.33 pts
104
Palmyra X5
179.33 pts
105
gpt-oss-120b (exacto)
179.00 pts
106
Cogito v2.1 671B
179.00 pts
107
Step 3.5 Flash
178.66 pts
108
Grok 4.1 Fast
178.66 pts
109
Claude Haiku 4.5
178.66 pts
110
Llama 3.3 Nemotron Super 49B V1.5
178.33 pts
111
Nova Pro 1.0
178.33 pts
112
Qwen3 Coder Plus
178.33 pts
113
Gemini 2.5 Flash Lite Preview 09-2025
178.00 pts
114
Qwen3 235B A22B Instruct 2507
178.00 pts
115
Kimi K2 0711
177.66 pts
116
Qwen3 Coder Next
177.33 pts
117
MiniMax M2
176.66 pts
118
Devstral Medium
176.33 pts
119
DeepSeek V3.1 Nex N1
176.33 pts
120
Qwen3 Next 80B A3B Instruct
176.33 pts
121
Qwen3 Coder 480B A35B
176.33 pts
122
gpt-oss-20b
176.00 pts
123
Gemini 2.5 Flash Lite
176.00 pts
124
GPT-4 Turbo Preview
175.33 pts
125
KAT-Coder-Pro V1
175.00 pts
126
GPT-4 Turbo (older v1106)
174.00 pts
127
Qwen2.5 VL 72B Instruct
174.00 pts
128
ERNIE 4.5 VL 424B A47B
173.66 pts
129
Tongyi DeepResearch 30B A3B
173.33 pts
130
Mistral Large 2411
173.33 pts
131
Grok Code Fast 1
173.00 pts
132
Sonar Pro
173.00 pts
133
GPT-4
173.00 pts
134
Pixtral Large 2411
172.66 pts
135
Llama 4 Scout
172.33 pts
136
ERNIE 4.5 300B A47B
172.00 pts
137
Kimi K2 0905
172.00 pts
138
GLM 4.6V
171.33 pts
139
Kimi K2 0905 (exacto)
171.33 pts
140
Trinity Large Preview
171.00 pts
141
Gemini 2.0 Flash Lite
170.66 pts
142
Mistral Small Creative
170.66 pts
143
Aion-1.0-Mini
170.33 pts
144
Nova Premier 1.0
170.33 pts
145
Sonar Reasoning Pro
170.00 pts
146
gpt-oss-safeguard-20b
169.66 pts
147
Mistral Small 3.2 24B
169.33 pts
148
GPT-4 (older v0314)
169.00 pts
149
Llama 3.1 Nemotron Ultra 253B v1
168.66 pts
150
Jamba Large 1.7
168.66 pts
151
Qwen3 32B
168.33 pts
152
Qwen3 30B A3B Thinking 2507
168.33 pts
153
Qwen3 VL 30B A3B Instruct
168.33 pts
154
Qwen VL Max
168.33 pts
155
Hermes 3 405B Instruct
168.00 pts
156
Sonar
168.00 pts
157
Qwen3 30B A3B Instruct 2507
167.33 pts
158
GLM 4.5V
167.33 pts
159
Qwen2.5 72B Instruct
167.00 pts
160
R1 Distill Llama 70B
167.00 pts
161
Mixtral 8x22B Instruct
167.00 pts
162
Cogito V2 Preview Llama 405B
166.00 pts
163
QwQ 32B
165.33 pts
164
Kimi Dev 72B
165.33 pts
165
Mercury Coder
164.66 pts
166
Seed 1.6 Flash
164.00 pts
167
Nemotron 3 Nano 30B A3B
164.00 pts
168
Qwen3 14B
163.66 pts
169
MiniMax M2.1
163.66 pts
170
Saba
163.33 pts
171
MiMo-V2-Flash
163.33 pts
172
Hermes 4 405B
162.66 pts
173
Step3
162.66 pts
174
Llama 3.3 70B Instruct
162.00 pts
175
Mercury
162.00 pts
176
Llama 3.1 70B Instruct
160.66 pts
177
MiniMax M1
160.66 pts
178
MiniMax M2-her
160.33 pts
179
Cydonia 24B V4.1
159.33 pts
180
Command A
159.00 pts
181
GPT-4o-mini (2024-07-18)
158.33 pts
182
Qwen3 VL 8B Thinking
158.00 pts
183
GPT-4o-mini Search Preview
157.33 pts
184
GPT-4o-mini
157.33 pts
185
Llama 3.3 Euryale 70B
156.33 pts
186
Cogito V2 Preview Llama 70B
155.66 pts
187
Llama 3.1 Nemotron 70B Instruct
155.00 pts
188
Ministral 3 14B 2512
154.66 pts
189
Nemotron Nano 12B 2 VL
154.66 pts
190
Qwen-Max
154.66 pts
191
GLM 4 32B
154.33 pts
192
Mistral Small 3.1 24B
154.33 pts
193
Nova 2 Lite
154.33 pts
194
Devstral Small 1.1
154.00 pts
195
GPT-4.1 Nano
153.33 pts
196
Voxtral Small 24B 2507
153.00 pts
197
Inflection 3 Pi
153.00 pts
198
MiMo-V2-Flash
152.66 pts
199
GLM 4.5 Air
152.66 pts
200
Qwen-Turbo
152.33 pts
201
Qwen3 Coder 30B A3B Instruct
149.66 pts
202
Mistral Small 3
149.33 pts
203
Gemma 3 27B
148.00 pts
204
Claude 3.5 Haiku
147.66 pts
205
Qwen3 8B
147.33 pts
206
Qwen3 Coder Flash
147.33 pts
207
Hermes 4 70B
146.66 pts
208
Qwen VL Plus
146.66 pts
209
Inflection 3 Productivity
146.33 pts
210
R1 Distill Qwen 32B
146.00 pts
211
GLM 4.7 Flash
146.00 pts
212
Ministral 3 8B 2512
144.33 pts
213
Qwen2.5 VL 32B Instruct
144.00 pts
214
Llama 3 70B Instruct
143.66 pts
215
Llama 3.1 70B Hanami x1
143.66 pts
216
Qwen3 VL 8B Instruct
141.66 pts
217
Olmo 3 32B Think
140.00 pts
218
Olmo 3.1 32B Think
140.00 pts
219
Relace Search
140.00 pts
220
Nemotron Nano 9B V2
139.66 pts
221
Claude 3 Haiku
138.00 pts
222
Nova Micro 1.0
136.66 pts
223
Free Models Router
136.33 pts
224
Skyfall 36B V2
136.33 pts
225
Llama 3 Euryale 70B v2.1
135.33 pts
226
Solar Pro 3
133.00 pts
227
Trinity Mini
130.33 pts
228
Nova Lite 1.0
127.66 pts
229
SorcererLM 8x22B
126.66 pts
230
ERNIE 4.5 21B A3B
125.66 pts
231
ERNIE 4.5 VL 28B A3B
125.33 pts
232
Llama 3.1 Euryale 70B v2.2
125.00 pts
233
Gemma 3 12B
121.66 pts
234
Unknown
119.66 pts
235
Ministral 3 3B 2512
118.66 pts
236
Command R+ (08-2024)
118.33 pts
237
Gemma 2 27B
115.66 pts
238
Mixtral 8x7B Instruct
111.66 pts
239
ERNIE 4.5 21B A3B Thinking
107.66 pts
240
GPT-3.5 Turbo
105.66 pts
241
Gemma 2 9B
105.33 pts
242
Molmo2 8B
104.33 pts
243
Command R (08-2024)
104.00 pts
244
Phi 4
100.66 pts
245
Gemma 3n 4B
99.66 pts
246
Pixtral 12B
98.66 pts
247
Hunyuan A13B Instruct
94.66 pts
248
Mistral Nemo
93.33 pts
249
Qwen2.5 Coder 32B Instruct
92.33 pts
250
Ministral 8B
91.33 pts
251
Olmo 3.1 32B Instruct
90.66 pts
252
GPT-3.5 Turbo 16k
88.33 pts
253
Jamba Mini 1.7
87.33 pts
254
Olmo 3 7B Think
84.00 pts
255
Codestral 2508
79.33 pts
256
LFM2-8B-A1B
74.33 pts
257
Qwen2.5 7B Instruct
73.00 pts
258
GPT-3.5 Turbo Instruct
71.00 pts
259
Command R7B (12-2024)
66.66 pts
260
Llama 3 8B Instruct
65.33 pts
261
Rocinante 12B
64.33 pts
262
Gemma 3 4B
62.00 pts
263
Mistral 7B Instruct
61.33 pts
264
Qwen2.5-VL 7B Instruct
60.66 pts
265
Hermes 3 70B Instruct
59.33 pts
266
Goliath 120B
58.66 pts
267
Ministral 3B
55.00 pts
268
Mistral 7B Instruct v0.2
54.33 pts
269
Llama 3 8B Lunaris
53.33 pts
270
Mistral 7B Instruct v0.3
52.66 pts
271
Mistral Tiny
52.66 pts
272
UnslopNemo 12B
52.33 pts
273
Mistral 7B Instruct v0.1
45.00 pts
274
Llama 3.2 11B Vision Instruct
44.66 pts
275
Llama 3.1 8B Instruct
44.00 pts
276
Lumimaid v0.2 8B
40.00 pts
277
Granite 4.0 Micro
39.00 pts
278
Llama 3.2 3B Instruct
38.66 pts
279
Rnj 1 Instruct
38.66 pts
280
Noromaid 20B
38.00 pts
281
Hermes 2 Pro - Llama-3 8B
37.00 pts
282
Aion-RP 1.0 (8B)
33.00 pts
283
Morph V3 Large
29.66 pts
284
ReMM SLERP 13B
26.66 pts
285
Olmo 3 7B Instruct
25.66 pts
286
Weaver (alpha)
23.66 pts
287
MythoMax 13B
17.00 pts
288
Morph V3 Fast
9.33 pts
289
Llama 3.2 1B Instruct
7.33 pts
290
CodeLLaMa 7B Instruct Solidity
2.33 pts
291
Llemma 7b
0.00 pts
Media:150.86 pts
(291 modelos)
Menú de métricas
Aciertos obtenidos
Número total de respuestas correctas
1
Sonar Deep Research
195
2
Gemini 3 Flash Preview
195
3
GPT-5 Mini
195
4
Qwen3 235B A22B Thinking 2507
195
5
GPT-5 Chat
195
6
GPT-5.1
195
7
Gemini 2.5 Pro
195
8
Gemini 2.5 Pro Preview 05-06
195
9
o3 Pro
195
10
o3 Deep Research
195
11
DeepSeek V3.2 Speciale
194
12
GPT-5.1-Codex-Mini
194
13
GPT-5.1 Chat
194
14
R1 0528
194
15
o4 Mini
194
16
GPT-5.2-Codex
194
17
Claude Sonnet 4.5
194
18
Claude 3.5 Sonnet
194
19
Gemini 2.5 Pro Preview 06-05
194
20
Gemini 3 Pro Preview
194
21
GPT-5.2 Pro
194
22
o3
193
23
GPT-5 Codex
193
24
GPT-5.2 Chat
193
25
GPT-5.2
193
26
o4 Mini High
193
27
Grok 3
193
28
o1
193
29
Gemini 2.5 Flash
192
30
Gemini 2.5 Flash Preview 09-2025
192
31
GPT-5 Image Mini
192
32
Mistral Large 3 2512
192
33
GPT-5.1-Codex
192
34
GPT-4.1
192
35
Aion-1.0
192
36
GPT-5
192
37
GPT-5.1-Codex-Max
192
38
Auto Router
192
39
Grok 4
192
40
Claude Opus 4.5
192
41
DeepSeek V3.2
191
42
R1
191
43
Claude 3.7 Sonnet (thinking)
191
44
Gemini 2.0 Flash
191
45
Switchpoint Router
191
46
Mistral Large
191
47
GPT-4o (2024-11-20)
191
48
GPT-4o (2024-05-13)
191
49
ChatGPT-4o
191
50
Claude 3.7 Sonnet
191
51
GPT-5 Image
191
52
Nano Banana Pro (Gemini 3 Pro Image Preview)
191
53
o1-pro
191
54
DeepSeek V3 0324
190
55
Kimi K2.5
190
56
GPT-4o Search Preview
190
57
Qwen3 235B A22B
190
58
GLM 4.7
190
59
Qwen3 VL 235B A22B Instruct
190
60
Mistral Medium 3.1
190
61
Qwen Plus 0728 (thinking)
190
62
Claude Sonnet 4
190
63
o4 Mini Deep Research
190
Mejor humano
190
64
GPT-5 Nano
189
65
Llama 4 Maverick
189
66
DeepSeek V3.1 Terminus
189
67
GPT-3.5 Turbo (older v0613)
189
68
GLM 4.5
189
69
Qwen3 VL 235B A22B Thinking
189
70
Grok 3 Beta
189
71
Claude Opus 4
189
72
Claude Opus 4.1
189
73
Qwen3 Max
188
74
DeepSeek V3.2 Exp
188
75
Qwen-Plus
188
76
Claude Opus 4.6
188
77
DeepSeek V3
188
78
GPT-4.1 Mini
188
79
Qwen Plus 0728
188
80
Mistral Large 2407
188
81
GPT-4o (2024-08-06)
187
82
Gemini 2.5 Flash Image (Nano Banana)
187
83
DeepSeek V3.1 Terminus (exacto)
187
84
Seed 1.6
187
85
GLM 4.6 (exacto)
187
86
Mistral Medium 3
187
87
Kimi K2 Thinking
186
88
Grok 3 Mini Beta
186
89
GLM 4.6
186
90
Grok 3 Mini
186
91
Qwen3 Next 80B A3B Thinking
186
92
o3 Mini High
186
93
o3 Mini
186
94
DeepSeek V3.1
185
95
Qwen3 VL 32B Instruct
185
96
gpt-oss-120b
185
97
Grok 4 Fast
185
98
Qwen3 VL 30B A3B Thinking
185
99
GPT-4 Turbo
185
100
GPT-4o
184
101
Sonar Pro Search
184
102
Devstral 2 2512
184
103
Qwen3 Coder 480B A35B (exacto)
184
104
Palmyra X5
184
105
gpt-oss-120b (exacto)
184
106
Grok 4.1 Fast
184
107
Claude Haiku 4.5
184
108
Step 3.5 Flash
183
109
Llama 3.3 Nemotron Super 49B V1.5
183
110
Nova Pro 1.0
183
111
Qwen3 Coder Plus
183
112
Gemini 2.5 Flash Lite Preview 09-2025
183
113
Qwen3 235B A22B Instruct 2507
183
114
Cogito v2.1 671B
182
115
Kimi K2 0711
182
116
Qwen3 Coder Next
182
117
Devstral Medium
182
118
Qwen3 Next 80B A3B Instruct
182
119
Qwen3 Coder 480B A35B
182
120
gpt-oss-20b
182
121
Gemini 2.5 Flash Lite
182
122
MiniMax M2
181
123
DeepSeek V3.1 Nex N1
181
124
GPT-4 Turbo Preview
181
125
KAT-Coder-Pro V1
180
126
Qwen2.5 VL 72B Instruct
180
127
ERNIE 4.5 VL 424B A47B
180
128
Tongyi DeepResearch 30B A3B
180
129
Mistral Large 2411
180
130
Sonar Pro
179
131
Pixtral Large 2411
179
132
Llama 4 Scout
179
133
ERNIE 4.5 300B A47B
179
134
GPT-4 Turbo (older v1106)
178
135
Grok Code Fast 1
178
136
GPT-4
178
137
GLM 4.6V
178
138
Mistral Small Creative
178
139
Trinity Large Preview
177
140
Gemini 2.0 Flash Lite
177
141
Nova Premier 1.0
177
142
gpt-oss-safeguard-20b
177
143
Mistral Small 3.2 24B
177
144
Aion-1.0-Mini
176
145
Llama 3.1 Nemotron Ultra 253B v1
176
146
Jamba Large 1.7
176
147
Qwen3 32B
176
148
Qwen3 30B A3B Thinking 2507
176
149
Qwen3 VL 30B A3B Instruct
176
150
Kimi K2 0905
175
151
GPT-4 (older v0314)
175
152
Qwen VL Max
175
153
Hermes 3 405B Instruct
175
154
Sonar
175
155
Qwen3 30B A3B Instruct 2507
175
156
GLM 4.5V
175
157
Qwen2.5 72B Instruct
175
158
R1 Distill Llama 70B
175
159
Mixtral 8x22B Instruct
175
160
Kimi K2 0905 (exacto)
174
161
Sonar Reasoning Pro
174
162
QwQ 32B
174
163
Cogito V2 Preview Llama 405B
173
164
Mercury Coder
173
165
Nemotron 3 Nano 30B A3B
173
166
Kimi Dev 72B
172
167
Seed 1.6 Flash
172
168
Qwen3 14B
172
169
Saba
172
170
MiMo-V2-Flash
172
171
Step3
172
172
Llama 3.3 70B Instruct
171
173
Mercury
171
174
MiniMax M2.1
170
175
Llama 3.1 70B Instruct
170
176
Hermes 4 405B
169
177
MiniMax M1
169
178
Command A
169
179
MiniMax M2-her
168
180
Cydonia 24B V4.1
168
181
GPT-4o-mini (2024-07-18)
168
182
Qwen3 VL 8B Thinking
168
183
GPT-4o-mini Search Preview
167
184
GPT-4o-mini
167
185
Ministral 3 14B 2512
166
186
Qwen-Max
166
187
Llama 3.3 Euryale 70B
165
188
Cogito V2 Preview Llama 70B
165
189
Llama 3.1 Nemotron 70B Instruct
165
190
Nemotron Nano 12B 2 VL
165
191
Mistral Small 3.1 24B
165
192
Nova 2 Lite
165
193
Devstral Small 1.1
165
194
GPT-4.1 Nano
165
195
Voxtral Small 24B 2507
164
196
Inflection 3 Pi
164
197
MiMo-V2-Flash
164
198
GLM 4 32B
163
199
Qwen-Turbo
163
200
GLM 4.5 Air
162
201
Qwen3 Coder 30B A3B Instruct
162
202
Mistral Small 3
161
203
Gemma 3 27B
161
204
Claude 3.5 Haiku
160
205
Qwen3 8B
160
206
Qwen3 Coder Flash
160
207
Hermes 4 70B
159
208
Qwen VL Plus
159
209
Inflection 3 Productivity
159
210
R1 Distill Qwen 32B
159
211
GLM 4.7 Flash
158
212
Ministral 3 8B 2512
158
213
Qwen2.5 VL 32B Instruct
157
214
Llama 3 70B Instruct
157
215
Llama 3.1 70B Hanami x1
155
216
Qwen3 VL 8B Instruct
155
217
Relace Search
155
218
Olmo 3 32B Think
152
219
Claude 3 Haiku
152
220
Nemotron Nano 9B V2
151
221
Olmo 3.1 32B Think
150
222
Free Models Router
150
223
Skyfall 36B V2
150
224
Nova Micro 1.0
149
225
Llama 3 Euryale 70B v2.1
149
226
Trinity Mini
145
227
Nova Lite 1.0
145
228
ERNIE 4.5 21B A3B
143
229
ERNIE 4.5 VL 28B A3B
143
230
SorcererLM 8x22B
141
231
Gemma 3 12B
141
232
Llama 3.1 Euryale 70B v2.2
140
233
Solar Pro 3
139
234
Ministral 3 3B 2512
138
235
Command R+ (08-2024)
138
236
Gemma 2 27B
133
237
Mixtral 8x7B Instruct
131
238
ERNIE 4.5 21B A3B Thinking
130
239
GPT-3.5 Turbo
129
240
Command R (08-2024)
127
241
Unknown
125
242
Molmo2 8B
125
243
Phi 4
125
244
Gemma 3n 4B
123
245
Gemma 2 9B
122
246
Pixtral 12B
122
247
Mistral Nemo
118
248
Ministral 8B
116
249
Olmo 3.1 32B Instruct
116
250
GPT-3.5 Turbo 16k
116
251
Jamba Mini 1.7
114
252
Qwen2.5 Coder 32B Instruct
113
253
Olmo 3 7B Think
112
254
Hunyuan A13B Instruct
111
255
Codestral 2508
107
256
LFM2-8B-A1B
104
257
GPT-3.5 Turbo Instruct
102
258
Qwen2.5 7B Instruct
100
259
Command R7B (12-2024)
98
260
Gemma 3 4B
96
261
Llama 3 8B Instruct
93
262
Mistral 7B Instruct
93
263
Goliath 120B
91
264
Qwen2.5-VL 7B Instruct
90
265
Llama 3 8B Lunaris
88
266
Mistral 7B Instruct v0.2
87
267
Mistral 7B Instruct v0.3
87
268
Rocinante 12B
86
269
Mistral Tiny
86
270
Ministral 3B
83
271
Hermes 3 70B Instruct
78
272
Granite 4.0 Micro
78
273
Lumimaid v0.2 8B
77
274
Mistral 7B Instruct v0.1
75
275
UnslopNemo 12B
74
276
Llama 3.1 8B Instruct
74
277
Llama 3.2 3B Instruct
72
278
Rnj 1 Instruct
72
279
Hermes 2 Pro - Llama-3 8B
72
280
Noromaid 20B
67
281
Olmo 3 7B Instruct
67
282
Llama 3.2 11B Vision Instruct
61
283
ReMM SLERP 13B
59
284
Weaver (alpha)
57
285
Aion-RP 1.0 (8B)
51
286
MythoMax 13B
49
287
Morph V3 Large
43
288
Llama 3.2 1B Instruct
29
289
Morph V3 Fast
26
290
CodeLLaMa 7B Instruct Solidity
11
291
Llemma 7b
7
Total:46836
Media:160.94
(291 modelos)
Menú de métricas
Fallos cometidos
Número total de respuestas incorrectas
1
Sonar Deep Research
4
2
Gemini 3 Flash Preview
5
3
GPT-5 Mini
5
4
Qwen3 235B A22B Thinking 2507
5
5
GPT-5 Chat
5
6
GPT-5.1
5
7
Gemini 2.5 Pro
5
8
Gemini 2.5 Pro Preview 05-06
5
9
o3 Pro
5
10
o3 Deep Research
5
11
DeepSeek V3.2 Speciale
5
12
Gemini 2.5 Flash
5
13
GPT-5.1-Codex-Mini
6
14
GPT-5.1 Chat
6
15
R1 0528
6
16
o4 Mini
6
17
GPT-5.2-Codex
6
18
Claude Sonnet 4.5
6
19
Claude 3.5 Sonnet
6
20
Gemini 2.5 Pro Preview 06-05
6
21
Gemini 3 Pro Preview
6
22
GPT-5.2 Pro
6
23
o3
6
24
GPT-4o (2024-08-06)
6
25
GPT-5 Codex
7
26
GPT-5.2 Chat
7
27
GPT-5.2
7
28
o4 Mini High
7
29
Grok 3
7
30
o1
7
31
Gemini 2.5 Flash Preview 09-2025
7
32
GPT-5 Image Mini
7
33
DeepSeek V3 0324
7
34
Gemini 2.5 Flash Image (Nano Banana)
7
35
GPT-4o
7
36
Mistral Large 3 2512
8
37
GPT-5.1-Codex
8
38
GPT-4.1
8
39
Aion-1.0
8
40
GPT-5
8
41
GPT-5.1-Codex-Max
8
42
Auto Router
8
43
Grok 4
8
44
Claude Opus 4.5
8
45
DeepSeek V3.2
8
46
R1
8
47
Claude 3.7 Sonnet (thinking)
8
48
Kimi K2.5
8
49
Qwen3 Max
8
50
Kimi K2 0905 (exacto)
8
51
Gemini 2.0 Flash
9
52
Switchpoint Router
9
53
Mistral Large
9
54
GPT-4o (2024-11-20)
9
55
GPT-4o (2024-05-13)
9
56
ChatGPT-4o
9
57
Claude 3.7 Sonnet
9
58
GPT-5 Image
9
59
Nano Banana Pro (Gemini 3 Pro Image Preview)
9
60
o1-pro
9
61
GPT-4o Search Preview
9
62
Qwen3 235B A22B
9
63
GLM 4.7
9
64
GPT-5 Nano
9
65
DeepSeek V3.2 Exp
9
66
Qwen-Plus
9
67
DeepSeek V3.1
9
68
Cogito v2.1 671B
9
69
Kimi K2 0905
9
70
Qwen3 VL 235B A22B Instruct
10
71
Mistral Medium 3.1
10
72
Qwen Plus 0728 (thinking)
10
73
Claude Sonnet 4
10
74
o4 Mini Deep Research
10
75
Llama 4 Maverick
10
76
DeepSeek V3.1 Terminus
10
77
GPT-3.5 Turbo (older v0613)
10
78
Claude Opus 4.6
10
79
Kimi K2 Thinking
10
Mejor humano
10
80
GLM 4.5
11
81
Qwen3 VL 235B A22B Thinking
11
82
Grok 3 Beta
11
83
Claude Opus 4
11
84
Claude Opus 4.1
11
85
DeepSeek V3
11
86
GPT-4.1 Mini
11
87
Qwen Plus 0728
11
88
DeepSeek V3.1 Terminus (exacto)
11
89
Grok 3 Mini Beta
11
90
GLM 4.6
11
91
Mistral Large 2407
12
92
Seed 1.6
12
93
GLM 4.6 (exacto)
12
94
Grok 3 Mini
12
95
Qwen3 Next 80B A3B Thinking
12
96
o3 Mini High
12
97
GPT-4 Turbo (older v1106)
12
98
Sonar Reasoning Pro
12
99
Mistral Medium 3
13
100
Sonar Pro Search
13
101
Step 3.5 Flash
13
102
Kimi K2 0711
13
103
MiniMax M2
13
104
o3 Mini
14
105
Qwen3 VL 32B Instruct
14
106
Devstral 2 2512
14
107
Qwen3 Coder 480B A35B (exacto)
14
108
Palmyra X5
14
109
Llama 3.3 Nemotron Super 49B V1.5
14
110
Nova Pro 1.0
14
111
Qwen3 Coder Plus
14
112
Qwen3 Coder Next
14
113
DeepSeek V3.1 Nex N1
14
114
gpt-oss-120b
15
115
Grok 4 Fast
15
116
Qwen3 VL 30B A3B Thinking
15
117
GPT-4 Turbo
15
118
gpt-oss-120b (exacto)
15
119
Gemini 2.5 Flash Lite Preview 09-2025
15
120
Qwen3 235B A22B Instruct 2507
15
121
KAT-Coder-Pro V1
15
122
Grok Code Fast 1
15
123
GPT-4
15
124
Grok 4.1 Fast
16
125
Claude Haiku 4.5
16
126
Unknown
16
127
Devstral Medium
17
128
Qwen3 Next 80B A3B Instruct
17
129
Qwen3 Coder 480B A35B
17
130
GPT-4 Turbo Preview
17
131
Aion-1.0-Mini
17
132
gpt-oss-20b
18
133
Gemini 2.5 Flash Lite
18
134
Qwen2.5 VL 72B Instruct
18
135
Sonar Pro
18
136
Trinity Large Preview
18
137
GPT-4 (older v0314)
18
138
Solar Pro 3
18
139
ERNIE 4.5 VL 424B A47B
19
140
Pixtral Large 2411
19
141
Gemini 2.0 Flash Lite
19
142
MiniMax M2.1
19
143
Hermes 4 405B
19
144
Tongyi DeepResearch 30B A3B
20
145
Mistral Large 2411
20
146
Llama 4 Scout
20
147
GLM 4.6V
20
148
Nova Premier 1.0
20
149
Qwen VL Max
20
150
Kimi Dev 72B
20
151
ERNIE 4.5 300B A47B
21
152
Hermes 3 405B Instruct
21
153
Sonar
21
154
Cogito V2 Preview Llama 405B
21
155
Mistral Small Creative
22
156
gpt-oss-safeguard-20b
22
157
Llama 3.1 Nemotron Ultra 253B v1
22
158
Jamba Large 1.7
22
159
Mistral Small 3.2 24B
23
160
Qwen3 32B
23
161
Qwen3 30B A3B Thinking 2507
23
162
Qwen3 VL 30B A3B Instruct
23
163
Qwen3 30B A3B Instruct 2507
23
164
GLM 4.5V
23
165
MiniMax M2-her
23
166
Qwen2.5 72B Instruct
24
167
R1 Distill Llama 70B
24
168
Mixtral 8x22B Instruct
24
169
Seed 1.6 Flash
24
170
Mercury Coder
25
171
Qwen3 14B
25
172
MiniMax M1
25
173
QwQ 32B
26
174
Saba
26
175
MiMo-V2-Flash
26
176
Cydonia 24B V4.1
26
177
Llama 3.3 Euryale 70B
26
178
GLM 4 32B
26
179
CodeLLaMa 7B Instruct Solidity
26
180
Nemotron 3 Nano 30B A3B
27
181
Llama 3.3 70B Instruct
27
182
Mercury
27
183
Step3
28
184
Llama 3.1 70B Instruct
28
185
Cogito V2 Preview Llama 70B
28
186
GLM 4.5 Air
28
187
GPT-4o-mini (2024-07-18)
29
188
GPT-4o-mini Search Preview
29
189
GPT-4o-mini
29
190
Command A
30
191
Qwen3 VL 8B Thinking
30
192
Llama 3.1 Nemotron 70B Instruct
30
193
Olmo 3.1 32B Think
30
194
Nemotron Nano 12B 2 VL
31
195
Mistral Small 3.1 24B
32
196
Nova 2 Lite
32
197
Qwen-Turbo
32
198
Devstral Small 1.1
33
199
Voxtral Small 24B 2507
33
200
Inflection 3 Pi
33
201
Ministral 3 14B 2512
34
202
Qwen-Max
34
203
MiMo-V2-Flash
34
204
Llama 3.1 70B Hanami x1
34
205
Nemotron Nano 9B V2
34
206
GPT-4.1 Nano
35
207
Mistral Small 3
35
208
Llemma 7b
35
209
GLM 4.7 Flash
36
210
Olmo 3 32B Think
36
211
Qwen3 Coder 30B A3B Instruct
37
212
Claude 3.5 Haiku
37
213
Hermes 4 70B
37
214
Qwen VL Plus
37
215
Nova Micro 1.0
37
216
Qwen3 8B
38
217
Qwen3 Coder Flash
38
218
Inflection 3 Productivity
38
219
Gemma 3 27B
39
220
R1 Distill Qwen 32B
39
221
Qwen2.5 VL 32B Instruct
39
222
Llama 3 70B Instruct
40
223
Qwen3 VL 8B Instruct
40
224
Morph V3 Large
40
225
Ministral 3 8B 2512
41
226
Free Models Router
41
227
Skyfall 36B V2
41
228
Llama 3 Euryale 70B v2.1
41
229
Claude 3 Haiku
42
230
SorcererLM 8x22B
43
231
Trinity Mini
44
232
Relace Search
45
233
Llama 3.1 Euryale 70B v2.2
45
234
Hunyuan A13B Instruct
49
235
Llama 3.2 11B Vision Instruct
49
236
Gemma 2 9B
50
237
Morph V3 Fast
50
238
Nova Lite 1.0
52
239
ERNIE 4.5 21B A3B
52
240
Gemma 2 27B
52
241
ERNIE 4.5 VL 28B A3B
53
242
Aion-RP 1.0 (8B)
54
243
Hermes 3 70B Instruct
56
244
Gemma 3 12B
58
245
Ministral 3 3B 2512
58
246
Mixtral 8x7B Instruct
58
247
Command R+ (08-2024)
59
248
Molmo2 8B
62
249
Qwen2.5 Coder 32B Instruct
62
250
Rocinante 12B
65
251
UnslopNemo 12B
65
252
Llama 3.2 1B Instruct
65
253
ERNIE 4.5 21B A3B Thinking
67
254
Command R (08-2024)
69
255
GPT-3.5 Turbo
70
256
Gemma 3n 4B
70
257
Pixtral 12B
70
258
Phi 4
73
259
Mistral Nemo
74
260
Ministral 8B
74
261
Olmo 3.1 32B Instruct
76
262
Jamba Mini 1.7
80
263
Qwen2.5 7B Instruct
81
264
GPT-3.5 Turbo 16k
83
265
Codestral 2508
83
266
Llama 3 8B Instruct
83
267
Olmo 3 7B Think
84
268
Ministral 3B
84
269
Noromaid 20B
87
270
Qwen2.5-VL 7B Instruct
88
271
LFM2-8B-A1B
89
272
Mistral 7B Instruct v0.1
90
273
Llama 3.1 8B Instruct
90
274
GPT-3.5 Turbo Instruct
93
275
Command R7B (12-2024)
94
276
Mistral 7B Instruct
95
277
MythoMax 13B
96
278
Goliath 120B
97
279
ReMM SLERP 13B
97
280
Mistral 7B Instruct v0.2
98
281
Mistral Tiny
100
282
Llama 3.2 3B Instruct
100
283
Rnj 1 Instruct
100
284
Weaver (alpha)
100
285
Gemma 3 4B
102
286
Mistral 7B Instruct v0.3
103
287
Llama 3 8B Lunaris
104
288
Hermes 2 Pro - Llama-3 8B
105
289
Lumimaid v0.2 8B
111
290
Granite 4.0 Micro
117
291
Olmo 3 7B Instruct
124
Total:8813
Media:30.28
(291 modelos)
Menú de métricas
Porcentaje de aciertos
Proporción de respuestas correctas sobre el total
1
Sonar Deep Research
97.5%
2
Gemini 3 Flash Preview
97.5%
3
GPT-5 Mini
97.5%
4
Qwen3 235B A22B Thinking 2507
97.5%
5
GPT-5 Chat
97.5%
6
GPT-5.1
97.5%
7
Gemini 2.5 Pro
97.5%
8
Gemini 2.5 Pro Preview 05-06
97.5%
9
o3 Pro
97.5%
10
o3 Deep Research
97.5%
11
DeepSeek V3.2 Speciale
97.0%
12
GPT-5.1-Codex-Mini
97.0%
13
GPT-5.1 Chat
97.0%
14
R1 0528
97.0%
15
o4 Mini
97.0%
16
GPT-5.2-Codex
97.0%
17
Claude Sonnet 4.5
97.0%
18
Claude 3.5 Sonnet
97.0%
19
Gemini 2.5 Pro Preview 06-05
97.0%
20
Gemini 3 Pro Preview
97.0%
21
GPT-5.2 Pro
97.0%
22
o3
96.5%
23
GPT-5 Codex
96.5%
24
GPT-5.2 Chat
96.5%
25
GPT-5.2
96.5%
26
o4 Mini High
96.5%
27
Grok 3
96.5%
28
o1
96.5%
29
Gemini 2.5 Flash
96.0%
30
Gemini 2.5 Flash Preview 09-2025
96.0%
31
GPT-5 Image Mini
96.0%
32
Mistral Large 3 2512
96.0%
33
GPT-5.1-Codex
96.0%
34
GPT-4.1
96.0%
35
Aion-1.0
96.0%
36
GPT-5
96.0%
37
GPT-5.1-Codex-Max
96.0%
38
Auto Router
96.0%
39
Grok 4
96.0%
40
Claude Opus 4.5
96.0%
41
DeepSeek V3.2
95.5%
42
R1
95.5%
43
Claude 3.7 Sonnet (thinking)
95.5%
44
Gemini 2.0 Flash
95.5%
45
Switchpoint Router
95.5%
46
Mistral Large
95.5%
47
GPT-4o (2024-11-20)
95.5%
48
GPT-4o (2024-05-13)
95.5%
49
ChatGPT-4o
95.5%
50
Claude 3.7 Sonnet
95.5%
51
GPT-5 Image
95.5%
52
Nano Banana Pro (Gemini 3 Pro Image Preview)
95.5%
53
o1-pro
95.5%
54
DeepSeek V3 0324
95.0%
55
Kimi K2.5
95.0%
56
GPT-4o Search Preview
95.0%
57
Qwen3 235B A22B
95.0%
58
GLM 4.7
95.0%
59
Qwen3 VL 235B A22B Instruct
95.0%
60
Mistral Medium 3.1
95.0%
61
Qwen Plus 0728 (thinking)
95.0%
62
Claude Sonnet 4
95.0%
63
o4 Mini Deep Research
95.0%
Mejor humano
95.0%
64
GPT-5 Nano
94.5%
65
Llama 4 Maverick
94.5%
66
DeepSeek V3.1 Terminus
94.5%
67
GPT-3.5 Turbo (older v0613)
94.5%
68
GLM 4.5
94.5%
69
Qwen3 VL 235B A22B Thinking
94.5%
70
Grok 3 Beta
94.5%
71
Claude Opus 4
94.5%
72
Claude Opus 4.1
94.5%
73
Qwen3 Max
94.0%
74
DeepSeek V3.2 Exp
94.0%
75
Qwen-Plus
94.0%
76
Claude Opus 4.6
94.0%
77
DeepSeek V3
94.0%
78
GPT-4.1 Mini
94.0%
79
Qwen Plus 0728
94.0%
80
Mistral Large 2407
94.0%
81
GPT-4o (2024-08-06)
93.5%
82
Gemini 2.5 Flash Image (Nano Banana)
93.5%
83
DeepSeek V3.1 Terminus (exacto)
93.5%
84
Seed 1.6
93.5%
85
GLM 4.6 (exacto)
93.5%
86
Mistral Medium 3
93.5%
87
Kimi K2 Thinking
93.0%
88
Grok 3 Mini Beta
93.0%
89
GLM 4.6
93.0%
90
Grok 3 Mini
93.0%
91
Qwen3 Next 80B A3B Thinking
93.0%
92
o3 Mini High
93.0%
93
o3 Mini
93.0%
94
DeepSeek V3.1
92.5%
95
Qwen3 VL 32B Instruct
92.5%
96
gpt-oss-120b
92.5%
97
Grok 4 Fast
92.5%
98
Qwen3 VL 30B A3B Thinking
92.5%
99
GPT-4 Turbo
92.5%
100
GPT-4o
92.0%
101
Sonar Pro Search
92.0%
102
Devstral 2 2512
92.0%
103
Qwen3 Coder 480B A35B (exacto)
92.0%
104
Palmyra X5
92.0%
105
gpt-oss-120b (exacto)
92.0%
106
Grok 4.1 Fast
92.0%
107
Claude Haiku 4.5
92.0%
108
Step 3.5 Flash
91.5%
109
Llama 3.3 Nemotron Super 49B V1.5
91.5%
110
Nova Pro 1.0
91.5%
111
Qwen3 Coder Plus
91.5%
112
Gemini 2.5 Flash Lite Preview 09-2025
91.5%
113
Qwen3 235B A22B Instruct 2507
91.5%
114
Cogito v2.1 671B
91.0%
115
Kimi K2 0711
91.0%
116
Qwen3 Coder Next
91.0%
117
Devstral Medium
91.0%
118
Qwen3 Next 80B A3B Instruct
91.0%
119
Qwen3 Coder 480B A35B
91.0%
120
gpt-oss-20b
91.0%
121
Gemini 2.5 Flash Lite
91.0%
122
MiniMax M2
90.5%
123
DeepSeek V3.1 Nex N1
90.5%
124
GPT-4 Turbo Preview
90.5%
125
KAT-Coder-Pro V1
90.0%
126
Qwen2.5 VL 72B Instruct
90.0%
127
ERNIE 4.5 VL 424B A47B
90.0%
128
Tongyi DeepResearch 30B A3B
90.0%
129
Mistral Large 2411
90.0%
130
Sonar Pro
89.5%
131
Pixtral Large 2411
89.5%
132
Llama 4 Scout
89.5%
133
ERNIE 4.5 300B A47B
89.5%
134
GPT-4 Turbo (older v1106)
89.0%
135
Grok Code Fast 1
89.0%
136
GPT-4
89.0%
137
GLM 4.6V
89.0%
138
Mistral Small Creative
89.0%
139
Trinity Large Preview
88.5%
140
Gemini 2.0 Flash Lite
88.5%
141
Nova Premier 1.0
88.5%
142
gpt-oss-safeguard-20b
88.5%
143
Mistral Small 3.2 24B
88.5%
144
Aion-1.0-Mini
88.0%
145
Llama 3.1 Nemotron Ultra 253B v1
88.0%
146
Jamba Large 1.7
88.0%
147
Qwen3 32B
88.0%
148
Qwen3 30B A3B Thinking 2507
88.0%
149
Qwen3 VL 30B A3B Instruct
88.0%
150
Kimi K2 0905
87.5%
151
GPT-4 (older v0314)
87.5%
152
Qwen VL Max
87.5%
153
Hermes 3 405B Instruct
87.5%
154
Sonar
87.5%
155
Qwen3 30B A3B Instruct 2507
87.5%
156
GLM 4.5V
87.5%
157
Qwen2.5 72B Instruct
87.5%
158
R1 Distill Llama 70B
87.5%
159
Mixtral 8x22B Instruct
87.5%
160
Kimi K2 0905 (exacto)
87.0%
161
Sonar Reasoning Pro
87.0%
162
QwQ 32B
87.0%
163
Cogito V2 Preview Llama 405B
86.5%
164
Mercury Coder
86.5%
165
Nemotron 3 Nano 30B A3B
86.5%
166
Kimi Dev 72B
86.0%
167
Seed 1.6 Flash
86.0%
168
Qwen3 14B
86.0%
169
Saba
86.0%
170
MiMo-V2-Flash
86.0%
171
Step3
86.0%
172
Llama 3.3 70B Instruct
85.5%
173
Mercury
85.5%
174
MiniMax M2.1
85.0%
175
Llama 3.1 70B Instruct
85.0%
176
Hermes 4 405B
84.5%
177
MiniMax M1
84.5%
178
Command A
84.5%
179
MiniMax M2-her
84.0%
180
Cydonia 24B V4.1
84.0%
181
GPT-4o-mini (2024-07-18)
84.0%
182
Qwen3 VL 8B Thinking
84.0%
183
GPT-4o-mini Search Preview
83.5%
184
GPT-4o-mini
83.5%
185
Ministral 3 14B 2512
83.0%
186
Qwen-Max
83.0%
187
Llama 3.3 Euryale 70B
82.5%
188
Cogito V2 Preview Llama 70B
82.5%
189
Llama 3.1 Nemotron 70B Instruct
82.5%
190
Nemotron Nano 12B 2 VL
82.5%
191
Mistral Small 3.1 24B
82.5%
192
Nova 2 Lite
82.5%
193
Devstral Small 1.1
82.5%
194
GPT-4.1 Nano
82.5%
195
Voxtral Small 24B 2507
82.0%
196
Inflection 3 Pi
82.0%
197
MiMo-V2-Flash
82.0%
198
GLM 4 32B
81.5%
199
Qwen-Turbo
81.5%
200
GLM 4.5 Air
81.0%
201
Qwen3 Coder 30B A3B Instruct
81.0%
202
Mistral Small 3
80.5%
203
Gemma 3 27B
80.5%
204
Claude 3.5 Haiku
80.0%
205
Qwen3 8B
80.0%
206
Qwen3 Coder Flash
80.0%
207
Hermes 4 70B
79.5%
208
Qwen VL Plus
79.5%
209
Inflection 3 Productivity
79.5%
210
R1 Distill Qwen 32B
79.5%
211
GLM 4.7 Flash
79.0%
212
Ministral 3 8B 2512
79.0%
213
Qwen2.5 VL 32B Instruct
78.5%
214
Llama 3 70B Instruct
78.5%
215
Llama 3.1 70B Hanami x1
77.5%
216
Qwen3 VL 8B Instruct
77.5%
217
Relace Search
77.5%
218
Olmo 3 32B Think
76.0%
219
Claude 3 Haiku
76.0%
220
Nemotron Nano 9B V2
75.5%
221
Olmo 3.1 32B Think
75.0%
222
Free Models Router
75.0%
223
Skyfall 36B V2
75.0%
224
Nova Micro 1.0
74.5%
225
Llama 3 Euryale 70B v2.1
74.5%
226
Trinity Mini
72.5%
227
Nova Lite 1.0
72.5%
228
ERNIE 4.5 21B A3B
71.5%
229
ERNIE 4.5 VL 28B A3B
71.5%
230
SorcererLM 8x22B
70.5%
231
Gemma 3 12B
70.5%
232
Llama 3.1 Euryale 70B v2.2
70.0%
233
Solar Pro 3
69.5%
234
Ministral 3 3B 2512
69.0%
235
Command R+ (08-2024)
69.0%
236
Gemma 2 27B
66.5%
237
Mixtral 8x7B Instruct
65.5%
238
ERNIE 4.5 21B A3B Thinking
65.0%
239
GPT-3.5 Turbo
64.5%
240
Command R (08-2024)
63.5%
241
Unknown
62.5%
242
Molmo2 8B
62.5%
243
Phi 4
62.5%
244
Gemma 3n 4B
61.5%
245
Gemma 2 9B
61.0%
246
Pixtral 12B
61.0%
247
Mistral Nemo
59.0%
248
Ministral 8B
58.0%
249
Olmo 3.1 32B Instruct
58.0%
250
GPT-3.5 Turbo 16k
58.0%
251
Jamba Mini 1.7
57.0%
252
Qwen2.5 Coder 32B Instruct
56.5%
253
Olmo 3 7B Think
56.0%
254
Hunyuan A13B Instruct
55.5%
255
Codestral 2508
53.5%
256
LFM2-8B-A1B
52.0%
257
GPT-3.5 Turbo Instruct
51.0%
258
Qwen2.5 7B Instruct
50.0%
259
Command R7B (12-2024)
49.0%
260
Gemma 3 4B
48.0%
261
Llama 3 8B Instruct
46.5%
262
Mistral 7B Instruct
46.5%
263
Goliath 120B
45.5%
264
Qwen2.5-VL 7B Instruct
45.0%
265
Llama 3 8B Lunaris
44.0%
266
Mistral 7B Instruct v0.2
43.5%
267
Mistral 7B Instruct v0.3
43.5%
268
Rocinante 12B
43.0%
269
Mistral Tiny
43.0%
270
Ministral 3B
41.5%
271
Hermes 3 70B Instruct
39.0%
272
Granite 4.0 Micro
39.0%
273
Lumimaid v0.2 8B
38.5%
274
Mistral 7B Instruct v0.1
37.5%
275
UnslopNemo 12B
37.0%
276
Llama 3.1 8B Instruct
37.0%
277
Llama 3.2 3B Instruct
36.0%
278
Rnj 1 Instruct
36.0%
279
Hermes 2 Pro - Llama-3 8B
36.0%
280
Noromaid 20B
33.5%
281
Olmo 3 7B Instruct
33.5%
282
Llama 3.2 11B Vision Instruct
30.5%
283
ReMM SLERP 13B
29.5%
284
Weaver (alpha)
28.5%
285
Aion-RP 1.0 (8B)
25.5%
286
MythoMax 13B
24.5%
287
Morph V3 Large
21.5%
288
Llama 3.2 1B Instruct
14.5%
289
Morph V3 Fast
13.0%
290
CodeLLaMa 7B Instruct Solidity
5.5%
291
Llemma 7b
3.5%
Media:80.5%
(291 modelos)
Menú de métricas
Tiempo promedio de respuesta
Tiempo promedio que tarda el modelo en responder a cada pregunta
1
Ministral 3B
1.5s
2
Devstral Small 1.1
1.5s
3
Ministral 8B
1.6s
4
gpt-oss-safeguard-20b
1.8s
5
Voxtral Small 24B 2507
1.9s
6
Mistral 7B Instruct v0.3
1.9s
7
Morph V3 Large
2.0s
8
Mercury Coder
2.1s
9
Mistral 7B Instruct
2.1s
10
LFM2-8B-A1B
2.2s
11
Codestral 2508
2.2s
12
Mercury
2.3s
13
Mistral 7B Instruct v0.2
2.3s
14
Morph V3 Fast
2.3s
15
GPT-3.5 Turbo 16k
2.3s
16
GPT-3.5 Turbo
2.4s
17
Nova Micro 1.0
2.6s
18
GPT-4o (2024-05-13)
2.9s
19
Mistral Tiny
3.0s
20
Kimi K2 0905
3.0s
21
Gemini 2.5 Flash Lite Preview 09-2025
3.1s
22
Gemini 2.0 Flash
3.1s
23
GPT-4.1 Nano
3.2s
24
Gemini 2.0 Flash Lite
3.2s
25
GPT-5.1-Codex
3.2s
26
Mixtral 8x22B Instruct
3.3s
27
Devstral Medium
3.4s
28
Saba
3.4s
29
Claude 3 Haiku
3.4s
30
Command R7B (12-2024)
3.4s
31
Nova Pro 1.0
3.4s
32
Nova Lite 1.0
3.5s
33
Gemini 2.5 Flash Lite
3.5s
34
Ministral 3 3B 2512
3.5s
35
Jamba Mini 1.7
3.6s
36
Llama 3.2 1B Instruct
3.6s
37
GPT-3.5 Turbo Instruct
3.6s
38
Qwen3 Coder 480B A35B (exacto)
3.8s
39
GPT-5.1 Chat
3.8s
40
GPT-5 Chat
3.9s
41
Hermes 2 Pro - Llama-3 8B
4.0s
42
Pixtral 12B
4.1s
43
Lumimaid v0.2 8B
4.1s
44
Gemini 3 Flash Preview
4.2s
45
Aion-1.0-Mini
4.3s
46
GPT-5.1-Codex-Mini
4.4s
47
GPT-4o-mini Search Preview
4.4s
48
Gemma 2 9B
4.4s
49
Relace Search
4.4s
50
Llama 3 8B Lunaris
4.5s
51
Gemini 2.5 Flash Preview 09-2025
4.6s
52
GPT-5 Codex
4.7s
53
Gemini 2.5 Flash
4.8s
54
Hermes 4 70B
4.9s
55
Cogito v2.1 671B
5.0s
56
Ministral 3 8B 2512
5.1s
57
Qwen3 Next 80B A3B Instruct
5.1s
58
ChatGPT-4o
5.2s
59
Rnj 1 Instruct
5.3s
60
Molmo2 8B
5.3s
61
GPT-4o (2024-11-20)
5.3s
62
Gemma 2 27B
5.3s
63
Trinity Mini
5.7s
64
Mistral Medium 3
5.8s
65
Sonar Pro
5.9s
66
Claude Haiku 4.5
6.0s
67
gpt-oss-120b
6.0s
68
Sonar
6.0s
69
Skyfall 36B V2
6.0s
70
Kimi K2 0905 (exacto)
6.4s
71
gpt-oss-20b
6.5s
72
Mistral Medium 3.1
6.5s
73
Hunyuan A13B Instruct
6.6s
74
Ministral 3 14B 2512
6.6s
75
Qwen3 Coder Flash
6.6s
76
ERNIE 4.5 21B A3B
6.7s
77
o3 Mini
6.8s
78
Llama 4 Scout
6.8s
79
o3 Mini High
6.9s
80
Claude 3.5 Haiku
7.0s
81
Mistral Small Creative
7.0s
82
Mistral Small 3.1 24B
7.1s
83
GPT-4o-mini
7.1s
84
GPT-4.1 Mini
7.2s
85
Qwen2.5-VL 7B Instruct
7.3s
86
GPT-4o-mini (2024-07-18)
7.3s
87
Nova 2 Lite
7.3s
88
GPT-3.5 Turbo (older v0613)
7.4s
89
KAT-Coder-Pro V1
7.5s
90
GPT-4o
7.6s
91
Mistral Large 2411
7.6s
92
Qwen-Turbo
7.7s
93
Command A
7.8s
94
Mistral Nemo
7.8s
95
Cogito V2 Preview Llama 70B
7.8s
96
MiniMax M2-her
7.9s
97
GPT-5.2 Chat
7.9s
98
Hermes 4 405B
7.9s
99
o4 Mini
8.0s
100
Mistral Small 3
8.2s
101
Command R+ (08-2024)
8.2s
102
Qwen VL Plus
8.3s
103
Llama 4 Maverick
8.4s
104
GPT-4o (2024-08-06)
8.6s
105
Mistral Small 3.2 24B
8.6s
106
Cydonia 24B V4.1
8.6s
107
GLM 4 32B
8.6s
108
Palmyra X5
8.6s
109
Grok 4 Fast
8.8s
110
o3
8.9s
111
GPT-4.1
8.9s
112
Aion-RP 1.0 (8B)
8.9s
113
Seed 1.6 Flash
9.0s
114
Llama 3 Euryale 70B v2.1
9.0s
115
Step 3.5 Flash
9.1s
116
o1
9.3s
117
GPT-5.1-Codex-Max
9.5s
118
Sonar Pro Search
9.5s
119
UnslopNemo 12B
9.6s
120
GPT-4o Search Preview
9.7s
121
Mixtral 8x7B Instruct
9.9s
122
Qwen-Max
10.0s
123
Inflection 3 Pi
10.0s
124
Inflection 3 Productivity
10.1s
125
Kimi K2 0711
10.1s
126
Rocinante 12B
10.2s
127
Claude 3.7 Sonnet
10.3s
128
Grok Code Fast 1
10.3s
129
Claude Sonnet 4
10.3s
130
Nemotron Nano 9B V2
10.4s
131
Qwen2.5 7B Instruct
10.5s
132
Llama 3.1 70B Instruct
10.6s
133
Qwen-Plus
10.6s
134
Gemma 3n 4B
10.7s
135
gpt-oss-120b (exacto)
10.7s
136
GPT-4 Turbo (older v1106)
10.7s
137
Grok 4.1 Fast
10.8s
138
Qwen Plus 0728
10.8s
139
GPT-4
11.0s
140
GPT-4 Turbo
11.1s
141
Qwen3 Coder Plus
11.1s
142
GPT-5.2-Codex
11.1s
143
DeepSeek V3
11.2s
144
Gemma 3 27B
11.2s
145
o4 Mini High
11.2s
146
Pixtral Large 2411
11.3s
147
Mistral Large
11.7s
148
Nova Premier 1.0
11.7s
149
Qwen3 Coder Next
11.7s
150
GPT-4 (older v0314)
11.8s
151
Qwen3 Coder 480B A35B
11.8s
152
Mistral Large 3 2512
11.9s
153
SorcererLM 8x22B
12.0s
154
Mistral Large 2407
12.0s
155
Qwen3 Coder 30B A3B Instruct
12.2s
156
Sonar Reasoning Pro
12.3s
157
Weaver (alpha)
12.5s
158
Claude Sonnet 4.5
12.6s
159
Gemma 3 12B
12.7s
160
Nemotron Nano 12B 2 VL
12.7s
161
ReMM SLERP 13B
12.8s
162
Olmo 3.1 32B Instruct
12.8s
163
Gemma 3 4B
12.8s
164
GLM 4.5 Air
12.9s
165
Llama 3.1 Nemotron Ultra 253B v1
12.9s
166
ERNIE 4.5 300B A47B
13.0s
167
GPT-4 Turbo Preview
13.0s
168
Llama 3 8B Instruct
13.1s
169
Qwen2.5 72B Instruct
13.2s
170
Phi 4
13.2s
171
Claude Opus 4.5
13.3s
172
Llama 3 70B Instruct
13.5s
173
Llama 3.3 70B Instruct
13.6s
174
Cogito V2 Preview Llama 405B
13.6s
175
Command R (08-2024)
13.6s
176
Qwen3 30B A3B Instruct 2507
13.8s
177
Noromaid 20B
13.9s
178
Grok 3 Mini
13.9s
179
Trinity Large Preview
14.2s
180
Grok 3 Mini Beta
14.2s
181
ERNIE 4.5 VL 28B A3B
14.2s
182
R1 Distill Llama 70B
14.2s
183
Llama 3.1 Nemotron 70B Instruct
14.3s
184
Claude 3.5 Sonnet
14.3s
185
GPT-5 Mini
14.5s
186
MiMo-V2-Flash
14.5s
187
GPT-5.2
14.6s
188
GPT-5 Image Mini
14.7s
189
Claude Opus 4.6
15.0s
190
Auto Router
15.1s
191
Qwen2.5 Coder 32B Instruct
15.1s
192
Granite 4.0 Micro
15.1s
193
MythoMax 13B
15.2s
194
GPT-5.1
15.6s
195
Qwen2.5 VL 72B Instruct
15.7s
196
Gemini 2.5 Flash Image (Nano Banana)
15.9s
197
MiniMax M2
16.0s
198
Jamba Large 1.7
16.0s
199
Olmo 3 7B Think
16.3s
200
Qwen3 VL 30B A3B Instruct
16.4s
201
Qwen VL Max
16.6s
202
Qwen3 Max
16.7s
203
Qwen3 VL 32B Instruct
16.7s
204
R1 0528
16.8s
205
DeepSeek V3.1 Terminus (exacto)
16.9s
206
Switchpoint Router
17.1s
207
DeepSeek V3 0324
17.2s
208
Grok 3 Beta
17.3s
209
Qwen3 VL 235B A22B Instruct
17.3s
210
Grok 3
17.3s
211
Qwen3 30B A3B Thinking 2507
17.4s
212
Qwen3 Next 80B A3B Thinking
17.9s
213
GLM 4.6
18.2s
214
DeepSeek V3.1 Terminus
18.4s
215
Olmo 3 7B Instruct
18.5s
216
GPT-5
18.7s
217
ERNIE 4.5 VL 424B A47B
18.7s
218
GPT-5 Image
18.8s
219
Qwen3 VL 8B Instruct
19.1s
220
Llama 3.3 Nemotron Super 49B V1.5
19.3s
221
GPT-5 Nano
20.1s
222
MiniMax M1
20.3s
223
Llama 3.1 8B Instruct
20.8s
224
Llama 3.3 Euryale 70B
20.9s
225
Llama 3.1 Euryale 70B v2.2
21.1s
226
Nano Banana Pro (Gemini 3 Pro Image Preview)
22.1s
227
Qwen3 235B A22B Instruct 2507
22.3s
228
Mistral 7B Instruct v0.1
22.4s
229
Hermes 3 405B Instruct
22.9s
230
Gemini 2.5 Pro
23.1s
231
MiniMax M2.1
23.1s
232
Free Models Router
23.1s
233
Gemini 2.5 Pro Preview 06-05
23.2s
234
Gemini 3 Pro Preview
23.4s
235
Gemini 2.5 Pro Preview 05-06
23.5s
236
Devstral 2 2512
23.6s
237
Goliath 120B
24.0s
238
Qwen3 32B
24.0s
239
DeepSeek V3.1 Nex N1
24.3s
240
MiMo-V2-Flash
24.7s
241
Qwen3 14B
25.0s
242
Aion-1.0
25.2s
243
GLM 4.5V
25.4s
244
Nemotron 3 Nano 30B A3B
26.0s
245
Llama 3.2 3B Instruct
26.1s
246
Qwen3 235B A22B
26.5s
247
Qwen3 VL 30B A3B Thinking
26.9s
248
Claude Opus 4
27.0s
249
GLM 4.5
27.2s
250
Grok 4
28.0s
251
Qwen Plus 0728 (thinking)
28.1s
252
Tongyi DeepResearch 30B A3B
28.3s
253
ERNIE 4.5 21B A3B Thinking
29.0s
254
DeepSeek V3.2
29.7s
255
Claude Opus 4.1
29.8s
256
Claude 3.7 Sonnet (thinking)
29.9s
257
CodeLLaMa 7B Instruct Solidity
30.6s
258
o1-pro
31.0s
259
Llama 3.1 70B Hanami x1
31.4s
260
DeepSeek V3.2 Exp
31.5s
261
GLM 4.6 (exacto)
32.5s
262
Solar Pro 3
33.1s
263
Qwen3 VL 235B A22B Thinking
33.7s
264
GLM 4.6V
35.6s
265
o3 Pro
36.1s
266
R1 Distill Qwen 32B
37.0s
267
Seed 1.6
37.2s
268
GPT-5.2 Pro
38.8s
269
Qwen3 8B
39.3s
270
Qwen2.5 VL 32B Instruct
40.2s
271
DeepSeek V3.1
40.6s
272
Qwen3 VL 8B Thinking
41.3s
273
GLM 4.7
41.6s
274
R1
43.8s
275
Kimi K2.5
44.2s
276
Sonar Deep Research
46.0s
277
Olmo 3 32B Think
47.6s
278
Olmo 3.1 32B Think
47.6s
279
Kimi K2 Thinking
48.2s
280
Kimi Dev 72B
51.2s
281
Step3
51.5s
282
Llama 3.2 11B Vision Instruct
53.9s
283
QwQ 32B
55.2s
284
DeepSeek V3.2 Speciale
60.9s
285
Llemma 7b
66.5s
286
Qwen3 235B A22B Thinking 2507
85.5s
287
o4 Mini Deep Research
90.7s
288
GLM 4.7 Flash
119.3s
289
o3 Deep Research
127.7s
290
Hermes 3 70B Instruct
177.4s
Media:16.4s
(290 modelos)
Menú de métricas
Coste promedio por pregunta
Coste medio en USD por pregunta evaluada
1
LFM2-8B-A1B
$0.0000
2
Mistral Nemo
$0.0000
3
Ministral 3B
$0.0000
4
Gemma 3n 4B
$0.0000
5
Llama 3 8B Lunaris
$0.0000
6
Gemma 2 9B
$0.0000
7
Llama 3 8B Instruct
$0.0001
8
Gemma 3 4B
$0.0001
9
Granite 4.0 Micro
$0.0001
10
Llama 3.2 3B Instruct
$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
Llama 3.1 8B Instruct
$0.0001
17
Nova Micro 1.0
$0.0001
18
Mistral Small 3
$0.0001
19
Llama 3.2 1B Instruct
$0.0001
20
Pixtral 12B
$0.0001
21
Phi 4
$0.0001
22
Voxtral Small 24B 2507
$0.0001
23
Hermes 2 Pro - Llama-3 8B
$0.0001
24
Gemma 3 12B
$0.0001
25
Qwen-Turbo
$0.0001
26
Mistral 7B Instruct v0.1
$0.0001
27
Devstral Small 1.1
$0.0001
28
Nova Lite 1.0
$0.0001
29
Ministral 3 3B 2512
$0.0001
30
Mistral Small 3.2 24B
$0.0002
31
Rnj 1 Instruct
$0.0002
32
Gemini 2.0 Flash Lite
$0.0002
33
gpt-oss-120b (exacto)
$0.0002
34
Gemma 3 27B
$0.0002
35
ERNIE 4.5 21B A3B
$0.0002
36
Mistral 7B Instruct v0.3
$0.0002
37
Mistral 7B Instruct v0.2
$0.0002
38
Mistral 7B Instruct
$0.0002
39
Llama 3.2 11B Vision Instruct
$0.0002
40
Trinity Mini
$0.0002
41
Ministral 3 8B 2512
$0.0002
42
Qwen2.5-VL 7B Instruct
$0.0002
43
Molmo2 8B
$0.0002
44
Lumimaid v0.2 8B
$0.0002
45
GPT-4.1 Nano
$0.0002
46
Gemini 2.0 Flash
$0.0002
47
Olmo 3 7B Instruct
$0.0002
48
Hermes 4 70B
$0.0002
49
Qwen3 Coder 30B A3B Instruct
$0.0002
50
gpt-oss-20b
$0.0003
51
Mistral Tiny
$0.0003
52
Nemotron Nano 9B V2
$0.0003
53
Ministral 3 14B 2512
$0.0003
54
Llama 4 Scout
$0.0003
55
Qwen2.5 72B Instruct
$0.0003
56
Saba
$0.0003
57
Command R (08-2024)
$0.0003
58
Jamba Mini 1.7
$0.0003
59
Qwen3 14B
$0.0003
60
Qwen3 30B A3B Instruct 2507
$0.0003
61
gpt-oss-safeguard-20b
$0.0003
62
UnslopNemo 12B
$0.0003
63
Mistral Small 3.1 24B
$0.0003
64
MiMo-V2-Flash
$0.0003
65
Rocinante 12B
$0.0004
66
DeepSeek V3.2 Exp
$0.0004
67
Qwen3 8B
$0.0004
68
KAT-Coder-Pro V1
$0.0004
69
Llama 3.1 70B Instruct
$0.0004
70
Hunyuan A13B Instruct
$0.0004
71
DeepSeek V3.2
$0.0004
72
Qwen2.5 Coder 32B Instruct
$0.0004
73
GPT-4o Search Preview
$0.0004
74
Gemini 2.5 Flash Lite
$0.0004
75
Cydonia 24B V4.1
$0.0004
76
Seed 1.6 Flash
$0.0004
77
Gemma 2 27B
$0.0004
78
gpt-oss-120b
$0.0005
79
Gemini 2.5 Flash Lite Preview 09-2025
$0.0005
80
Llama 3.3 70B Instruct
$0.0005
81
Mistral Small Creative
$0.0005
82
Qwen3 235B A22B Instruct 2507
$0.0005
83
Mercury Coder
$0.0005
84
Mercury
$0.0005
85
Llama 3 70B Instruct
$0.0005
86
Codestral 2508
$0.0005
87
ReMM SLERP 13B
$0.0005
88
Olmo 3.1 32B Instruct
$0.0006
89
Mixtral 8x7B Instruct
$0.0006
90
Llama 4 Maverick
$0.0006
91
Qwen2.5 VL 72B Instruct
$0.0006
92
Qwen3 32B
$0.0006
93
DeepSeek V3 0324
$0.0006
94
DeepSeek V3
$0.0006
95
DeepSeek V3.1 Terminus (exacto)
$0.0006
96
Qwen VL Plus
$0.0006
97
Skyfall 36B V2
$0.0006
98
Claude 3 Haiku
$0.0007
99
GPT-4o-mini
$0.0007
100
GPT-4o-mini (2024-07-18)
$0.0007
101
ERNIE 4.5 300B A47B
$0.0007
102
Grok 4 Fast
$0.0007
103
Aion-1.0-Mini
$0.0007
104
Llama 3.3 Nemotron Super 49B V1.5
$0.0007
105
ERNIE 4.5 VL 28B A3B
$0.0007
106
GPT-3.5 Turbo
$0.0007
107
DeepSeek V3.1
$0.0007
108
Grok 4.1 Fast
$0.0007
109
Olmo 3 7B Think
$0.0007
110
Qwen3 30B A3B Thinking 2507
$0.0007
111
Qwen3 VL 30B A3B Instruct
$0.0007
112
Tongyi DeepResearch 30B A3B
$0.0008
113
DeepSeek V3.1 Terminus
$0.0008
114
Nemotron 3 Nano 30B A3B
$0.0008
115
Cogito V2 Preview Llama 70B
$0.0008
116
Qwen2.5 VL 32B Instruct
$0.0008
117
Hermes 3 405B Instruct
$0.0008
118
ERNIE 4.5 21B A3B Thinking
$0.0008
119
GPT-5 Nano
$0.0008
120
Llama 3.3 Euryale 70B
$0.0009
121
Qwen3 VL 235B A22B Instruct
$0.0009
122
Llama 3.1 Euryale 70B v2.2
$0.0009
123
Grok 3 Mini Beta
$0.0009
124
Grok 3 Mini
$0.0009
125
QwQ 32B
$0.0009
126
Qwen3 VL 8B Instruct
$0.0009
127
GLM 4.5 Air
$0.0010
128
Devstral Medium
$0.0010
129
GPT-4.1 Mini
$0.0010
130
Aion-RP 1.0 (8B)
$0.0010
131
DeepSeek V3.1 Nex N1
$0.0010
132
Qwen3 Next 80B A3B Instruct
$0.0010
133
MiniMax M2-her
$0.0010
134
GPT-5.1-Codex-Mini
$0.0010
135
Weaver (alpha)
$0.0011
136
R1 Distill Qwen 32B
$0.0011
137
Qwen3 Coder 480B A35B
$0.0011
138
Mistral Medium 3
$0.0011
139
Cogito v2.1 671B
$0.0011
140
Qwen-Plus
$0.0011
141
Qwen Plus 0728
$0.0012
142
ERNIE 4.5 VL 424B A47B
$0.0012
143
Mistral Large 3 2512
$0.0012
144
Qwen3 235B A22B
$0.0012
145
Qwen3 Coder 480B A35B (exacto)
$0.0012
146
Nemotron Nano 12B 2 VL
$0.0012
147
Qwen3 Coder Flash
$0.0013
148
Llama 3.1 Nemotron Ultra 253B v1
$0.0013
149
Qwen3 Coder Next
$0.0013
150
R1 Distill Llama 70B
$0.0013
151
MiniMax M2.1
$0.0014
152
Llama 3 Euryale 70B v2.1
$0.0014
153
Morph V3 Large
$0.0014
154
Hermes 4 405B
$0.0014
155
GPT-3.5 Turbo (older v0613)
$0.0014
156
Llama 3.1 Nemotron 70B Instruct
$0.0014
157
DeepSeek V3.2 Speciale
$0.0015
158
Noromaid 20B
$0.0015
159
Kimi K2 0711
$0.0015
160
GPT-3.5 Turbo Instruct
$0.0015
161
Qwen3 VL 32B Instruct
$0.0015
162
GLM 4.7 Flash
$0.0015
163
MiniMax M2
$0.0015
164
Mistral Medium 3.1
$0.0016
165
Kimi K2 0905
$0.0016
166
Nova Pro 1.0
$0.0016
167
Kimi Dev 72B
$0.0016
168
Gemini 3 Flash Preview
$0.0017
169
GLM 4.5V
$0.0017
170
CodeLLaMa 7B Instruct Solidity
$0.0017
171
GLM 4.6
$0.0018
172
GLM 4.6V
$0.0018
173
Olmo 3 32B Think
$0.0019
174
Olmo 3.1 32B Think
$0.0019
175
Qwen3 VL 30B A3B Thinking
$0.0020
176
Claude 3.5 Haiku
$0.0020
177
Grok Code Fast 1
$0.0020
178
GPT-5 Mini
$0.0021
179
Gemini 2.5 Flash
$0.0024
180
MiniMax M1
$0.0025
181
Relace Search
$0.0025
182
Gemini 2.5 Flash Preview 09-2025
$0.0026
183
Hermes 3 70B Instruct
$0.0027
184
Nova 2 Lite
$0.0028
185
Seed 1.6
$0.0028
186
Qwen3 235B A22B Thinking 2507
$0.0028
187
GLM 4.5
$0.0029
188
Qwen VL Max
$0.0029
189
Switchpoint Router
$0.0029
190
GLM 4.6 (exacto)
$0.0029
191
Gemini 2.5 Flash Image (Nano Banana)
$0.0030
192
Cogito V2 Preview Llama 405B
$0.0030
193
Step3
$0.0030
194
GPT-5.1-Codex
$0.0030
195
Mixtral 8x22B Instruct
$0.0031
196
Llama 3.1 70B Hanami x1
$0.0031
197
Llemma 7b
$0.0032
198
GPT-5.1 Chat
$0.0034
199
Qwen3 Next 80B A3B Thinking
$0.0037
200
Qwen3 Coder Plus
$0.0038
201
Kimi K2 0905 (exacto)
$0.0038
202
Palmyra X5
$0.0040
203
Mistral Large 2411
$0.0040
204
R1
$0.0040
205
GPT-5 Image Mini
$0.0041
206
Claude Haiku 4.5
$0.0041
207
Command A
$0.0044
208
GPT-4.1
$0.0045
209
Mistral Large
$0.0045
210
R1 0528
$0.0045
211
Pixtral Large 2411
$0.0046
212
Qwen3 Max
$0.0046
213
Mistral Large 2407
$0.0046
214
Qwen-Max
$0.0047
215
Command R+ (08-2024)
$0.0047
216
Kimi K2 Thinking
$0.0048
217
GPT-5 Codex
$0.0048
218
Inflection 3 Productivity
$0.0050
219
Inflection 3 Pi
$0.0050
220
GPT-4o
$0.0051
221
GPT-4o (2024-08-06)
$0.0052
222
GPT-5 Chat
$0.0054
223
GLM 4.7
$0.0056
224
SorcererLM 8x22B
$0.0056
225
Nova Premier 1.0
$0.0059
226
Qwen3 VL 235B A22B Thinking
$0.0059
227
Sonar
$0.0063
228
o3 Mini High
$0.0064
229
Goliath 120B
$0.0064
230
o3 Mini
$0.0064
231
Kimi K2.5
$0.0065
232
o4 Mini
$0.0065
233
Qwen3 VL 8B Thinking
$0.0070
234
Morph V3 Fast
$0.0071
235
GPT-4o (2024-11-20)
$0.0073
236
Jamba Large 1.7
$0.0081
237
GPT-5.2 Chat
$0.0081
238
Qwen Plus 0728 (thinking)
$0.0086
239
GPT-5.2-Codex
$0.0091
240
GPT-4o (2024-05-13)
$0.0095
241
GPT-5.1
$0.0099
242
Aion-1.0
$0.0102
243
GPT-5.2
$0.0102
244
o4 Mini High
$0.0107
245
o3
$0.0109
246
GPT-5
$0.0109
247
ChatGPT-4o
$0.0110
248
Claude Sonnet 4
$0.0110
249
GPT-5.1-Codex-Max
$0.0119
250
Claude 3.7 Sonnet
$0.0124
251
Claude Sonnet 4.5
$0.0127
252
Grok 3
$0.0131
253
Grok 3 Beta
$0.0132
254
Sonar Pro
$0.0160
255
Claude 3.5 Sonnet
$0.0168
256
Sonar Reasoning Pro
$0.0173
257
GPT-5 Image
$0.0187
258
Auto Router
$0.0209
259
GPT-4 Turbo
$0.0209
260
Grok 4
$0.0215
261
GPT-4 Turbo Preview
$0.0219
262
Claude Opus 4.5
$0.0231
263
Claude Opus 4.6
$0.0242
264
Sonar Pro Search
$0.0272
265
Nano Banana Pro (Gemini 3 Pro Image Preview)
$0.0276
266
Gemini 2.5 Pro
$0.0287
267
Gemini 2.5 Pro Preview 06-05
$0.0288
268
Gemini 3 Pro Preview
$0.0289
269
Gemini 2.5 Pro Preview 05-06
$0.0293
270
Claude 3.7 Sonnet (thinking)
$0.0360
271
GPT-4 (older v0314)
$0.0381
272
GPT-4
$0.0418
273
Claude Opus 4
$0.0523
274
Claude Opus 4.1
$0.0556
275
o3 Pro
$0.1048
276
o1
$0.1147
277
GPT-5.2 Pro
$0.1226
278
o4 Mini Deep Research
$0.1792
279
o3 Deep Research
$0.7948
280
Sonar Deep Research
$1.1791
281
o1-pro
$1.1830
Media:$0.0100
(281 modelos)
Menú de métricas
Confianza promedio
Nivel de confianza medio reportado por el modelo
1
Gemini 3 Flash Preview
100.0%
2
GPT-5 Chat
100.0%
3
Gemini 2.5 Pro Preview 05-06
100.0%
4
o3 Pro
100.0%
5
GPT-5.1-Codex-Mini
100.0%
6
GPT-5.1 Chat
100.0%
7
o4 Mini
100.0%
8
GPT-5.2 Chat
100.0%
9
Aion-1.0
100.0%
10
GPT-5.1-Codex-Max
100.0%
11
Claude Opus 4.5
100.0%
12
Nano Banana Pro (Gemini 3 Pro Image Preview)
100.0%
13
o1-pro
100.0%
14
o4 Mini Deep Research
100.0%
15
gpt-oss-120b
100.0%
16
Grok 4 Fast
100.0%
17
Qwen3 VL 30B A3B Thinking
100.0%
18
Grok 4.1 Fast
100.0%
19
gpt-oss-20b
100.0%
20
Mistral Large 2411
100.0%
21
Gemini 2.5 Pro
100.0%
22
o3 Deep Research
100.0%
23
Gemini 3 Pro Preview
100.0%
24
DeepSeek V3.2 Speciale
100.0%
25
Claude Sonnet 4.5
100.0%
26
Gemini 2.5 Pro Preview 06-05
100.0%
27
o4 Mini High
100.0%
28
GPT-4.1
100.0%
29
Qwen3 VL 235B A22B Instruct
100.0%
30
Qwen Plus 0728 (thinking)
100.0%
31
R1 0528
100.0%
32
Step3
100.0%
33
GPT-5 Mini
100.0%
34
Auto Router
100.0%
35
Mistral Medium 3.1
100.0%
36
Claude Sonnet 4
100.0%
37
Qwen3 VL 235B A22B Thinking
100.0%
38
Claude Opus 4.1
100.0%
39
o3 Mini
100.0%
40
Qwen3 235B A22B Thinking 2507
100.0%
41
Grok 4
100.0%
42
Claude Opus 4
99.9%
43
Claude 3.5 Sonnet
99.9%
44
Mistral Large
99.9%
45
Claude 3.7 Sonnet
99.9%
46
Mistral Large 2407
99.9%
47
Mistral Large 3 2512
99.9%
48
GLM 4.6V
99.9%
49
ChatGPT-4o
99.9%
50
Qwen Plus 0728
99.9%
51
Tongyi DeepResearch 30B A3B
99.9%
52
GPT-4o (2024-11-20)
99.9%
53
GLM 4.5
99.9%
54
o1
99.9%
55
Gemini 2.0 Flash
99.9%
56
Claude Opus 4.6
99.9%
57
gpt-oss-safeguard-20b
99.9%
58
Gemma 3 27B
99.8%
59
Gemini 2.5 Flash Lite
99.8%
60
GPT-5.1
99.8%
61
GPT-4 Turbo
99.8%
62
Kimi K2.5
99.8%
63
Nemotron 3 Nano 30B A3B
99.8%
64
Mistral Small Creative
99.7%
65
Ministral 3 14B 2512
99.7%
66
Qwen2.5 72B Instruct
99.7%
67
Switchpoint Router
99.7%
68
GPT-5 Codex
99.7%
69
ERNIE 4.5 300B A47B
99.7%
70
Qwen3 30B A3B Instruct 2507
99.6%
71
Mistral Medium 3
99.6%
72
Command A
99.6%
73
Qwen-Max
99.6%
74
Claude Haiku 4.5
99.6%
75
GPT-3.5 Turbo
99.6%
76
GPT-5.2 Pro
99.5%
77
GLM 4.7
99.5%
78
DeepSeek V3.1 Terminus
99.5%
79
gpt-oss-120b (exacto)
99.5%
80
GPT-5.2
99.5%
81
Seed 1.6
99.5%
82
Sonar Deep Research
99.5%
83
Gemini 2.5 Flash Preview 09-2025
99.5%
84
GPT-5
99.5%
85
R1
99.5%
86
Claude 3.7 Sonnet (thinking)
99.5%
87
Qwen3 235B A22B
99.5%
88
Qwen3 VL 32B Instruct
99.5%
89
QwQ 32B
99.5%
90
o3
99.4%
91
Qwen3 Next 80B A3B Instruct
99.4%
92
Devstral Medium
99.4%
93
Mercury Coder
99.4%
94
GPT-5 Image Mini
99.4%
95
GPT-4.1 Mini
99.4%
96
GPT-4o Search Preview
99.4%
97
Qwen3 Coder 480B A35B
99.4%
98
Mistral Small 3.2 24B
99.3%
99
Gemma 3 12B
99.3%
100
GLM 4.6 (exacto)
99.3%
101
DeepSeek V3
99.2%
102
Solar Pro 3
99.2%
103
GPT-3.5 Turbo (older v0613)
99.2%
104
Qwen3 30B A3B Thinking 2507
99.2%
105
Grok 3
99.1%
106
Llama 4 Maverick
99.1%
107
GPT-5.2-Codex
99.1%
108
GPT-5 Nano
99.0%
109
Qwen3 Next 80B A3B Thinking
99.0%
110
Mercury
99.0%
111
DeepSeek V3.2
99.0%
112
Qwen3 Coder 480B A35B (exacto)
99.0%
113
Pixtral Large 2411
99.0%
114
Mistral Small 3.1 24B
99.0%
115
Ministral 3 8B 2512
99.0%
116
Grok 3 Beta
99.0%
117
Qwen3 235B A22B Instruct 2507
99.0%
118
DeepSeek V3.2 Exp
99.0%
119
o3 Mini High
99.0%
120
Palmyra X5
99.0%
121
GLM 4.5V
99.0%
122
Qwen3 Coder Next
98.9%
123
DeepSeek V3.1 Terminus (exacto)
98.9%
124
Jamba Large 1.7
98.9%
125
GPT-4o (2024-05-13)
98.9%
126
GPT-5 Image
98.9%
127
Devstral 2 2512
98.9%
128
Qwen3 VL 30B A3B Instruct
98.9%
129
R1 Distill Qwen 32B
98.9%
130
Grok 3 Mini
98.8%
131
MiMo-V2-Flash
98.8%
132
GPT-5.1-Codex
98.8%
133
Gemma 3 4B
98.8%
134
Llama 3.1 Nemotron Ultra 253B v1
98.8%
135
Devstral Small 1.1
98.8%
136
Gemini 2.5 Flash Lite Preview 09-2025
98.7%
137
Hermes 3 405B Instruct
98.7%
138
MiMo-V2-Flash
98.7%
139
GPT-3.5 Turbo 16k
98.7%
140
GPT-4o-mini
98.7%
141
ERNIE 4.5 VL 424B A47B
98.7%
142
Step 3.5 Flash
98.6%
143
Llama 3 70B Instruct
98.6%
144
Qwen3 32B
98.5%
145
R1 Distill Llama 70B
98.5%
146
Gemini 2.5 Flash
98.5%
147
DeepSeek V3 0324
98.5%
148
Qwen VL Max
98.5%
149
Qwen-Plus
98.5%
150
Saba
98.5%
151
Nova Pro 1.0
98.5%
152
Llama 3.3 Nemotron Super 49B V1.5
98.5%
153
Relace Search
98.5%
154
Sonar Pro
98.4%
155
Mixtral 8x22B Instruct
98.4%
156
Voxtral Small 24B 2507
98.4%
157
Kimi K2 Thinking
98.4%
158
Qwen VL Plus
98.4%
159
ERNIE 4.5 21B A3B Thinking
98.4%
160
Sonar Pro Search
98.3%
161
GPT-4o-mini (2024-07-18)
98.3%
162
GLM 4.6
98.3%
163
Claude 3.5 Haiku
98.3%
164
Llama 4 Scout
98.3%
165
GPT-4.1 Nano
98.1%
166
Nova Premier 1.0
98.1%
167
Command R+ (08-2024)
98.1%
168
Qwen2.5 VL 72B Instruct
98.1%
169
DeepSeek V3.1
98.1%
170
Qwen3 Max
98.0%
171
Grok 3 Mini Beta
98.0%
172
Qwen2.5 VL 32B Instruct
98.0%
173
Qwen3 Coder Plus
98.0%
174
Qwen3 Coder 30B A3B Instruct
98.0%
175
Llama 3.1 70B Instruct
98.0%
176
ERNIE 4.5 VL 28B A3B
98.0%
177
Mistral Small 3
98.0%
178
GPT-4o-mini Search Preview
97.9%
179
Nova 2 Lite
97.9%
180
MiniMax M2
97.8%
181
Qwen3 VL 8B Thinking
97.8%
182
GPT-3.5 Turbo Instruct
97.8%
183
Claude 3 Haiku
97.7%
184
GPT-4 Turbo Preview
97.7%
185
Gemini 2.0 Flash Lite
97.6%
186
Kimi K2 0711
97.6%
187
Inflection 3 Productivity
97.6%
188
Llama 3.3 70B Instruct
97.6%
189
Qwen3 Coder Flash
97.6%
190
GPT-4o (2024-08-06)
97.5%
191
Olmo 3 7B Think
97.4%
192
GPT-4o
97.4%
193
Inflection 3 Pi
97.4%
194
Sonar
97.2%
195
KAT-Coder-Pro V1
97.2%
196
Trinity Large Preview
97.2%
197
Command R (08-2024)
97.1%
198
Qwen3 14B
97.0%
199
Phi 4
97.0%
200
Qwen-Turbo
97.0%
201
GLM 4.7 Flash
96.9%
202
Cogito V2 Preview Llama 405B
96.9%
203
DeepSeek V3.1 Nex N1
96.9%
204
Seed 1.6 Flash
96.8%
205
Hermes 4 70B
96.7%
206
Granite 4.0 Micro
96.6%
207
Free Models Router
96.5%
208
GPT-4 (older v0314)
96.5%
209
Gemini 2.5 Flash Image (Nano Banana)
96.5%
210
Cogito v2.1 671B
96.4%
211
MiniMax M1
96.4%
212
Cogito V2 Preview Llama 70B
96.3%
213
Grok Code Fast 1
96.3%
214
Llama 3.1 Nemotron 70B Instruct
96.2%
215
Ministral 3 3B 2512
96.2%
216
Nemotron Nano 12B 2 VL
96.2%
217
Qwen3 8B
96.2%
218
Cydonia 24B V4.1
96.1%
219
GPT-4
96.0%
220
ERNIE 4.5 21B A3B
96.0%
221
LFM2-8B-A1B
95.9%
222
Qwen3 VL 8B Instruct
95.6%
223
GLM 4 32B
95.6%
224
GLM 4.5 Air
95.6%
225
Mistral Nemo
95.5%
226
Ministral 8B
95.4%
227
Pixtral 12B
95.3%
228
MiniMax M2.1
95.2%
229
Jamba Mini 1.7
95.2%
230
Kimi Dev 72B
95.1%
231
Skyfall 36B V2
95.0%
232
Kimi K2 0905
95.0%
233
Aion-1.0-Mini
94.9%
234
MiniMax M2-her
94.8%
235
Olmo 3.1 32B Instruct
94.7%
236
Trinity Mini
94.6%
237
Hermes 4 405B
94.3%
238
Nova Lite 1.0
94.3%
239
Llama 3.3 Euryale 70B
94.2%
240
Mixtral 8x7B Instruct
94.1%
241
Gemma 3n 4B
94.1%
242
GPT-4 Turbo (older v1106)
93.9%
243
Molmo2 8B
93.8%
244
Mistral 7B Instruct
93.7%
245
Llama 3 Euryale 70B v2.1
93.3%
246
Kimi K2 0905 (exacto)
93.3%
247
Llama 3.1 70B Hanami x1
93.3%
248
Command R7B (12-2024)
93.2%
249
Gemma 2 27B
92.8%
250
Llama 3 8B Lunaris
92.8%
251
Mistral Tiny
92.8%
252
Llama 3.1 Euryale 70B v2.2
92.7%
253
Mistral 7B Instruct v0.3
92.3%
254
Lumimaid v0.2 8B
92.1%
255
Sonar Reasoning Pro
92.1%
256
Mistral 7B Instruct v0.2
92.1%
257
SorcererLM 8x22B
91.8%
258
Nova Micro 1.0
91.5%
259
Olmo 3 32B Think
90.4%
260
Codestral 2508
90.4%
261
Qwen2.5 7B Instruct
90.2%
262
Nemotron Nano 9B V2
90.0%
263
Gemma 2 9B
89.1%
264
Olmo 3.1 32B Think
89.0%
265
Olmo 3 7B Instruct
88.7%
266
Goliath 120B
87.7%
267
Qwen2.5-VL 7B Instruct
87.0%
268
Qwen2.5 Coder 32B Instruct
85.8%
269
Rnj 1 Instruct
85.2%
270
Llama 3 8B Instruct
84.2%
271
Hermes 2 Pro - Llama-3 8B
84.1%
272
Mistral 7B Instruct v0.1
84.0%
273
Llama 3.1 8B Instruct
81.6%
274
Llama 3.2 3B Instruct
81.0%
275
ReMM SLERP 13B
79.1%
276
Weaver (alpha)
79.0%
277
Hunyuan A13B Instruct
78.5%
278
Noromaid 20B
75.6%
279
Ministral 3B
74.6%
280
MythoMax 13B
72.5%
281
Rocinante 12B
72.0%
282
UnslopNemo 12B
68.3%
283
Hermes 3 70B Instruct
64.8%
284
Aion-RP 1.0 (8B)
58.3%
285
Llama 3.2 11B Vision Instruct
57.2%
286
Llama 3.2 1B Instruct
47.8%
287
Morph V3 Large
41.1%
288
Morph V3 Fast
32.9%
289
CodeLLaMa 7B Instruct Solidity
24.0%
290
Llemma 7b
22.7%
Media:95.3%
(290 modelos)
Menú de métricas
Coste total
Coste total en USD para evaluar todas las preguntas
1
LFM2-8B-A1B
$0.00
2
Mistral Nemo
$0.01
3
Ministral 3B
$0.01
4
Gemma 3n 4B
$0.01
5
Llama 3 8B Lunaris
$0.01
6
Gemma 2 9B
$0.01
7
Llama 3 8B Instruct
$0.01
8
Gemma 3 4B
$0.01
9
Granite 4.0 Micro
$0.01
10
Llama 3.2 3B Instruct
$0.01
11
MythoMax 13B
$0.01
12
Command R7B (12-2024)
$0.02
13
Ministral 8B
$0.02
14
Qwen2.5 7B Instruct
$0.02
15
GLM 4 32B
$0.02
16
Llama 3.1 8B Instruct
$0.02
17
Nova Micro 1.0
$0.02
18
Mistral Small 3
$0.02
19
Llama 3.2 1B Instruct
$0.02
20
Pixtral 12B
$0.02
21
Phi 4
$0.02
22
Voxtral Small 24B 2507
$0.02
23
Hermes 2 Pro - Llama-3 8B
$0.03
24
Gemma 3 12B
$0.03
25
Qwen-Turbo
$0.03
26
Mistral 7B Instruct v0.1
$0.03
27
Devstral Small 1.1
$0.03
28
Nova Lite 1.0
$0.03
29
Ministral 3 3B 2512
$0.03
30
Mistral Small 3.2 24B
$0.03
31
Rnj 1 Instruct
$0.04
32
Gemini 2.0 Flash Lite
$0.04
33
gpt-oss-120b (exacto)
$0.04
34
Gemma 3 27B
$0.04
35
ERNIE 4.5 21B A3B
$0.04
36
Mistral 7B Instruct v0.3
$0.04
37
Mistral 7B Instruct v0.2
$0.04
38
Mistral 7B Instruct
$0.04
39
Llama 3.2 11B Vision Instruct
$0.04
40
Trinity Mini
$0.04
41
Ministral 3 8B 2512
$0.04
42
Qwen2.5-VL 7B Instruct
$0.04
43
Molmo2 8B
$0.04
44
Lumimaid v0.2 8B
$0.04
45
GPT-4.1 Nano
$0.04
46
Gemini 2.0 Flash
$0.05
47
Olmo 3 7B Instruct
$0.05
48
Hermes 4 70B
$0.05
49
Qwen3 Coder 30B A3B Instruct
$0.05
50
gpt-oss-20b
$0.05
51
Mistral Tiny
$0.05
52
Nemotron Nano 9B V2
$0.05
53
Ministral 3 14B 2512
$0.06
54
Llama 4 Scout
$0.06
55
Qwen2.5 72B Instruct
$0.06
56
Saba
$0.06
57
Command R (08-2024)
$0.06
58
Jamba Mini 1.7
$0.06
59
Qwen3 14B
$0.06
60
Qwen3 30B A3B Instruct 2507
$0.07
61
gpt-oss-safeguard-20b
$0.07
62
UnslopNemo 12B
$0.07
63
Mistral Small 3.1 24B
$0.07
64
MiMo-V2-Flash
$0.07
65
Rocinante 12B
$0.08
66
DeepSeek V3.2 Exp
$0.08
67
Qwen3 8B
$0.08
68
KAT-Coder-Pro V1
$0.08
69
Llama 3.1 70B Instruct
$0.08
70
Hunyuan A13B Instruct
$0.08
71
DeepSeek V3.2
$0.08
72
Qwen2.5 Coder 32B Instruct
$0.08
73
GPT-4o Search Preview
$0.08
74
Gemini 2.5 Flash Lite
$0.09
75
Cydonia 24B V4.1
$0.09
76
Seed 1.6 Flash
$0.09
77
Gemma 2 27B
$0.09
78
gpt-oss-120b
$0.09
79
Gemini 2.5 Flash Lite Preview 09-2025
$0.09
80
Llama 3.3 70B Instruct
$0.09
81
Mistral Small Creative
$0.09
82
Qwen3 235B A22B Instruct 2507
$0.10
83
Mercury Coder
$0.10
84
Mercury
$0.10
85
Llama 3 70B Instruct
$0.10
86
Codestral 2508
$0.11
87
ReMM SLERP 13B
$0.11
88
Olmo 3.1 32B Instruct
$0.11
89
Mixtral 8x7B Instruct
$0.11
90
Llama 4 Maverick
$0.12
91
Qwen2.5 VL 72B Instruct
$0.12
92
Qwen3 32B
$0.12
93
DeepSeek V3 0324
$0.12
94
DeepSeek V3
$0.12
95
DeepSeek V3.1 Terminus (exacto)
$0.13
96
Qwen VL Plus
$0.13
97
Skyfall 36B V2
$0.13
98
Claude 3 Haiku
$0.13
99
GPT-4o-mini
$0.13
100
GPT-4o-mini (2024-07-18)
$0.13
101
ERNIE 4.5 300B A47B
$0.13
102
Grok 4 Fast
$0.13
103
Aion-1.0-Mini
$0.13
104
Llama 3.3 Nemotron Super 49B V1.5
$0.13
105
ERNIE 4.5 VL 28B A3B
$0.14
106
GPT-3.5 Turbo
$0.14
107
DeepSeek V3.1
$0.14
108
Grok 4.1 Fast
$0.14
109
Olmo 3 7B Think
$0.14
110
Qwen3 30B A3B Thinking 2507
$0.14
111
Qwen3 VL 30B A3B Instruct
$0.15
112
Tongyi DeepResearch 30B A3B
$0.15
113
DeepSeek V3.1 Terminus
$0.15
114
Nemotron 3 Nano 30B A3B
$0.16
115
Cogito V2 Preview Llama 70B
$0.16
116
Qwen2.5 VL 32B Instruct
$0.16
117
Hermes 3 405B Instruct
$0.16
118
ERNIE 4.5 21B A3B Thinking
$0.16
119
GPT-5 Nano
$0.17
120
Llama 3.3 Euryale 70B
$0.17
121
Qwen3 VL 235B A22B Instruct
$0.18
122
Llama 3.1 Euryale 70B v2.2
$0.18
123
Grok 3 Mini Beta
$0.18
124
Grok 3 Mini
$0.18
125
QwQ 32B
$0.18
126
Qwen3 VL 8B Instruct
$0.19
127
GLM 4.5 Air
$0.19
128
Devstral Medium
$0.19
129
GPT-4.1 Mini
$0.19
130
Aion-RP 1.0 (8B)
$0.19
131
DeepSeek V3.1 Nex N1
$0.20
132
Qwen3 Next 80B A3B Instruct
$0.20
133
MiniMax M2-her
$0.20
134
GPT-5.1-Codex-Mini
$0.20
135
Weaver (alpha)
$0.21
136
R1 Distill Qwen 32B
$0.22
137
Qwen3 Coder 480B A35B
$0.22
138
Mistral Medium 3
$0.22
139
Cogito v2.1 671B
$0.22
140
Qwen-Plus
$0.23
141
Qwen Plus 0728
$0.23
142
ERNIE 4.5 VL 424B A47B
$0.23
143
Mistral Large 3 2512
$0.23
144
Qwen3 235B A22B
$0.23
145
Qwen3 Coder 480B A35B (exacto)
$0.24
146
Nemotron Nano 12B 2 VL
$0.25
147
Qwen3 Coder Flash
$0.25
148
Llama 3.1 Nemotron Ultra 253B v1
$0.25
149
Qwen3 Coder Next
$0.26
150
R1 Distill Llama 70B
$0.26
151
MiniMax M2.1
$0.27
152
Llama 3 Euryale 70B v2.1
$0.28
153
Morph V3 Large
$0.28
154
Hermes 4 405B
$0.29
155
GPT-3.5 Turbo (older v0613)
$0.29
156
Llama 3.1 Nemotron 70B Instruct
$0.29
157
DeepSeek V3.2 Speciale
$0.29
158
Noromaid 20B
$0.30
159
Kimi K2 0711
$0.30
160
GPT-3.5 Turbo Instruct
$0.30
161
Qwen3 VL 32B Instruct
$0.30
162
GLM 4.7 Flash
$0.30
163
MiniMax M2
$0.31
164
Mistral Medium 3.1
$0.31
165
Kimi K2 0905
$0.32
166
Nova Pro 1.0
$0.32
167
Kimi Dev 72B
$0.33
168
Gemini 3 Flash Preview
$0.33
169
GLM 4.5V
$0.34
170
CodeLLaMa 7B Instruct Solidity
$0.34
171
GLM 4.6
$0.36
172
GLM 4.6V
$0.36
173
Olmo 3 32B Think
$0.38
174
Olmo 3.1 32B Think
$0.38
175
Qwen3 VL 30B A3B Thinking
$0.40
176
Claude 3.5 Haiku
$0.41
177
Grok Code Fast 1
$0.41
178
GPT-5 Mini
$0.41
179
Gemini 2.5 Flash
$0.48
180
MiniMax M1
$0.51
181
Relace Search
$0.51
182
Gemini 2.5 Flash Preview 09-2025
$0.52
183
Hermes 3 70B Instruct
$0.53
184
Nova 2 Lite
$0.55
185
Seed 1.6
$0.55
186
Qwen3 235B A22B Thinking 2507
$0.57
187
GLM 4.5
$0.58
188
Qwen VL Max
$0.58
189
Switchpoint Router
$0.59
190
GLM 4.6 (exacto)
$0.59
191
Gemini 2.5 Flash Image (Nano Banana)
$0.59
192
Cogito V2 Preview Llama 405B
$0.60
193
Step3
$0.60
194
GPT-5.1-Codex
$0.60
195
Mixtral 8x22B Instruct
$0.62
196
Llama 3.1 70B Hanami x1
$0.63
197
Llemma 7b
$0.63
198
GPT-5.1 Chat
$0.69
199
Qwen3 Next 80B A3B Thinking
$0.73
200
Qwen3 Coder Plus
$0.76
201
Kimi K2 0905 (exacto)
$0.77
202
Palmyra X5
$0.79
203
Mistral Large 2411
$0.80
204
R1
$0.81
205
GPT-5 Image Mini
$0.82
206
Claude Haiku 4.5
$0.83
207
Command A
$0.87
208
GPT-4.1
$0.89
209
Mistral Large
$0.90
210
R1 0528
$0.91
211
Pixtral Large 2411
$0.91
212
Qwen3 Max
$0.92
213
Mistral Large 2407
$0.92
214
Qwen-Max
$0.95
215
Command R+ (08-2024)
$0.95
216
Kimi K2 Thinking
$0.96
217
GPT-5 Codex
$0.96
218
Inflection 3 Productivity
$1.00
219
Inflection 3 Pi
$1.01
220
GPT-4o
$1.01
221
GPT-4o (2024-08-06)
$1.05
222
GPT-5 Chat
$1.08
223
GLM 4.7
$1.13
224
SorcererLM 8x22B
$1.13
225
Nova Premier 1.0
$1.18
226
Qwen3 VL 235B A22B Thinking
$1.19
227
Sonar
$1.27
228
o3 Mini High
$1.28
229
Goliath 120B
$1.28
230
o3 Mini
$1.29
231
Kimi K2.5
$1.29
232
o4 Mini
$1.30
233
Qwen3 VL 8B Thinking
$1.39
234
Morph V3 Fast
$1.42
235
GPT-4o (2024-11-20)
$1.46
236
Jamba Large 1.7
$1.62
237
GPT-5.2 Chat
$1.63
238
Qwen Plus 0728 (thinking)
$1.72
239
GPT-5.2-Codex
$1.81
240
GPT-4o (2024-05-13)
$1.90
241
GPT-5.1
$1.98
242
Aion-1.0
$2.03
243
GPT-5.2
$2.03
244
o4 Mini High
$2.14
245
o3
$2.17
246
GPT-5
$2.19
247
ChatGPT-4o
$2.20
248
Claude Sonnet 4
$2.21
249
GPT-5.1-Codex-Max
$2.37
250
Claude 3.7 Sonnet
$2.47
251
Claude Sonnet 4.5
$2.54
252
Grok 3
$2.62
253
Grok 3 Beta
$2.65
254
Sonar Pro
$3.20
255
Claude 3.5 Sonnet
$3.37
256
Sonar Reasoning Pro
$3.45
257
GPT-5 Image
$3.74
258
Auto Router
$4.17
259
GPT-4 Turbo
$4.17
260
Grok 4
$4.31
261
GPT-4 Turbo Preview
$4.38
262
Claude Opus 4.5
$4.62
263
Claude Opus 4.6
$4.85
264
Sonar Pro Search
$5.43
265
Nano Banana Pro (Gemini 3 Pro Image Preview)
$5.51
266
Gemini 2.5 Pro
$5.74
267
Gemini 2.5 Pro Preview 06-05
$5.77
268
Gemini 3 Pro Preview
$5.78
269
Gemini 2.5 Pro Preview 05-06
$5.87
270
Claude 3.7 Sonnet (thinking)
$7.19
271
GPT-4 (older v0314)
$7.63
272
GPT-4
$8.36
273
Claude Opus 4
$10.46
274
Claude Opus 4.1
$11.12
275
o3 Pro
$20.97
276
o1
$22.95
277
GPT-5.2 Pro
$24.52
278
o4 Mini Deep Research
$35.85
279
o3 Deep Research
$158.95
280
Sonar Deep Research
$235.83
281
o1-pro
$236.61
Total:$967.27
Media:$3.44
(281 modelos)
Menú de métricas
Tokens de razonamiento
Tokens utilizados en el proceso de razonamiento
1
GPT-5.1 Chat
7K
2
Auto Router
11K
3
GPT-5.1-Codex
18K
4
GPT-5.2 Chat
19K
5
DeepSeek V3.2
21K
6
DeepSeek V3.1 Terminus
24K
7
GPT-5.2 Pro
39K
8
GPT-5.2
40K
9
DeepSeek V3.2 Exp
45K
10
GPT-5.1-Codex-Mini
48K
11
GPT-5 Codex
53K
12
GLM 4.5
57K
13
GLM 4.5V
61K
14
GLM 4.6
66K
15
gpt-oss-120b
71K
16
GPT-5.1
75K
17
gpt-oss-120b (exacto)
76K
18
o3 Pro
78K
19
GPT-5.2-Codex
78K
20
o3
86K
21
o4 Mini
105K
22
o3 Mini High
107K
23
o3 Mini
109K
24
gpt-oss-20b
110K
25
Grok 4 Fast
118K
26
gpt-oss-safeguard-20b
120K
27
GPT-5 Mini
120K
28
GPT-5 Image Mini
125K
29
Nemotron Nano 9B V2
125K
30
Free Models Router
130K
31
MiniMax M1
131K
32
MiniMax M2.1
141K
33
R1 Distill Llama 70B
143K
34
GPT-5 Image
146K
35
GPT-5
147K
36
GLM 4.6 (exacto)
149K
37
Grok Code Fast 1
149K
38
o1
152K
39
Grok 4.1 Fast
153K
40
o1-pro
157K
41
R1 Distill Qwen 32B
160K
42
Grok 4
161K
43
Seed 1.6
166K
44
Seed 1.6 Flash
171K
45
Qwen3 32B
173K
46
Grok 3 Mini
173K
47
R1
174K
48
Grok 3 Mini Beta
175K
49
Qwen3 14B
178K
50
MiniMax M2
185K
51
GPT-5.1-Codex-Max
187K
52
Qwen3 VL 235B A22B Thinking
188K
53
Kimi Dev 72B
190K
54
Trinity Mini
198K
55
o4 Mini High
199K
56
R1 0528
208K
57
Qwen3 8B
210K
58
Step3
222K
59
Qwen3 235B A22B
224K
60
Kimi K2 Thinking
243K
61
Llama 3.3 Nemotron Super 49B V1.5
252K
62
Solar Pro 3
255K
63
Tongyi DeepResearch 30B A3B
256K
64
GLM 4.6V
257K
65
Qwen3 VL 30B A3B Thinking
260K
66
Qwen3 30B A3B Thinking 2507
270K
67
Claude 3.7 Sonnet (thinking)
281K
68
Nano Banana Pro (Gemini 3 Pro Image Preview)
282K
69
Kimi K2.5
283K
70
Qwen3 235B A22B Thinking 2507
287K
71
QwQ 32B
291K
72
Qwen Plus 0728 (thinking)
296K
73
Nemotron Nano 12B 2 VL
313K
74
Gemini 3 Pro Preview
322K
75
GPT-5 Nano
336K
76
DeepSeek V3.2 Speciale
363K
77
Gemini 2.5 Pro Preview 06-05
386K
78
Gemini 2.5 Pro
386K
79
Step 3.5 Flash
393K
80
Gemini 2.5 Pro Preview 05-06
394K
81
GLM 4.7
410K
82
ERNIE 4.5 21B A3B Thinking
417K
83
Qwen3 Next 80B A3B Thinking
476K
84
Qwen3 VL 8B Thinking
561K
85
Olmo 3 7B Think
583K
86
Nemotron 3 Nano 30B A3B
620K
87
GLM 4.7 Flash
625K
88
Olmo 3.1 32B Think
661K
89
Olmo 3 32B Think
663K
90
o4 Mini Deep Research
1.5M
91
o3 Deep Research
1.6M
92
Sonar Deep Research
68.4M
Total:90.1M
Media:979K
(92 modelos)
Menú de métricas
Tokens salientes
Tokens generados en las respuestas
1
Unknown
0
2
Gemma 2 27B
45K
3
Aion-1.0-Mini
47K
4
GPT-5.1-Codex
48K
5
Voxtral Small 24B 2507
52K
6
Mistral Nemo
52K
7
Lumimaid v0.2 8B
56K
8
GPT-5.1 Chat
56K
9
Ministral 3B
57K
10
Gemma 2 9B
59K
11
GPT-3.5 Turbo
59K
12
GPT-3.5 Turbo 16k
60K
13
Devstral Small 1.1
61K
14
Hermes 4 405B
62K
15
Hermes 3 405B Instruct
64K
16
Mistral Small 3.1 24B
64K
17
Ministral 8B
64K
18
Command A
65K
19
Nova Premier 1.0
66K
20
Nova Pro 1.0
69K
21
MythoMax 13B
69K
22
Llama 3 8B Lunaris
69K
23
Mistral Small 3
70K
24
Mistral 7B Instruct v0.3
71K
25
GPT-4o-mini
71K
26
Skyfall 36B V2
71K
27
Llama 3 70B Instruct
72K
28
GPT-4o-mini (2024-07-18)
72K
29
Command R+ (08-2024)
72K
30
Mistral 7B Instruct v0.2
72K
31
Mistral 7B Instruct v0.1
72K
32
Mistral Small 3.2 24B
72K
33
Saba
73K
34
Cogito V2 Preview Llama 405B
73K
35
Aion-RP 1.0 (8B)
73K
36
Mixtral 8x22B Instruct
73K
37
ReMM SLERP 13B
74K
38
Mistral 7B Instruct
75K
39
GPT-4o
76K
40
UnslopNemo 12B
76K
41
Inflection 3 Productivity
77K
42
Claude 3.5 Haiku
77K
43
Inflection 3 Pi
77K
44
Devstral Medium
78K
45
GPT-3.5 Turbo Instruct
78K
46
Command R7B (12-2024)
78K
47
Cogito v2.1 671B
78K
48
Mercury Coder
79K
49
GPT-4 (older v0314)
79K
50
Claude 3 Haiku
79K
51
GPT-4o (2024-08-06)
79K
52
Mercury
80K
53
KAT-Coder-Pro V1
80K
54
Kimi K2 0905
81K
55
Gemini 2.0 Flash
81K
56
Command R (08-2024)
81K
57
GPT-4.1 Nano
83K
58
DeepSeek V3
83K
59
Cogito V2 Preview Llama 70B
83K
60
Nova Lite 1.0
83K
61
Hermes 4 70B
84K
62
DeepSeek V3 0324
84K
63
GPT-5 Codex
84K
64
Mixtral 8x7B Instruct
84K
65
Pixtral 12B
86K
66
Gemini 2.0 Flash Lite
86K
67
GPT-4.1
86K
68
Llama 3.1 70B Instruct
86K
69
Hermes 2 Pro - Llama-3 8B
86K
70
Codestral 2508
87K
71
Claude 3.5 Sonnet
87K
72
Llama 3 Euryale 70B v2.1
88K
73
Gemma 3 12B
89K
74
Mistral Medium 3
90K
75
GPT-5.1-Codex-Mini
90K
76
Devstral 2 2512
91K
77
GPT-4
91K
78
Sonar Pro Search
91K
79
Molmo2 8B
91K
80
Morph V3 Large
92K
81
Mistral Tiny
92K
82
Gemini 3 Flash Preview
92K
83
GPT-4o (2024-05-13)
92K
84
Noromaid 20B
92K
85
Gemma 3 4B
92K
86
Kimi K2 0905 (exacto)
93K
87
GPT-4o Search Preview
93K
88
Mistral Large 2411
93K
89
ERNIE 4.5 300B A47B
93K
90
GPT-4o-mini Search Preview
94K
91
Cydonia 24B V4.1
94K
92
Gemma 3 27B
95K
93
GPT-4.1 Mini
95K
94
GPT-5 Chat
96K
95
GLM 4 32B
96K
96
GPT-4 Turbo (older v1106)
98K
97
Pixtral Large 2411
100K
98
Trinity Large Preview
100K
99
GPT-3.5 Turbo (older v0613)
100K
100
Llama 3 8B Instruct
100K
101
Granite 4.0 Micro
100K
102
Llama 3.2 1B Instruct
101K
103
GPT-4 Turbo
102K
104
Goliath 120B
103K
105
Kimi K2 0711
103K
106
Llama 4 Scout
104K
107
LFM2-8B-A1B
104K
108
GPT-5.2 Chat
104K
109
Qwen2.5-VL 7B Instruct
104K
110
Jamba Mini 1.7
105K
111
Llama 3.3 70B Instruct
105K
112
ERNIE 4.5 21B A3B
106K
113
Llama 3.1 70B Hanami x1
107K
114
Sonar Pro
108K
115
Qwen2.5 VL 72B Instruct
108K
116
Llama 3.1 Nemotron Ultra 253B v1
108K
117
Llama 4 Maverick
110K
118
Sonar
110K
119
Qwen3 VL 235B A22B Instruct
111K
120
Qwen-Turbo
111K
121
Weaver (alpha)
111K
122
ChatGPT-4o
112K
123
GPT-4 Turbo Preview
114K
124
Hunyuan A13B Instruct
114K
125
Claude Opus 4
115K
126
Nova Micro 1.0
115K
127
Qwen2.5 72B Instruct
115K
128
Llama 3.1 Euryale 70B v2.2
117K
129
Palmyra X5
117K
130
GPT-5.2-Codex
118K
131
Gemma 3n 4B
119K
132
Mistral Large
119K
133
Qwen2.5 Coder 32B Instruct
121K
134
GPT-4o (2024-11-20)
121K
135
Qwen2.5 7B Instruct
121K
136
Mistral Large 3 2512
121K
137
SorcererLM 8x22B
121K
138
Claude Sonnet 4
122K
139
DeepSeek V3.2
123K
140
Mistral Large 2407
123K
141
Claude Opus 4.1
123K
142
Qwen3 Coder 480B A35B (exacto)
123K
143
Qwen-Max
124K
144
Rocinante 12B
125K
145
Qwen3 Coder 480B A35B
127K
146
Llama 3.3 Euryale 70B
128K
147
DeepSeek V3.1
128K
148
Phi 4
130K
149
Rnj 1 Instruct
131K
150
DeepSeek V3.1 Terminus (exacto)
132K
151
Qwen3 Coder Plus
133K
152
GPT-5.2
133K
153
Qwen3 Max
133K
154
GPT-5.2 Pro
134K
155
Mistral Medium 3.1
136K
156
Relace Search
137K
157
MiniMax M2-her
138K
158
DeepSeek V3.1 Nex N1
139K
159
Claude 3.7 Sonnet
140K
160
DeepSeek V3.2 Exp
141K
161
Claude Haiku 4.5
141K
162
ERNIE 4.5 VL 424B A47B
142K
163
Qwen3 Coder 30B A3B Instruct
144K
164
Llama 3.1 Nemotron 70B Instruct
144K
165
Claude Sonnet 4.5
144K
166
DeepSeek V3.1 Terminus
146K
167
Olmo 3.1 32B Instruct
147K
168
Qwen3 Coder Flash
148K
169
Qwen VL Max
149K
170
Qwen3 Next 80B A3B Instruct
150K
171
gpt-oss-120b
151K
172
Switchpoint Router
152K
173
GLM 4.6
152K
174
Ministral 3 14B 2512
153K
175
gpt-oss-120b (exacto)
153K
176
Gemini 2.5 Flash Image (Nano Banana)
153K
177
Qwen3 235B A22B Instruct 2507
154K
178
GLM 4.5V
155K
179
Qwen VL Plus
157K
180
Qwen-Plus
158K
181
o3 Pro
158K
182
Claude Opus 4.5
160K
183
o3
161K
184
Qwen Plus 0728
161K
185
o3 Mini High
161K
186
o3 Mini
161K
187
Auto Router
164K
188
Qwen3 VL 32B Instruct
164K
189
Grok 3 Beta
164K
190
Grok 3
165K
191
o4 Mini
165K
192
Ministral 3 8B 2512
168K
193
R1 Distill Llama 70B
169K
194
Claude Opus 4.6
169K
195
Qwen3 30B A3B Instruct 2507
172K
196
Ministral 3 3B 2512
173K
197
Jamba Large 1.7
176K
198
Olmo 3 7B Instruct
177K
199
Gemini 2.5 Flash
178K
200
Llama 3.2 3B Instruct
179K
201
Gemini 2.5 Flash Lite
181K
202
GPT-5.1
185K
203
MiMo-V2-Flash
187K
204
gpt-oss-20b
189K
205
GPT-5 Mini
194K
206
Gemini 2.5 Flash Preview 09-2025
196K
207
Qwen3 VL 30B A3B Instruct
197K
208
R1 Distill Qwen 32B
198K
209
GPT-5 Image Mini
199K
210
Gemini 2.5 Flash Lite Preview 09-2025
201K
211
gpt-oss-safeguard-20b
202K
212
GPT-5 Image
202K
213
Free Models Router
203K
214
MiMo-V2-Flash
204K
215
CodeLLaMa 7B Instruct Solidity
205K
216
Aion-1.0
206K
217
GPT-5
206K
218
Llama 3.2 11B Vision Instruct
207K
219
o1
208K
220
Nova 2 Lite
208K
221
MiniMax M1
211K
222
ERNIE 4.5 VL 28B A3B
211K
223
MiniMax M2.1
212K
224
Qwen2.5 VL 32B Instruct
213K
225
o1-pro
215K
226
GLM 4.5 Air
216K
227
GPT-5.1-Codex-Max
225K
228
Grok 4 Fast
228K
229
Qwen3 Coder Next
237K
230
Qwen3 14B
238K
231
Trinity Mini
241K
232
Grok 4.1 Fast
242K
233
Sonar Reasoning Pro
247K
234
GLM 4.5
248K
235
Nemotron Nano 9B V2
254K
236
Seed 1.6 Flash
255K
237
GLM 4.6 (exacto)
256K
238
MiniMax M2
256K
239
Qwen3 32B
258K
240
Llama 3.1 8B Instruct
258K
241
Kimi Dev 72B
259K
242
Seed 1.6
261K
243
o4 Mini High
262K
244
Grok Code Fast 1
264K
245
Grok 4
265K
246
Qwen3 VL 235B A22B Thinking
280K
247
Mistral Small Creative
282K
248
Qwen3 235B A22B
287K
249
Qwen3 8B
290K
250
R1
296K
251
Qwen3 VL 8B Instruct
296K
252
Llama 3.3 Nemotron Super 49B V1.5
311K
253
Grok 3 Mini
329K
254
Grok 3 Mini Beta
333K
255
Tongyi DeepResearch 30B A3B
336K
256
R1 0528
338K
257
Qwen3 30B A3B Thinking 2507
343K
258
Nemotron Nano 12B 2 VL
360K
259
Kimi K2 Thinking
366K
260
QwQ 32B
371K
261
Qwen3 VL 30B A3B Thinking
371K
262
GLM 4.6V
371K
263
Step3
379K
264
Solar Pro 3
399K
265
Qwen3 235B A22B Thinking 2507
400K
266
GPT-5 Nano
407K
267
Qwen Plus 0728 (thinking)
420K
268
Kimi K2.5
437K
269
DeepSeek V3.2 Speciale
438K
270
Nano Banana Pro (Gemini 3 Pro Image Preview)
443K
271
Llemma 7b
444K
272
Claude 3.7 Sonnet (thinking)
453K
273
Gemini 3 Pro Preview
463K
274
Step 3.5 Flash
515K
275
GLM 4.7
534K
276
Qwen3 Next 80B A3B Thinking
555K
277
ERNIE 4.5 21B A3B Thinking
559K
278
Gemini 2.5 Pro
562K
279
Gemini 2.5 Pro Preview 06-05
562K
280
Gemini 2.5 Pro Preview 05-06
572K
281
Nemotron 3 Nano 30B A3B
634K
282
Olmo 3 7B Think
647K
283
Qwen3 VL 8B Thinking
653K
284
Olmo 3 32B Think
728K
285
GLM 4.7 Flash
729K
286
Olmo 3.1 32B Think
729K
287
Morph V3 Fast
1.1M
288
o4 Mini Deep Research
1.6M
289
Hermes 3 70B Instruct
1.7M
290
o3 Deep Research
1.7M
291
Sonar Deep Research
68.8M
Total:124.4M
Media:427K
(291 modelos)