Ranking de MIR 2025
25 de enero de 2025
210preguntes
4anul·lades
Comparar amb:
Anar a mètrica:
Menú de mètriques
Netes obtingudes
Puntuació MIR: (3 × encerts - errors) / 3
1
Gemini 3 Flash Preview
190.66 pts
2
GPT-5.2-Codex
189.66 pts
3
GPT-5 Codex
189.33 pts
4
o3 Pro
189.33 pts
5
GPT-5.2 Chat
188.66 pts
6
GPT-5.2 Pro
188.66 pts
7
GPT-5.1 Chat
188.33 pts
8
GPT-5 Image
188.33 pts
9
GPT-5 Mini
188.00 pts
10
GPT-5.2
188.00 pts
11
GPT-5.1-Codex
187.00 pts
12
GPT-5
187.00 pts
13
GPT-5.1
186.66 pts
14
GPT-5.1-Codex-Max
186.66 pts
15
Gemini 3 Pro Preview
185.66 pts
16
Nano Banana Pro (Gemini 3 Pro Image Preview)
185.33 pts
17
Gemini 2.5 Pro Preview 05-06
185.33 pts
18
o3
184.66 pts
19
Gemini 2.5 Pro
184.33 pts
20
Claude Opus 4.6
184.00 pts
21
o4 Mini Deep Research
184.00 pts
22
GPT-5 Image Mini
183.66 pts
23
Gemini 2.5 Pro Preview 06-05
182.66 pts
24
o3 Deep Research
182.66 pts
25
Sonar Deep Research
182.66 pts
26
o4 Mini High
181.66 pts
27
o1-pro
181.33 pts
28
Gemini 2.5 Flash
181.00 pts
29
Grok 4.1 Fast
180.33 pts
30
Qwen3 235B A22B Thinking 2507
180.33 pts
31
Kimi K2.5
180.33 pts
32
Grok 4
180.33 pts
33
GPT-5.1-Codex-Mini
180.00 pts
34
o4 Mini
180.00 pts
35
Auto Router
180.00 pts
36
Claude Opus 4.5
180.00 pts
37
Qwen3 235B A22B
179.00 pts
38
GLM 4.7
179.00 pts
39
Qwen Plus 0728 (thinking)
179.00 pts
40
Claude 3.7 Sonnet
179.00 pts
41
Claude 3.7 Sonnet (thinking)
179.00 pts
42
Grok 4 Fast
178.66 pts
43
Aion-1.0
178.66 pts
44
Claude Sonnet 4
178.66 pts
45
o1
178.66 pts
46
Llama 4 Maverick
178.33 pts
47
GLM 4.5
177.00 pts
48
gpt-oss-120b
176.66 pts
49
GPT-5 Chat
176.66 pts
50
Gemini 2.5 Flash Preview 09-2025
176.33 pts
51
Claude Sonnet 4.5
176.00 pts
52
Grok 3 Beta
175.33 pts
53
R1 0528
174.66 pts
54
Claude Opus 4
174.66 pts
55
Claude 3.5 Sonnet
174.00 pts
56
Gemini 2.5 Flash Image (Nano Banana)
173.66 pts
57
Step 3.5 Flash
173.33 pts
58
DeepSeek V3.2 Exp
173.00 pts
59
GLM 4.6
173.00 pts
60
Grok 3
173.00 pts
61
Switchpoint Router
172.66 pts
62
Seed 1.6
172.66 pts
63
Qwen-Plus
172.33 pts
64
Qwen3 Max
172.33 pts
65
Claude Opus 4.1
172.33 pts
66
Qwen3 VL 30B A3B Thinking
172.00 pts
67
Qwen3 Next 80B A3B Thinking
172.00 pts
68
DeepSeek V3.1 Terminus (exacto)
171.66 pts
69
DeepSeek V3.2 Speciale
171.66 pts
70
R1
171.66 pts
71
Llama 3.3 Nemotron Super 49B V1.5
171.33 pts
72
Qwen3 VL 235B A22B Thinking
171.33 pts
73
Qwen Plus 0728
171.00 pts
74
Mistral Large
171.00 pts
75
GPT-4.1
171.00 pts
76
Mistral Large 3 2512
170.66 pts
77
ChatGPT-4o
170.66 pts
78
Mistral Medium 3
170.33 pts
79
GPT-4.1 Mini
169.66 pts
80
GLM 4.6 (exacto)
169.33 pts
81
Sonar Pro Search
169.33 pts
82
gpt-oss-120b (exacto)
168.66 pts
83
Grok 3 Mini
168.66 pts
84
Kimi K2 Thinking
168.66 pts
85
Qwen3 Coder Plus
168.33 pts
86
Mistral Large 2407
168.33 pts
87
o3 Mini High
168.33 pts
88
Nova Premier 1.0
168.00 pts
89
Qwen3 32B
167.66 pts
90
Qwen3 Coder Next
167.66 pts
91
GPT-4o (2024-11-20)
167.66 pts
92
GPT-5 Nano
167.33 pts
93
DeepSeek V3 0324
167.00 pts
94
DeepSeek V3.1
166.66 pts
95
Grok Code Fast 1
166.66 pts
96
Qwen VL Max
166.66 pts
97
o3 Mini
166.66 pts
98
DeepSeek V3.1 Terminus
166.00 pts
99
MiniMax M2
166.00 pts
100
Mistral Medium 3.1
165.66 pts
101
GPT-4o (2024-05-13)
165.66 pts
Millor humà
165.66 pts
102
Qwen3 Next 80B A3B Instruct
165.33 pts
103
GPT-4
165.33 pts
104
Pixtral Large 2411
165.00 pts
105
Qwen3 235B A22B Instruct 2507
164.66 pts
106
Grok 3 Mini Beta
164.66 pts
107
Qwen3 VL 235B A22B Instruct
164.33 pts
108
Kimi K2 0711
164.33 pts
109
Palmyra X5
164.33 pts
110
Gemini 2.0 Flash
164.00 pts
111
DeepSeek V3.2
163.66 pts
112
DeepSeek V3.1 Nex N1
163.66 pts
113
Jamba Large 1.7
163.66 pts
114
Devstral 2 2512
163.33 pts
115
Gemini 2.5 Flash Lite Preview 09-2025
162.66 pts
116
GPT-4o (2024-08-06)
162.66 pts
117
Kimi K2 0905
162.33 pts
118
GPT-4 Turbo Preview
162.33 pts
119
Tongyi DeepResearch 30B A3B
162.00 pts
120
GPT-3.5 Turbo (older v0613)
162.00 pts
121
Claude Haiku 4.5
162.00 pts
122
Qwen3 Coder 480B A35B (exacto)
161.66 pts
123
GPT-4o
161.66 pts
124
Qwen3 VL 32B Instruct
161.00 pts
125
DeepSeek V3
160.66 pts
126
Cogito v2.1 671B
160.66 pts
127
gpt-oss-safeguard-20b
160.33 pts
128
Qwen3 30B A3B Thinking 2507
160.33 pts
129
KAT-Coder-Pro V1
160.00 pts
130
GPT-4 Turbo (older v1106)
159.66 pts
131
Mistral Small Creative
159.33 pts
132
gpt-oss-20b
159.00 pts
133
Gemini 2.5 Flash Lite
159.00 pts
134
Qwen3 Coder 480B A35B
159.00 pts
135
GLM 4.6V
159.00 pts
136
GPT-4o Search Preview
158.66 pts
137
Nemotron 3 Nano 30B A3B
158.00 pts
138
Step3
157.66 pts
139
Aion-1.0-Mini
157.33 pts
140
Sonar
156.66 pts
141
GPT-4 Turbo
156.66 pts
142
Trinity Large Preview
156.33 pts
143
Nova Pro 1.0
156.00 pts
144
Kimi K2 0905 (exacto)
155.33 pts
145
Command A
155.33 pts
146
Qwen3 30B A3B Instruct 2507
155.00 pts
147
Qwen3 VL 30B A3B Instruct
155.00 pts
148
QwQ 32B
155.00 pts
149
Mistral Large 2411
155.00 pts
150
ERNIE 4.5 VL 424B A47B
154.66 pts
151
Qwen3 VL 8B Thinking
154.66 pts
152
Sonar Pro
154.33 pts
153
Cogito V2 Preview Llama 405B
153.66 pts
154
Qwen3 14B
153.33 pts
155
Devstral Medium
153.33 pts
156
GLM 4.5V
153.33 pts
157
Llama 4 Scout
153.00 pts
158
Qwen2.5 VL 72B Instruct
152.66 pts
159
Cogito V2 Preview Llama 70B
152.66 pts
160
Llama 3.1 Nemotron Ultra 253B v1
152.66 pts
161
Sonar Reasoning Pro
152.66 pts
162
R1 Distill Llama 70B
152.33 pts
163
MiniMax M2.1
152.33 pts
164
Mistral Small 3.2 24B
152.00 pts
165
Mistral Small 3.1 24B
151.33 pts
166
MiMo-V2-Flash
151.00 pts
167
Seed 1.6 Flash
151.00 pts
168
Hermes 3 405B Instruct
150.66 pts
169
Hermes 4 405B
150.00 pts
170
Solar Pro 3
149.33 pts
171
Mercury Coder
148.66 pts
172
Qwen-Max
148.66 pts
173
MiMo-V2-Flash
148.33 pts
174
Llama 3.3 70B Instruct
148.33 pts
175
ERNIE 4.5 300B A47B
148.33 pts
176
GPT-4 (older v0314)
148.33 pts
177
Gemini 2.0 Flash Lite
147.66 pts
178
Llama 3.1 70B Instruct
147.66 pts
179
Mercury
147.33 pts
180
Qwen2.5 72B Instruct
147.00 pts
181
GLM 4 32B
146.33 pts
182
Voxtral Small 24B 2507
146.33 pts
183
Llama 3.1 Nemotron 70B Instruct
146.33 pts
184
Ministral 3 8B 2512
145.33 pts
185
Saba
145.33 pts
186
GLM 4.5 Air
143.66 pts
187
MiniMax M1
143.33 pts
188
Mixtral 8x22B Instruct
143.33 pts
189
GPT-4o-mini (2024-07-18)
142.33 pts
190
Nova 2 Lite
141.66 pts
191
GPT-4o-mini Search Preview
141.00 pts
192
Llama 3.3 Euryale 70B
140.66 pts
193
Cydonia 24B V4.1
140.33 pts
194
GPT-4o-mini
140.33 pts
195
Qwen-Turbo
139.66 pts
196
Ministral 3 14B 2512
139.66 pts
197
Inflection 3 Pi
139.00 pts
198
Mistral Small 3
138.66 pts
199
Devstral Small 1.1
138.66 pts
200
Nemotron Nano 12B 2 VL
137.66 pts
201
Hermes 4 70B
137.00 pts
202
Qwen VL Plus
136.33 pts
203
MiniMax M2-her
136.33 pts
204
Kimi Dev 72B
136.33 pts
205
Qwen3 8B
136.00 pts
206
Qwen3 Coder Flash
136.00 pts
207
Nemotron Nano 9B V2
134.66 pts
208
Qwen2.5 VL 32B Instruct
134.66 pts
209
Relace Search
134.66 pts
210
Qwen3 Coder 30B A3B Instruct
134.00 pts
211
Inflection 3 Productivity
134.00 pts
212
Skyfall 36B V2
132.66 pts
213
GPT-4.1 Nano
131.00 pts
214
Free Models Router
130.33 pts
215
Claude 3.5 Haiku
129.00 pts
216
Llama 3.1 70B Hanami x1
129.00 pts
217
Qwen3 VL 8B Instruct
128.66 pts
218
GLM 4.7 Flash
125.33 pts
219
Olmo 3.1 32B Think
125.33 pts
220
Olmo 3 32B Think
123.66 pts
221
R1 Distill Qwen 32B
123.33 pts
222
Gemma 3 27B
122.66 pts
223
Gemma 3 12B
119.33 pts
224
Llama 3 70B Instruct
118.66 pts
225
SorcererLM 8x22B
118.66 pts
226
Llama 3.1 Euryale 70B v2.2
118.00 pts
227
Trinity Mini
114.00 pts
228
Nova Lite 1.0
113.00 pts
229
Claude 3 Haiku
111.66 pts
230
ERNIE 4.5 21B A3B Thinking
111.00 pts
231
Gemma 2 27B
108.00 pts
232
Nova Micro 1.0
106.33 pts
233
ERNIE 4.5 VL 28B A3B
105.66 pts
234
ERNIE 4.5 21B A3B
102.66 pts
235
Phi 4
101.00 pts
236
Command R+ (08-2024)
100.66 pts
237
Llama 3 Euryale 70B v2.1
100.00 pts
238
Mixtral 8x7B Instruct
99.00 pts
239
Command R (08-2024)
93.66 pts
240
GPT-3.5 Turbo 16k
93.33 pts
241
Qwen2.5 Coder 32B Instruct
90.66 pts
242
Jamba Mini 1.7
89.33 pts
243
Ministral 3 3B 2512
88.00 pts
244
Gemma 2 9B
84.66 pts
245
Gemma 3n 4B
82.66 pts
246
Pixtral 12B
80.66 pts
247
GPT-3.5 Turbo
80.33 pts
248
Mistral Nemo
79.00 pts
249
Molmo2 8B
76.33 pts
250
Olmo 3.1 32B Instruct
75.33 pts
251
Ministral 8B
74.66 pts
252
GPT-3.5 Turbo Instruct
74.33 pts
253
Hunyuan A13B Instruct
72.66 pts
254
Goliath 120B
71.33 pts
255
LFM2-8B-A1B
70.00 pts
256
Hermes 3 70B Instruct
70.00 pts
257
Codestral 2508
69.66 pts
258
Qwen2.5 7B Instruct
68.66 pts
259
Olmo 3 7B Think
62.66 pts
260
Qwen2.5-VL 7B Instruct
59.66 pts
261
Llama 3 8B Lunaris
56.33 pts
262
Llama 3.1 8B Instruct
52.33 pts
263
Gemma 3 4B
51.00 pts
264
Mistral 7B Instruct v0.3
49.33 pts
265
Mistral 7B Instruct v0.2
49.33 pts
266
Mistral Tiny
49.33 pts
267
Granite 4.0 Micro
49.00 pts
268
Mistral 7B Instruct
48.66 pts
269
Rocinante 12B
43.00 pts
270
Hermes 2 Pro - Llama-3 8B
42.66 pts
271
Command R7B (12-2024)
38.66 pts
272
Llama 3 8B Instruct
38.33 pts
273
Ministral 3B
35.66 pts
274
UnslopNemo 12B
35.33 pts
275
Mistral 7B Instruct v0.1
34.00 pts
276
Llama 3.2 11B Vision Instruct
29.00 pts
277
Llama 3.2 3B Instruct
27.66 pts
278
Lumimaid v0.2 8B
26.33 pts
279
MythoMax 13B
24.33 pts
280
Olmo 3 7B Instruct
23.66 pts
281
Aion-RP 1.0 (8B)
23.66 pts
282
Noromaid 20B
19.33 pts
283
Rnj 1 Instruct
19.00 pts
284
ReMM SLERP 13B
17.33 pts
285
Weaver (alpha)
12.00 pts
286
Morph V3 Large
8.00 pts
287
Llama 3.2 1B Instruct
6.66 pts
288
Llemma 7b
3.33 pts
289
Morph V3 Fast
1.66 pts
290
CodeLLaMa 7B Instruct Solidity
0.00 pts
Mitjana:138.99 pts
(290 modelos)
Menú de mètriques
Encerts obtinguts
Nombre total de respostes correctes
1
Gemini 3 Flash Preview
193
2
GPT-5.2-Codex
192
3
GPT-5 Codex
192
4
o3 Pro
192
5
GPT-5.2 Chat
191
6
GPT-5.2 Pro
191
7
GPT-5.1 Chat
191
8
GPT-5 Image
191
9
GPT-5 Mini
191
10
GPT-5.2
191
11
GPT-5.1-Codex
190
12
GPT-5
190
13
GPT-5.1
190
14
GPT-5.1-Codex-Max
190
15
Gemini 3 Pro Preview
189
16
Nano Banana Pro (Gemini 3 Pro Image Preview)
189
17
Gemini 2.5 Pro Preview 05-06
189
18
o3
188
19
Gemini 2.5 Pro
188
20
Claude Opus 4.6
188
21
o4 Mini Deep Research
188
22
GPT-5 Image Mini
187
23
Gemini 2.5 Pro Preview 06-05
187
24
o3 Deep Research
187
25
Sonar Deep Research
187
26
o4 Mini High
186
27
o1-pro
186
28
Gemini 2.5 Flash
185
29
Grok 4.1 Fast
185
30
Qwen3 235B A22B Thinking 2507
185
31
Kimi K2.5
185
32
Grok 4
185
33
GPT-5.1-Codex-Mini
185
34
o4 Mini
185
35
Auto Router
185
36
Claude Opus 4.5
185
37
Qwen3 235B A22B
184
38
GLM 4.7
184
39
Qwen Plus 0728 (thinking)
184
40
Claude 3.7 Sonnet (thinking)
184
41
Grok 4 Fast
184
42
Aion-1.0
184
43
Claude Sonnet 4
184
44
o1
184
45
Claude 3.7 Sonnet
183
46
Llama 4 Maverick
183
47
GLM 4.5
182
48
gpt-oss-120b
182
49
GPT-5 Chat
182
50
Gemini 2.5 Flash Preview 09-2025
182
51
Claude Sonnet 4.5
182
52
Grok 3 Beta
181
53
R1 0528
181
54
Claude Opus 4
181
55
Claude 3.5 Sonnet
180
56
Gemini 2.5 Flash Image (Nano Banana)
179
57
Step 3.5 Flash
179
58
DeepSeek V3.2 Exp
179
59
GLM 4.6
179
60
Grok 3
179
61
Switchpoint Router
179
62
Seed 1.6
179
63
Qwen-Plus
179
64
Claude Opus 4.1
179
65
Qwen3 VL 30B A3B Thinking
179
66
Qwen3 Max
178
67
Qwen3 Next 80B A3B Thinking
178
68
DeepSeek V3.1 Terminus (exacto)
178
69
R1
178
70
Llama 3.3 Nemotron Super 49B V1.5
178
71
Qwen3 VL 235B A22B Thinking
178
72
Qwen Plus 0728
178
73
Mistral Large
178
74
GPT-4.1
178
75
Mistral Large 3 2512
178
76
ChatGPT-4o
178
77
Mistral Medium 3
177
78
GPT-4.1 Mini
177
79
DeepSeek V3.2 Speciale
176
80
GLM 4.6 (exacto)
176
81
gpt-oss-120b (exacto)
176
82
Mistral Large 2407
176
83
o3 Mini High
176
84
Nova Premier 1.0
176
85
Sonar Pro Search
175
86
Grok 3 Mini
175
87
Qwen3 Coder Plus
175
88
Qwen3 32B
175
89
Qwen3 Coder Next
175
90
GPT-4o (2024-11-20)
175
91
GPT-5 Nano
175
92
DeepSeek V3 0324
175
93
o3 Mini
175
94
Kimi K2 Thinking
174
95
DeepSeek V3.1
174
96
Grok Code Fast 1
174
97
Qwen VL Max
174
98
DeepSeek V3.1 Terminus
174
99
MiniMax M2
174
100
Mistral Medium 3.1
174
101
GPT-4o (2024-05-13)
174
102
Qwen3 Next 80B A3B Instruct
174
Millor humà
174
103
GPT-4
173
104
Pixtral Large 2411
173
105
Qwen3 235B A22B Instruct 2507
173
106
Qwen3 VL 235B A22B Instruct
173
107
Palmyra X5
173
108
Grok 3 Mini Beta
172
109
Kimi K2 0711
172
110
Gemini 2.0 Flash
172
111
DeepSeek V3.2
172
112
Jamba Large 1.7
172
113
Devstral 2 2512
172
114
Gemini 2.5 Flash Lite Preview 09-2025
172
115
DeepSeek V3.1 Nex N1
171
116
GPT-4 Turbo Preview
171
117
Tongyi DeepResearch 30B A3B
171
118
GPT-3.5 Turbo (older v0613)
171
119
Claude Haiku 4.5
171
120
Qwen3 Coder 480B A35B (exacto)
171
121
GPT-4o (2024-08-06)
170
122
Qwen3 VL 32B Instruct
170
123
DeepSeek V3
170
124
gpt-oss-safeguard-20b
170
125
KAT-Coder-Pro V1
170
126
GPT-4o
169
127
Qwen3 30B A3B Thinking 2507
169
128
Mistral Small Creative
169
129
gpt-oss-20b
169
130
Gemini 2.5 Flash Lite
169
131
Qwen3 Coder 480B A35B
169
132
GLM 4.6V
169
133
Kimi K2 0905
168
134
Cogito v2.1 671B
168
135
Nemotron 3 Nano 30B A3B
168
136
Step3
168
137
GPT-4 Turbo (older v1106)
167
138
GPT-4o Search Preview
167
139
Aion-1.0-Mini
167
140
Sonar
167
141
GPT-4 Turbo
167
142
Trinity Large Preview
166
143
Nova Pro 1.0
166
144
Command A
166
145
Qwen3 30B A3B Instruct 2507
166
146
Qwen3 VL 30B A3B Instruct
166
147
QwQ 32B
166
148
Mistral Large 2411
166
149
ERNIE 4.5 VL 424B A47B
166
150
Qwen3 VL 8B Thinking
166
151
Sonar Pro
165
152
GLM 4.5V
165
153
Qwen3 14B
164
154
Devstral Medium
164
155
Llama 4 Scout
164
156
Qwen2.5 VL 72B Instruct
164
157
Llama 3.1 Nemotron Ultra 253B v1
164
158
Cogito V2 Preview Llama 405B
163
159
Cogito V2 Preview Llama 70B
163
160
R1 Distill Llama 70B
163
161
Mistral Small 3.2 24B
163
162
Mistral Small 3.1 24B
163
163
MiMo-V2-Flash
163
164
Seed 1.6 Flash
163
165
Kimi K2 0905 (exacto)
162
166
Sonar Reasoning Pro
162
167
MiniMax M2.1
161
168
Hermes 4 405B
161
169
Mercury Coder
161
170
Qwen-Max
161
171
ERNIE 4.5 300B A47B
161
172
Hermes 3 405B Instruct
160
173
MiMo-V2-Flash
160
174
GPT-4 (older v0314)
160
175
Gemini 2.0 Flash Lite
160
176
Llama 3.3 70B Instruct
159
177
Llama 3.1 70B Instruct
159
178
Mercury
159
179
GLM 4 32B
159
180
Voxtral Small 24B 2507
159
181
Ministral 3 8B 2512
159
182
Qwen2.5 72B Instruct
158
183
Llama 3.1 Nemotron 70B Instruct
158
184
Saba
158
185
Solar Pro 3
157
186
MiniMax M1
156
187
Mixtral 8x22B Instruct
156
188
GPT-4o-mini (2024-07-18)
156
189
Nova 2 Lite
155
190
GPT-4o-mini Search Preview
155
191
GPT-4o-mini
155
192
GLM 4.5 Air
154
193
Ministral 3 14B 2512
154
194
Cydonia 24B V4.1
153
195
Qwen-Turbo
153
196
Inflection 3 Pi
153
197
Llama 3.3 Euryale 70B
152
198
Mistral Small 3
152
199
Devstral Small 1.1
152
200
Nemotron Nano 12B 2 VL
152
201
Qwen VL Plus
152
202
Qwen3 Coder Flash
152
203
Qwen3 8B
151
204
Qwen2.5 VL 32B Instruct
151
205
Relace Search
151
206
MiniMax M2-her
150
207
Nemotron Nano 9B V2
150
208
Qwen3 Coder 30B A3B Instruct
150
209
Hermes 4 70B
149
210
Inflection 3 Productivity
149
211
GPT-4.1 Nano
148
212
Skyfall 36B V2
147
213
Free Models Router
146
214
Claude 3.5 Haiku
146
215
Kimi Dev 72B
145
216
Llama 3.1 70B Hanami x1
145
217
Qwen3 VL 8B Instruct
144
218
GLM 4.7 Flash
143
219
R1 Distill Qwen 32B
142
220
Gemma 3 27B
142
221
Olmo 3.1 32B Think
139
222
Gemma 3 12B
139
223
Olmo 3 32B Think
138
224
SorcererLM 8x22B
135
225
Llama 3.1 Euryale 70B v2.2
135
226
Nova Lite 1.0
134
227
Llama 3 70B Instruct
133
228
ERNIE 4.5 21B A3B Thinking
133
229
Trinity Mini
132
230
Claude 3 Haiku
132
231
Gemma 2 27B
128
232
ERNIE 4.5 VL 28B A3B
128
233
Nova Micro 1.0
127
234
ERNIE 4.5 21B A3B
126
235
Phi 4
125
236
Llama 3 Euryale 70B v2.1
122
237
Mixtral 8x7B Instruct
122
238
Command R+ (08-2024)
121
239
Command R (08-2024)
120
240
GPT-3.5 Turbo 16k
119
241
Jamba Mini 1.7
115
242
Ministral 3 3B 2512
115
243
Qwen2.5 Coder 32B Instruct
114
244
Gemma 3n 4B
110
245
GPT-3.5 Turbo
110
246
Pixtral 12B
108
247
Gemma 2 9B
107
248
Mistral Nemo
106
249
Olmo 3.1 32B Instruct
104
250
GPT-3.5 Turbo Instruct
104
251
Ministral 8B
103
252
Molmo2 8B
102
253
LFM2-8B-A1B
101
254
Codestral 2508
101
255
Goliath 120B
99
256
Olmo 3 7B Think
96
257
Hunyuan A13B Instruct
95
258
Qwen2.5 7B Instruct
93
259
Gemma 3 4B
88
260
Hermes 3 70B Instruct
87
261
Llama 3 8B Lunaris
87
262
Qwen2.5-VL 7B Instruct
84
263
Granite 4.0 Micro
84
264
Mistral 7B Instruct v0.3
83
265
Mistral 7B Instruct v0.2
83
266
Mistral Tiny
82
267
Mistral 7B Instruct
82
268
Llama 3.1 8B Instruct
78
269
Hermes 2 Pro - Llama-3 8B
77
270
Command R7B (12-2024)
77
271
Llama 3 8B Instruct
72
272
Ministral 3B
72
273
Lumimaid v0.2 8B
68
274
Rocinante 12B
66
275
Mistral 7B Instruct v0.1
65
276
Olmo 3 7B Instruct
65
277
Llama 3.2 3B Instruct
63
278
Rnj 1 Instruct
59
279
UnslopNemo 12B
56
280
Noromaid 20B
54
281
MythoMax 13B
53
282
ReMM SLERP 13B
51
283
Weaver (alpha)
49
284
Llama 3.2 11B Vision Instruct
45
285
Aion-RP 1.0 (8B)
44
286
Llama 3.2 1B Instruct
29
287
Morph V3 Large
23
288
Morph V3 Fast
21
289
Llemma 7b
17
290
CodeLLaMa 7B Instruct Solidity
6
Total:44025
Mitjana:151.81
(290 modelos)
Menú de mètriques
Errors comesos
Nombre total de respostes incorrectes
1
Gemini 3 Flash Preview
7
2
GPT-5.2-Codex
7
3
GPT-5.2 Chat
7
4
GPT-5.2 Pro
7
5
GPT-5 Codex
8
6
o3 Pro
8
7
GPT-5.1 Chat
8
8
GPT-5 Image
8
9
GPT-5 Mini
9
10
GPT-5.2
9
11
GPT-5.1-Codex
9
12
GPT-5
9
13
GPT-5.1
10
14
GPT-5.1-Codex-Max
10
15
Gemini 3 Pro Preview
10
16
o3
10
17
GPT-5 Image Mini
10
18
Nano Banana Pro (Gemini 3 Pro Image Preview)
11
19
Gemini 2.5 Pro Preview 05-06
11
20
Gemini 2.5 Pro
11
21
Claude Opus 4.6
12
22
o4 Mini Deep Research
12
23
Gemini 2.5 Flash
12
24
Claude 3.7 Sonnet
12
25
Gemini 2.5 Pro Preview 06-05
13
26
o3 Deep Research
13
27
Sonar Deep Research
13
28
o4 Mini High
13
29
DeepSeek V3.2 Speciale
13
30
o1-pro
14
31
Grok 4.1 Fast
14
32
Qwen3 235B A22B Thinking 2507
14
33
Kimi K2.5
14
34
Grok 4
14
35
Llama 4 Maverick
14
36
GPT-5.1-Codex-Mini
15
37
o4 Mini
15
38
Auto Router
15
39
Claude Opus 4.5
15
40
Qwen3 235B A22B
15
41
GLM 4.7
15
42
Qwen Plus 0728 (thinking)
15
43
Claude 3.7 Sonnet (thinking)
15
44
GLM 4.5
15
45
Grok 4 Fast
16
46
Aion-1.0
16
47
Claude Sonnet 4
16
48
o1
16
49
gpt-oss-120b
16
50
GPT-5 Chat
16
51
Gemini 2.5 Flash Image (Nano Banana)
16
52
Kimi K2 Thinking
16
53
Gemini 2.5 Flash Preview 09-2025
17
54
Grok 3 Beta
17
55
Step 3.5 Flash
17
56
Qwen3 Max
17
57
Sonar Pro Search
17
58
Kimi K2 0905
17
59
Claude Sonnet 4.5
18
60
Claude 3.5 Sonnet
18
61
DeepSeek V3.2 Exp
18
62
GLM 4.6
18
63
Grok 3
18
64
Qwen3 Next 80B A3B Thinking
18
65
R1 0528
19
66
Claude Opus 4
19
67
Switchpoint Router
19
68
Seed 1.6
19
69
DeepSeek V3.1 Terminus (exacto)
19
70
R1
19
71
Grok 3 Mini
19
72
Qwen-Plus
20
73
Claude Opus 4.1
20
74
Llama 3.3 Nemotron Super 49B V1.5
20
75
Qwen3 VL 235B A22B Thinking
20
76
Mistral Medium 3
20
77
GLM 4.6 (exacto)
20
78
Qwen3 Coder Plus
20
79
Kimi K2 0905 (exacto)
20
80
Qwen3 VL 30B A3B Thinking
21
81
Qwen Plus 0728
21
82
Mistral Large
21
83
GPT-4.1
21
84
CodeLLaMa 7B Instruct Solidity
21
85
Mistral Large 3 2512
22
86
ChatGPT-4o
22
87
GPT-4.1 Mini
22
88
gpt-oss-120b (exacto)
22
89
Qwen3 32B
22
90
Qwen3 Coder Next
22
91
GPT-4o (2024-11-20)
22
92
DeepSeek V3.1
22
93
Grok Code Fast 1
22
94
Qwen VL Max
22
95
Grok 3 Mini Beta
22
96
DeepSeek V3.1 Nex N1
22
97
GPT-4o (2024-08-06)
22
98
GPT-4o
22
99
Cogito v2.1 671B
22
100
GPT-4 Turbo (older v1106)
22
101
Mistral Large 2407
23
102
o3 Mini High
23
103
GPT-5 Nano
23
104
GPT-4
23
105
Kimi K2 0711
23
106
Solar Pro 3
23
107
Nova Premier 1.0
24
108
DeepSeek V3 0324
24
109
DeepSeek V3.1 Terminus
24
110
MiniMax M2
24
111
Pixtral Large 2411
24
112
Gemini 2.0 Flash
24
113
o3 Mini
25
114
Mistral Medium 3.1
25
115
GPT-4o (2024-05-13)
25
116
Qwen3 235B A22B Instruct 2507
25
117
DeepSeek V3.2
25
118
Jamba Large 1.7
25
119
GPT-4o Search Preview
25
Millor humà
25
120
Qwen3 Next 80B A3B Instruct
26
121
Qwen3 VL 235B A22B Instruct
26
122
Palmyra X5
26
123
Devstral 2 2512
26
124
GPT-4 Turbo Preview
26
125
Qwen3 30B A3B Thinking 2507
26
126
MiniMax M2.1
26
127
Kimi Dev 72B
26
128
Tongyi DeepResearch 30B A3B
27
129
GPT-3.5 Turbo (older v0613)
27
130
Claude Haiku 4.5
27
131
Qwen3 VL 32B Instruct
27
132
Gemini 2.5 Flash Lite Preview 09-2025
28
133
Qwen3 Coder 480B A35B (exacto)
28
134
DeepSeek V3
28
135
Cogito V2 Preview Llama 405B
28
136
Sonar Reasoning Pro
28
137
Hermes 3 405B Instruct
28
138
gpt-oss-safeguard-20b
29
139
Mistral Small Creative
29
140
Aion-1.0-Mini
29
141
Trinity Large Preview
29
142
KAT-Coder-Pro V1
30
143
gpt-oss-20b
30
144
Gemini 2.5 Flash Lite
30
145
Qwen3 Coder 480B A35B
30
146
GLM 4.6V
30
147
Nemotron 3 Nano 30B A3B
30
148
Nova Pro 1.0
30
149
Step3
31
150
Sonar
31
151
GPT-4 Turbo
31
152
Cogito V2 Preview Llama 70B
31
153
GLM 4.5 Air
31
154
Command A
32
155
Sonar Pro
32
156
Qwen3 14B
32
157
Devstral Medium
32
158
R1 Distill Llama 70B
32
159
Llama 3.3 70B Instruct
32
160
Qwen3 30B A3B Instruct 2507
33
161
Qwen3 VL 30B A3B Instruct
33
162
QwQ 32B
33
163
Mistral Large 2411
33
164
Llama 4 Scout
33
165
Mistral Small 3.2 24B
33
166
Hermes 4 405B
33
167
Qwen2.5 72B Instruct
33
168
ERNIE 4.5 VL 424B A47B
34
169
Qwen3 VL 8B Thinking
34
170
Qwen2.5 VL 72B Instruct
34
171
Llama 3.1 Nemotron Ultra 253B v1
34
172
Llama 3.1 70B Instruct
34
173
Llama 3.3 Euryale 70B
34
174
GLM 4.5V
35
175
Mistral Small 3.1 24B
35
176
MiMo-V2-Flash
35
177
GPT-4 (older v0314)
35
178
Mercury
35
179
Llama 3.1 Nemotron 70B Instruct
35
180
MiMo-V2-Flash
36
181
Seed 1.6 Flash
36
182
Hermes 4 70B
36
183
Mercury Coder
37
184
Qwen-Max
37
185
Gemini 2.0 Flash Lite
37
186
ERNIE 4.5 300B A47B
38
187
GLM 4 32B
38
188
Voxtral Small 24B 2507
38
189
Saba
38
190
MiniMax M1
38
191
Mixtral 8x22B Instruct
38
192
Cydonia 24B V4.1
38
193
Nova 2 Lite
40
194
Qwen-Turbo
40
195
Mistral Small 3
40
196
Devstral Small 1.1
40
197
Ministral 3 8B 2512
41
198
GPT-4o-mini (2024-07-18)
41
199
MiniMax M2-her
41
200
Olmo 3.1 32B Think
41
201
Llemma 7b
41
202
GPT-4o-mini Search Preview
42
203
Inflection 3 Pi
42
204
Ministral 3 14B 2512
43
205
Nemotron Nano 12B 2 VL
43
206
Skyfall 36B V2
43
207
Olmo 3 32B Think
43
208
Llama 3 70B Instruct
43
209
GPT-4o-mini
44
210
Qwen3 8B
45
211
Inflection 3 Productivity
45
212
Morph V3 Large
45
213
Nemotron Nano 9B V2
46
214
Qwen3 VL 8B Instruct
46
215
Qwen VL Plus
47
216
Free Models Router
47
217
Qwen3 Coder Flash
48
218
Qwen3 Coder 30B A3B Instruct
48
219
Llama 3.1 70B Hanami x1
48
220
Llama 3.2 11B Vision Instruct
48
221
Qwen2.5 VL 32B Instruct
49
222
Relace Search
49
223
SorcererLM 8x22B
49
224
GPT-4.1 Nano
51
225
Claude 3.5 Haiku
51
226
Llama 3.1 Euryale 70B v2.2
51
227
Hermes 3 70B Instruct
51
228
GLM 4.7 Flash
53
229
Trinity Mini
54
230
R1 Distill Qwen 32B
56
231
Gemma 3 27B
58
232
Morph V3 Fast
58
233
Gemma 3 12B
59
234
Gemma 2 27B
60
235
Claude 3 Haiku
61
236
Command R+ (08-2024)
61
237
Aion-RP 1.0 (8B)
61
238
Nova Micro 1.0
62
239
UnslopNemo 12B
62
240
Nova Lite 1.0
63
241
ERNIE 4.5 21B A3B Thinking
66
242
Llama 3 Euryale 70B v2.1
66
243
ERNIE 4.5 VL 28B A3B
67
244
Gemma 2 9B
67
245
Hunyuan A13B Instruct
67
246
Llama 3.2 1B Instruct
67
247
Mixtral 8x7B Instruct
69
248
Rocinante 12B
69
249
ERNIE 4.5 21B A3B
70
250
Qwen2.5 Coder 32B Instruct
70
251
Phi 4
72
252
Qwen2.5 7B Instruct
73
253
Qwen2.5-VL 7B Instruct
73
254
GPT-3.5 Turbo 16k
77
255
Jamba Mini 1.7
77
256
Molmo2 8B
77
257
Llama 3.1 8B Instruct
77
258
Command R (08-2024)
79
259
Ministral 3 3B 2512
81
260
Mistral Nemo
81
261
Gemma 3n 4B
82
262
Pixtral 12B
82
263
Goliath 120B
83
264
Ministral 8B
85
265
Olmo 3.1 32B Instruct
86
266
MythoMax 13B
86
267
GPT-3.5 Turbo
89
268
GPT-3.5 Turbo Instruct
89
269
Llama 3 8B Lunaris
92
270
LFM2-8B-A1B
93
271
Mistral 7B Instruct v0.1
93
272
Codestral 2508
94
273
Mistral Tiny
98
274
Olmo 3 7B Think
100
275
Mistral 7B Instruct
100
276
Mistral 7B Instruct v0.3
101
277
Mistral 7B Instruct v0.2
101
278
Llama 3 8B Instruct
101
279
ReMM SLERP 13B
101
280
Hermes 2 Pro - Llama-3 8B
103
281
Noromaid 20B
104
282
Granite 4.0 Micro
105
283
Llama 3.2 3B Instruct
106
284
Ministral 3B
109
285
Gemma 3 4B
111
286
Weaver (alpha)
111
287
Command R7B (12-2024)
115
288
Rnj 1 Instruct
120
289
Olmo 3 7B Instruct
124
290
Lumimaid v0.2 8B
125
Total:11150
Mitjana:38.44
(290 modelos)
Menú de mètriques
Percentatge d'encerts
Proporció de respostes correctes sobre el total
1
Gemini 3 Flash Preview
96.5%
2
GPT-5.2-Codex
96.0%
3
GPT-5 Codex
96.0%
4
o3 Pro
96.0%
5
GPT-5.2 Chat
95.5%
6
GPT-5.2 Pro
95.5%
7
GPT-5.1 Chat
95.5%
8
GPT-5 Image
95.5%
9
GPT-5 Mini
95.5%
10
GPT-5.2
95.5%
11
GPT-5.1-Codex
95.0%
12
GPT-5
95.0%
13
GPT-5.1
95.0%
14
GPT-5.1-Codex-Max
95.0%
15
Gemini 3 Pro Preview
94.5%
16
Nano Banana Pro (Gemini 3 Pro Image Preview)
94.5%
17
Gemini 2.5 Pro Preview 05-06
94.5%
18
o3
94.0%
19
Gemini 2.5 Pro
94.0%
20
Claude Opus 4.6
94.0%
21
o4 Mini Deep Research
94.0%
22
GPT-5 Image Mini
93.5%
23
Gemini 2.5 Pro Preview 06-05
93.5%
24
o3 Deep Research
93.5%
25
Sonar Deep Research
93.5%
26
o4 Mini High
93.0%
27
o1-pro
93.0%
28
Gemini 2.5 Flash
92.5%
29
Grok 4.1 Fast
92.5%
30
Qwen3 235B A22B Thinking 2507
92.5%
31
Kimi K2.5
92.5%
32
Grok 4
92.5%
33
GPT-5.1-Codex-Mini
92.5%
34
o4 Mini
92.5%
35
Auto Router
92.5%
36
Claude Opus 4.5
92.5%
37
Qwen3 235B A22B
92.0%
38
GLM 4.7
92.0%
39
Qwen Plus 0728 (thinking)
92.0%
40
Claude 3.7 Sonnet (thinking)
92.0%
41
Grok 4 Fast
92.0%
42
Aion-1.0
92.0%
43
Claude Sonnet 4
92.0%
44
o1
92.0%
45
Claude 3.7 Sonnet
91.5%
46
Llama 4 Maverick
91.5%
47
GLM 4.5
91.0%
48
gpt-oss-120b
91.0%
49
GPT-5 Chat
91.0%
50
Gemini 2.5 Flash Preview 09-2025
91.0%
51
Claude Sonnet 4.5
91.0%
52
Grok 3 Beta
90.5%
53
R1 0528
90.5%
54
Claude Opus 4
90.5%
55
Claude 3.5 Sonnet
90.0%
56
Gemini 2.5 Flash Image (Nano Banana)
89.5%
57
Step 3.5 Flash
89.5%
58
DeepSeek V3.2 Exp
89.5%
59
GLM 4.6
89.5%
60
Grok 3
89.5%
61
Switchpoint Router
89.5%
62
Seed 1.6
89.5%
63
Qwen-Plus
89.5%
64
Claude Opus 4.1
89.5%
65
Qwen3 VL 30B A3B Thinking
89.5%
66
Qwen3 Max
89.0%
67
Qwen3 Next 80B A3B Thinking
89.0%
68
DeepSeek V3.1 Terminus (exacto)
89.0%
69
R1
89.0%
70
Llama 3.3 Nemotron Super 49B V1.5
89.0%
71
Qwen3 VL 235B A22B Thinking
89.0%
72
Qwen Plus 0728
89.0%
73
Mistral Large
89.0%
74
GPT-4.1
89.0%
75
Mistral Large 3 2512
89.0%
76
ChatGPT-4o
89.0%
77
Mistral Medium 3
88.5%
78
GPT-4.1 Mini
88.5%
79
DeepSeek V3.2 Speciale
88.0%
80
GLM 4.6 (exacto)
88.0%
81
gpt-oss-120b (exacto)
88.0%
82
Mistral Large 2407
88.0%
83
o3 Mini High
88.0%
84
Nova Premier 1.0
88.0%
85
Sonar Pro Search
87.5%
86
Grok 3 Mini
87.5%
87
Qwen3 Coder Plus
87.5%
88
Qwen3 32B
87.5%
89
Qwen3 Coder Next
87.5%
90
GPT-4o (2024-11-20)
87.5%
91
GPT-5 Nano
87.5%
92
DeepSeek V3 0324
87.5%
93
o3 Mini
87.5%
94
Kimi K2 Thinking
87.0%
95
DeepSeek V3.1
87.0%
96
Grok Code Fast 1
87.0%
97
Qwen VL Max
87.0%
98
DeepSeek V3.1 Terminus
87.0%
99
MiniMax M2
87.0%
100
Mistral Medium 3.1
87.0%
101
GPT-4o (2024-05-13)
87.0%
102
Qwen3 Next 80B A3B Instruct
87.0%
Millor humà
87.0%
103
GPT-4
86.5%
104
Pixtral Large 2411
86.5%
105
Qwen3 235B A22B Instruct 2507
86.5%
106
Qwen3 VL 235B A22B Instruct
86.5%
107
Palmyra X5
86.5%
108
Grok 3 Mini Beta
86.0%
109
Kimi K2 0711
86.0%
110
Gemini 2.0 Flash
86.0%
111
DeepSeek V3.2
86.0%
112
Jamba Large 1.7
86.0%
113
Devstral 2 2512
86.0%
114
Gemini 2.5 Flash Lite Preview 09-2025
86.0%
115
DeepSeek V3.1 Nex N1
85.5%
116
GPT-4 Turbo Preview
85.5%
117
Tongyi DeepResearch 30B A3B
85.5%
118
GPT-3.5 Turbo (older v0613)
85.5%
119
Claude Haiku 4.5
85.5%
120
Qwen3 Coder 480B A35B (exacto)
85.5%
121
GPT-4o (2024-08-06)
85.0%
122
Qwen3 VL 32B Instruct
85.0%
123
DeepSeek V3
85.0%
124
gpt-oss-safeguard-20b
85.0%
125
KAT-Coder-Pro V1
85.0%
126
GPT-4o
84.5%
127
Qwen3 30B A3B Thinking 2507
84.5%
128
Mistral Small Creative
84.5%
129
gpt-oss-20b
84.5%
130
Gemini 2.5 Flash Lite
84.5%
131
Qwen3 Coder 480B A35B
84.5%
132
GLM 4.6V
84.5%
133
Kimi K2 0905
84.0%
134
Cogito v2.1 671B
84.0%
135
Nemotron 3 Nano 30B A3B
84.0%
136
Step3
84.0%
137
GPT-4 Turbo (older v1106)
83.5%
138
GPT-4o Search Preview
83.5%
139
Aion-1.0-Mini
83.5%
140
Sonar
83.5%
141
GPT-4 Turbo
83.5%
142
Trinity Large Preview
83.0%
143
Nova Pro 1.0
83.0%
144
Command A
83.0%
145
Qwen3 30B A3B Instruct 2507
83.0%
146
Qwen3 VL 30B A3B Instruct
83.0%
147
QwQ 32B
83.0%
148
Mistral Large 2411
83.0%
149
ERNIE 4.5 VL 424B A47B
83.0%
150
Qwen3 VL 8B Thinking
83.0%
151
Sonar Pro
82.5%
152
GLM 4.5V
82.5%
153
Qwen3 14B
82.0%
154
Devstral Medium
82.0%
155
Llama 4 Scout
82.0%
156
Qwen2.5 VL 72B Instruct
82.0%
157
Llama 3.1 Nemotron Ultra 253B v1
82.0%
158
Cogito V2 Preview Llama 405B
81.5%
159
Cogito V2 Preview Llama 70B
81.5%
160
R1 Distill Llama 70B
81.5%
161
Mistral Small 3.2 24B
81.5%
162
Mistral Small 3.1 24B
81.5%
163
MiMo-V2-Flash
81.5%
164
Seed 1.6 Flash
81.5%
165
Kimi K2 0905 (exacto)
81.0%
166
Sonar Reasoning Pro
81.0%
167
MiniMax M2.1
80.5%
168
Hermes 4 405B
80.5%
169
Mercury Coder
80.5%
170
Qwen-Max
80.5%
171
ERNIE 4.5 300B A47B
80.5%
172
Hermes 3 405B Instruct
80.0%
173
MiMo-V2-Flash
80.0%
174
GPT-4 (older v0314)
80.0%
175
Gemini 2.0 Flash Lite
80.0%
176
Llama 3.3 70B Instruct
79.5%
177
Llama 3.1 70B Instruct
79.5%
178
Mercury
79.5%
179
GLM 4 32B
79.5%
180
Voxtral Small 24B 2507
79.5%
181
Ministral 3 8B 2512
79.5%
182
Qwen2.5 72B Instruct
79.0%
183
Llama 3.1 Nemotron 70B Instruct
79.0%
184
Saba
79.0%
185
Solar Pro 3
78.5%
186
MiniMax M1
78.0%
187
Mixtral 8x22B Instruct
78.0%
188
GPT-4o-mini (2024-07-18)
78.0%
189
Nova 2 Lite
77.5%
190
GPT-4o-mini Search Preview
77.5%
191
GPT-4o-mini
77.5%
192
GLM 4.5 Air
77.0%
193
Ministral 3 14B 2512
77.0%
194
Cydonia 24B V4.1
76.5%
195
Qwen-Turbo
76.5%
196
Inflection 3 Pi
76.5%
197
Llama 3.3 Euryale 70B
76.0%
198
Mistral Small 3
76.0%
199
Devstral Small 1.1
76.0%
200
Nemotron Nano 12B 2 VL
76.0%
201
Qwen VL Plus
76.0%
202
Qwen3 Coder Flash
76.0%
203
Qwen3 8B
75.5%
204
Qwen2.5 VL 32B Instruct
75.5%
205
Relace Search
75.5%
206
MiniMax M2-her
75.0%
207
Nemotron Nano 9B V2
75.0%
208
Qwen3 Coder 30B A3B Instruct
75.0%
209
Hermes 4 70B
74.5%
210
Inflection 3 Productivity
74.5%
211
GPT-4.1 Nano
74.0%
212
Skyfall 36B V2
73.5%
213
Free Models Router
73.0%
214
Claude 3.5 Haiku
73.0%
215
Kimi Dev 72B
72.5%
216
Llama 3.1 70B Hanami x1
72.5%
217
Qwen3 VL 8B Instruct
72.0%
218
GLM 4.7 Flash
71.5%
219
R1 Distill Qwen 32B
71.0%
220
Gemma 3 27B
71.0%
221
Olmo 3.1 32B Think
69.5%
222
Gemma 3 12B
69.5%
223
Olmo 3 32B Think
69.0%
224
SorcererLM 8x22B
67.5%
225
Llama 3.1 Euryale 70B v2.2
67.5%
226
Nova Lite 1.0
67.0%
227
Llama 3 70B Instruct
66.5%
228
ERNIE 4.5 21B A3B Thinking
66.5%
229
Trinity Mini
66.0%
230
Claude 3 Haiku
66.0%
231
Gemma 2 27B
64.0%
232
ERNIE 4.5 VL 28B A3B
64.0%
233
Nova Micro 1.0
63.5%
234
ERNIE 4.5 21B A3B
63.0%
235
Phi 4
62.5%
236
Llama 3 Euryale 70B v2.1
61.0%
237
Mixtral 8x7B Instruct
61.0%
238
Command R+ (08-2024)
60.5%
239
Command R (08-2024)
60.0%
240
GPT-3.5 Turbo 16k
59.5%
241
Jamba Mini 1.7
57.5%
242
Ministral 3 3B 2512
57.5%
243
Qwen2.5 Coder 32B Instruct
57.0%
244
Gemma 3n 4B
55.0%
245
GPT-3.5 Turbo
55.0%
246
Pixtral 12B
54.0%
247
Gemma 2 9B
53.5%
248
Mistral Nemo
53.0%
249
Olmo 3.1 32B Instruct
52.0%
250
GPT-3.5 Turbo Instruct
52.0%
251
Ministral 8B
51.5%
252
Molmo2 8B
51.0%
253
LFM2-8B-A1B
50.5%
254
Codestral 2508
50.5%
255
Goliath 120B
49.5%
256
Olmo 3 7B Think
48.0%
257
Hunyuan A13B Instruct
47.5%
258
Qwen2.5 7B Instruct
46.5%
259
Gemma 3 4B
44.0%
260
Hermes 3 70B Instruct
43.5%
261
Llama 3 8B Lunaris
43.5%
262
Qwen2.5-VL 7B Instruct
42.0%
263
Granite 4.0 Micro
42.0%
264
Mistral 7B Instruct v0.3
41.5%
265
Mistral 7B Instruct v0.2
41.5%
266
Mistral Tiny
41.0%
267
Mistral 7B Instruct
41.0%
268
Llama 3.1 8B Instruct
39.0%
269
Hermes 2 Pro - Llama-3 8B
38.5%
270
Command R7B (12-2024)
38.5%
271
Llama 3 8B Instruct
36.0%
272
Ministral 3B
36.0%
273
Lumimaid v0.2 8B
34.0%
274
Rocinante 12B
33.0%
275
Mistral 7B Instruct v0.1
32.5%
276
Olmo 3 7B Instruct
32.5%
277
Llama 3.2 3B Instruct
31.5%
278
Rnj 1 Instruct
29.5%
279
UnslopNemo 12B
28.0%
280
Noromaid 20B
27.0%
281
MythoMax 13B
26.5%
282
ReMM SLERP 13B
25.5%
283
Weaver (alpha)
24.5%
284
Llama 3.2 11B Vision Instruct
22.5%
285
Aion-RP 1.0 (8B)
22.0%
286
Llama 3.2 1B Instruct
14.5%
287
Morph V3 Large
11.5%
288
Morph V3 Fast
10.5%
289
Llemma 7b
8.5%
290
CodeLLaMa 7B Instruct Solidity
3.0%
Mitjana:75.9%
(290 modelos)
Menú de mètriques
Temps mitjà de resposta
Temps mitjà que tarda el model a respondre a cada pregunta
1
Ministral 3B
1.5s
2
gpt-oss-safeguard-20b
1.5s
3
Devstral Small 1.1
1.5s
4
Ministral 8B
1.8s
5
Mistral 7B Instruct v0.3
1.9s
6
Mistral 7B Instruct
1.9s
7
Morph V3 Large
1.9s
8
Voxtral Small 24B 2507
2.0s
9
LFM2-8B-A1B
2.1s
10
Mercury Coder
2.2s
11
Mercury
2.3s
12
Codestral 2508
2.4s
13
Mistral Tiny
2.5s
14
Nova Micro 1.0
2.6s
15
Gemma 2 9B
2.6s
16
Mistral 7B Instruct v0.2
2.6s
17
GPT-3.5 Turbo 16k
3.0s
18
GPT-3.5 Turbo
3.1s
19
Morph V3 Fast
3.1s
20
Command R7B (12-2024)
3.2s
21
GPT-4o (2024-05-13)
3.4s
22
Ministral 3 3B 2512
3.5s
23
Jamba Mini 1.7
3.5s
24
Claude 3 Haiku
3.5s
25
Gemini 2.0 Flash
3.5s
26
Gemini 2.5 Flash Lite Preview 09-2025
3.6s
27
Devstral Medium
3.6s
28
GPT-3.5 Turbo Instruct
3.7s
29
GPT-4.1 Nano
3.8s
30
Nova Lite 1.0
3.9s
31
Gemini 2.0 Flash Lite
3.9s
32
GPT-5.1-Codex-Mini
4.0s
33
Hermes 2 Pro - Llama-3 8B
4.1s
34
Gemini 2.5 Flash Lite
4.2s
35
Qwen3 Coder 480B A35B (exacto)
4.2s
36
gpt-oss-20b
4.3s
37
Lumimaid v0.2 8B
4.3s
38
Pixtral 12B
4.3s
39
Mixtral 8x22B Instruct
4.3s
40
GPT-4o-mini Search Preview
4.4s
41
Nova Pro 1.0
4.5s
42
Relace Search
4.6s
43
Saba
4.7s
44
ChatGPT-4o
4.7s
45
GPT-5.1-Codex
4.8s
46
Hermes 4 70B
4.9s
47
Llama 3.2 1B Instruct
4.9s
48
Aion-1.0-Mini
4.9s
49
GPT-5 Chat
5.1s
50
GPT-5.1 Chat
5.1s
51
Rnj 1 Instruct
5.2s
52
Cogito v2.1 671B
5.3s
53
Skyfall 36B V2
5.4s
54
Gemini 2.5 Flash Preview 09-2025
5.4s
55
Gemini 2.5 Flash
5.5s
56
Gemma 2 27B
5.5s
57
Ministral 3 8B 2512
5.6s
58
Qwen3 Coder 480B A35B
5.7s
59
Llama 3 8B Lunaris
5.7s
60
GPT-5 Codex
5.8s
61
Mistral Medium 3
6.2s
62
Qwen2.5-VL 7B Instruct
6.2s
63
Claude Haiku 4.5
6.2s
64
Mixtral 8x7B Instruct
6.3s
65
Kimi K2 0905 (exacto)
6.4s
66
Molmo2 8B
6.5s
67
Sonar
6.5s
68
Gemini 3 Flash Preview
6.5s
69
GPT-4o (2024-11-20)
6.6s
70
Sonar Pro
6.6s
71
o3 Mini High
6.7s
72
Mistral Nemo
7.0s
73
GPT-4.1 Mini
7.1s
74
o3 Mini
7.1s
75
Claude 3.5 Haiku
7.2s
76
Kimi K2 0905
7.2s
77
Qwen-Turbo
7.2s
78
Mistral Small 3
7.3s
79
GPT-4o Search Preview
7.4s
80
Qwen3 Coder Flash
7.5s
81
Nova 2 Lite
7.5s
82
GLM 4 32B
7.6s
83
GPT-4o-mini (2024-07-18)
7.6s
84
GPT-4o-mini
7.6s
85
Mistral Small Creative
7.6s
86
Llama 4 Scout
7.8s
87
ERNIE 4.5 21B A3B
7.8s
88
Hunyuan A13B Instruct
7.9s
89
Seed 1.6 Flash
8.0s
90
Cogito V2 Preview Llama 70B
8.0s
91
Palmyra X5
8.1s
92
Ministral 3 14B 2512
8.2s
93
UnslopNemo 12B
8.3s
94
Command R (08-2024)
8.5s
95
Mistral Medium 3.1
8.5s
96
Cydonia 24B V4.1
8.6s
97
o4 Mini
8.7s
98
Mistral Small 3.1 24B
8.9s
99
Hermes 4 405B
8.9s
100
MiniMax M2-her
8.9s
101
Mistral Small 3.2 24B
8.9s
102
Llama 3 Euryale 70B v2.1
9.0s
103
GPT-3.5 Turbo (older v0613)
9.1s
104
GPT-5.2 Chat
9.1s
105
Qwen VL Plus
9.1s
106
Inflection 3 Productivity
9.2s
107
Inflection 3 Pi
9.2s
108
DeepSeek V3 0324
9.2s
109
KAT-Coder-Pro V1
9.2s
110
GPT-4o
9.3s
111
Grok 4 Fast
9.3s
112
Pixtral Large 2411
9.4s
113
Llama 3.1 70B Instruct
9.4s
114
Mistral Large 2411
9.5s
115
Rocinante 12B
9.5s
116
GPT-4o (2024-08-06)
9.6s
117
Qwen3 Next 80B A3B Instruct
9.6s
118
Command A
10.0s
119
Sonar Pro Search
10.2s
120
Command R+ (08-2024)
10.3s
121
MiMo-V2-Flash
10.4s
122
GPT-4 Turbo (older v1106)
10.5s
123
Claude 3.7 Sonnet
10.6s
124
o3
10.7s
125
Qwen2.5 72B Instruct
10.7s
126
Llama 3 8B Instruct
10.7s
127
Claude Sonnet 4
10.7s
128
Step 3.5 Flash
10.7s
129
Qwen2.5 7B Instruct
10.8s
130
Claude 3.5 Sonnet
10.8s
131
MythoMax 13B
10.8s
132
GPT-4.1
11.0s
133
Qwen-Max
11.1s
134
SorcererLM 8x22B
11.1s
135
Llama 4 Maverick
11.2s
136
o1
11.2s
137
Nemotron Nano 9B V2
11.3s
138
MiniMax M2
11.5s
139
o4 Mini High
11.9s
140
Aion-RP 1.0 (8B)
12.0s
141
Mistral Large
12.1s
142
Mistral Large 2407
12.1s
143
Grok Code Fast 1
12.1s
144
Gemma 3n 4B
12.2s
145
Qwen3 VL 8B Instruct
12.2s
146
Mistral Large 3 2512
12.2s
147
Gemma 3 4B
12.3s
148
Sonar Reasoning Pro
12.4s
149
gpt-oss-120b (exacto)
12.4s
150
Gemma 3 12B
12.4s
151
Qwen Plus 0728
12.5s
152
Llama 3 70B Instruct
12.5s
153
Trinity Large Preview
12.6s
154
Grok 4.1 Fast
12.7s
155
ReMM SLERP 13B
12.8s
156
Weaver (alpha)
13.0s
157
GPT-4 (older v0314)
13.1s
158
Qwen3 VL 30B A3B Instruct
13.1s
159
GPT-4 Turbo
13.1s
160
Claude Sonnet 4.5
13.2s
161
GPT-4
13.4s
162
Gemma 3 27B
13.4s
163
Llama 3.3 70B Instruct
13.5s
164
Noromaid 20B
13.5s
165
Cogito V2 Preview Llama 405B
13.6s
166
GPT-4 Turbo Preview
13.7s
167
Olmo 3.1 32B Instruct
13.7s
168
Qwen-Plus
13.8s
169
GPT-5.2-Codex
13.8s
170
Claude Opus 4.5
13.9s
171
DeepSeek V3
14.0s
172
GPT-5.2
14.1s
173
Nemotron Nano 12B 2 VL
14.2s
174
Llama 3.1 Nemotron Ultra 253B v1
14.3s
175
Granite 4.0 Micro
14.3s
176
Phi 4
14.4s
177
Qwen3 Coder 30B A3B Instruct
14.5s
178
Tongyi DeepResearch 30B A3B
14.5s
179
Llama 3.1 Nemotron 70B Instruct
14.6s
180
GPT-5.1-Codex-Max
14.9s
181
R1 Distill Llama 70B
15.2s
182
Auto Router
15.2s
183
Olmo 3 7B Think
15.2s
184
Qwen2.5 Coder 32B Instruct
15.4s
185
Nova Premier 1.0
15.5s
186
DeepSeek V3.1 Terminus
15.5s
187
DeepSeek V3.1 Terminus (exacto)
15.6s
188
Qwen3 Coder Plus
15.7s
189
Kimi K2 0711
15.8s
190
Hermes 3 405B Instruct
15.9s
191
ERNIE 4.5 VL 28B A3B
16.1s
192
Claude Opus 4.6
16.3s
193
Grok 3 Beta
16.4s
194
Grok 3 Mini
16.5s
195
Grok 3 Mini Beta
16.5s
196
Jamba Large 1.7
16.6s
197
Grok 3
16.6s
198
GPT-5 Mini
16.7s
199
Qwen2.5 VL 32B Instruct
16.8s
200
ERNIE 4.5 300B A47B
16.8s
201
Qwen3 30B A3B Instruct 2507
16.9s
202
GPT-5 Image Mini
17.0s
203
Qwen3 30B A3B Thinking 2507
17.3s
204
Trinity Mini
17.6s
205
Qwen3 VL 235B A22B Instruct
17.7s
206
Gemini 2.5 Flash Image (Nano Banana)
17.8s
207
GPT-5.1
17.8s
208
Llama 3.1 Euryale 70B v2.2
18.2s
209
Qwen3 VL 32B Instruct
18.5s
210
Qwen3 Max
18.9s
211
Llama 3.3 Nemotron Super 49B V1.5
19.0s
212
Switchpoint Router
19.2s
213
Olmo 3 7B Instruct
19.3s
214
Llama 3.2 3B Instruct
19.5s
215
Qwen3 8B
19.6s
216
Llama 3.3 Euryale 70B
19.6s
217
gpt-oss-120b
19.7s
218
Qwen3 235B A22B Instruct 2507
20.2s
219
ERNIE 4.5 VL 424B A47B
20.4s
220
Llama 3.1 8B Instruct
20.8s
221
Qwen VL Max
21.6s
222
GPT-5 Nano
21.7s
223
GPT-5 Image
21.9s
224
MiMo-V2-Flash
22.4s
225
Qwen2.5 VL 72B Instruct
22.7s
226
Qwen3 Next 80B A3B Thinking
22.8s
227
Qwen3 Coder Next
22.9s
228
GPT-5
23.8s
229
Goliath 120B
24.3s
230
Mistral 7B Instruct v0.1
24.5s
231
Qwen3 14B
25.0s
232
MiniMax M1
25.6s
233
Qwen3 235B A22B
25.7s
234
Gemini 2.5 Pro Preview 06-05
25.8s
235
Gemini 2.5 Pro
26.0s
236
GLM 4.5 Air
26.1s
237
Gemini 2.5 Pro Preview 05-06
26.2s
238
Qwen3 32B
27.5s
239
Free Models Router
28.3s
240
Claude Opus 4
28.5s
241
MiniMax M2.1
29.1s
242
DeepSeek V3.1 Nex N1
30.6s
243
Solar Pro 3
31.0s
244
Claude Opus 4.1
31.0s
245
Qwen Plus 0728 (thinking)
31.2s
246
Aion-1.0
31.4s
247
Llama 3.1 70B Hanami x1
31.8s
248
CodeLLaMa 7B Instruct Solidity
31.9s
249
ERNIE 4.5 21B A3B Thinking
31.9s
250
Nano Banana Pro (Gemini 3 Pro Image Preview)
32.1s
251
o1-pro
33.2s
252
R1 0528
33.7s
253
GLM 4.5V
33.8s
254
DeepSeek V3.2 Exp
33.9s
255
Gemini 3 Pro Preview
34.1s
256
Claude 3.7 Sonnet (thinking)
34.7s
257
Nemotron 3 Nano 30B A3B
35.2s
258
DeepSeek V3.2
36.2s
259
GLM 4.5
36.8s
260
GLM 4.6V
37.6s
261
R1 Distill Qwen 32B
38.5s
262
Qwen3 VL 30B A3B Thinking
38.8s
263
Qwen3 VL 8B Thinking
38.9s
264
Seed 1.6
39.7s
265
GLM 4.6
41.6s
266
GPT-5.2 Pro
42.2s
267
Devstral 2 2512
43.8s
268
Grok 4
44.7s
269
Sonar Deep Research
45.0s
270
Kimi Dev 72B
46.1s
271
R1
46.3s
272
DeepSeek V3.1
47.5s
273
Qwen3 VL 235B A22B Thinking
47.6s
274
Llama 3.2 11B Vision Instruct
50.8s
275
Olmo 3 32B Think
51.1s
276
Step3
52.1s
277
o3 Pro
52.9s
278
Olmo 3.1 32B Think
54.7s
279
Kimi K2 Thinking
54.8s
280
Kimi K2.5
60.4s
281
Llemma 7b
63.6s
282
QwQ 32B
64.2s
283
GLM 4.6 (exacto)
73.0s
284
GLM 4.7
74.1s
285
DeepSeek V3.2 Speciale
94.0s
286
GLM 4.7 Flash
100.1s
287
Qwen3 235B A22B Thinking 2507
107.9s
288
o4 Mini Deep Research
124.5s
289
o3 Deep Research
125.1s
290
Hermes 3 70B Instruct
163.5s
Mitjana:18.1s
(290 modelos)
Menú de mètriques
Cost mitjà per pregunta
Cost mitjà en USD per pregunta avaluada
1
LFM2-8B-A1B
$0.0000
2
Ministral 3B
$0.0000
3
Gemma 3n 4B
$0.0000
4
Mistral Nemo
$0.0000
5
Llama 3 8B Lunaris
$0.0000
6
Gemma 2 9B
$0.0000
7
Llama 3.2 3B Instruct
$0.0000
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
Llama 3.1 8B Instruct
$0.0001
16
GLM 4 32B
$0.0001
17
Nova Micro 1.0
$0.0001
18
Pixtral 12B
$0.0001
19
Mistral Small 3
$0.0001
20
Phi 4
$0.0001
21
Voxtral Small 24B 2507
$0.0001
22
Gemma 3 12B
$0.0001
23
Hermes 2 Pro - Llama-3 8B
$0.0001
24
Llama 3.2 1B Instruct
$0.0001
25
Ministral 3 3B 2512
$0.0001
26
Qwen-Turbo
$0.0001
27
Devstral Small 1.1
$0.0001
28
Nova Lite 1.0
$0.0001
29
Mistral 7B Instruct v0.1
$0.0001
30
Rnj 1 Instruct
$0.0002
31
Mistral Small 3.2 24B
$0.0002
32
Gemma 3 27B
$0.0002
33
Gemini 2.0 Flash Lite
$0.0002
34
Mistral 7B Instruct v0.3
$0.0002
35
Mistral 7B Instruct
$0.0002
36
gpt-oss-120b (exacto)
$0.0002
37
ERNIE 4.5 21B A3B
$0.0002
38
Qwen2.5-VL 7B Instruct
$0.0002
39
Ministral 3 8B 2512
$0.0002
40
Llama 3.2 11B Vision Instruct
$0.0002
41
Mistral 7B Instruct v0.2
$0.0002
42
GPT-4.1 Nano
$0.0002
43
Molmo2 8B
$0.0002
44
gpt-oss-20b
$0.0002
45
Lumimaid v0.2 8B
$0.0002
46
Gemini 2.0 Flash
$0.0002
47
Mistral Tiny
$0.0002
48
Olmo 3 7B Instruct
$0.0002
49
Qwen3 Coder 30B A3B Instruct
$0.0002
50
Hermes 4 70B
$0.0002
51
Nemotron Nano 9B V2
$0.0003
52
Llama 4 Scout
$0.0003
53
Qwen2.5 72B Instruct
$0.0003
54
Ministral 3 14B 2512
$0.0003
55
Jamba Mini 1.7
$0.0003
56
Qwen2.5 Coder 32B Instruct
$0.0003
57
Qwen3 14B
$0.0003
58
Saba
$0.0003
59
Command R (08-2024)
$0.0003
60
gpt-oss-safeguard-20b
$0.0003
61
Mistral Small 3.1 24B
$0.0004
62
Qwen3 30B A3B Instruct 2507
$0.0004
63
UnslopNemo 12B
$0.0004
64
Rocinante 12B
$0.0004
65
Hunyuan A13B Instruct
$0.0004
66
MiMo-V2-Flash
$0.0004
67
Qwen3 8B
$0.0004
68
KAT-Coder-Pro V1
$0.0004
69
Llama 3.1 70B Instruct
$0.0004
70
DeepSeek V3.2 Exp
$0.0004
71
Cydonia 24B V4.1
$0.0004
72
Gemma 2 27B
$0.0004
73
Seed 1.6 Flash
$0.0005
74
Llama 3 70B Instruct
$0.0005
75
DeepSeek V3.2
$0.0005
76
Gemini 2.5 Flash Lite
$0.0005
77
Gemini 2.5 Flash Lite Preview 09-2025
$0.0005
78
Llama 3.3 70B Instruct
$0.0005
79
gpt-oss-120b
$0.0005
80
GPT-4o-mini (2024-07-18)
$0.0005
81
Mistral Small Creative
$0.0005
82
GPT-4o-mini
$0.0005
83
Codestral 2508
$0.0005
84
Mercury Coder
$0.0005
85
Mercury
$0.0005
86
ReMM SLERP 13B
$0.0006
87
Qwen2.5 VL 72B Instruct
$0.0006
88
Llama 4 Maverick
$0.0006
89
Trinity Mini
$0.0006
90
Qwen3 VL 8B Instruct
$0.0006
91
Olmo 3.1 32B Instruct
$0.0006
92
DeepSeek V3.1 Terminus (exacto)
$0.0006
93
DeepSeek V3
$0.0006
94
Mixtral 8x7B Instruct
$0.0006
95
Qwen VL Plus
$0.0006
96
Skyfall 36B V2
$0.0006
97
Olmo 3 7B Think
$0.0007
98
ERNIE 4.5 300B A47B
$0.0007
99
DeepSeek V3.1
$0.0007
100
Qwen3 30B A3B Thinking 2507
$0.0007
101
Claude 3 Haiku
$0.0007
102
Qwen3 VL 235B A22B Instruct
$0.0007
103
Qwen3 32B
$0.0007
104
Llama 3.3 Nemotron Super 49B V1.5
$0.0007
105
ERNIE 4.5 VL 28B A3B
$0.0007
106
Grok 4 Fast
$0.0007
107
Qwen3 235B A22B Instruct 2507
$0.0007
108
Aion-1.0-Mini
$0.0007
109
GPT-3.5 Turbo
$0.0007
110
Qwen3 VL 30B A3B Instruct
$0.0007
111
Tongyi DeepResearch 30B A3B
$0.0008
112
DeepSeek V3.1 Terminus
$0.0008
113
Grok 4.1 Fast
$0.0008
114
Cogito V2 Preview Llama 70B
$0.0008
115
Llama 3.3 Euryale 70B
$0.0008
116
Hermes 3 405B Instruct
$0.0008
117
ERNIE 4.5 21B A3B Thinking
$0.0009
118
Llama 3.1 Euryale 70B v2.2
$0.0009
119
Nemotron 3 Nano 30B A3B
$0.0009
120
GPT-5 Nano
$0.0009
121
Grok 3 Mini Beta
$0.0009
122
QwQ 32B
$0.0009
123
Grok 3 Mini
$0.0010
124
GPT-4.1 Mini
$0.0010
125
DeepSeek V3 0324
$0.0010
126
Qwen3 Next 80B A3B Instruct
$0.0010
127
Devstral Medium
$0.0010
128
Aion-RP 1.0 (8B)
$0.0011
129
GLM 4.5 Air
$0.0011
130
Weaver (alpha)
$0.0011
131
MiniMax M2-her
$0.0011
132
GPT-5.1-Codex-Mini
$0.0011
133
Mistral Medium 3
$0.0012
134
Cogito v2.1 671B
$0.0012
135
DeepSeek V3.1 Nex N1
$0.0012
136
Mistral Large 3 2512
$0.0012
137
ERNIE 4.5 VL 424B A47B
$0.0012
138
R1 Distill Qwen 32B
$0.0013
139
Qwen3 Coder 480B A35B
$0.0013
140
Qwen Plus 0728
$0.0013
141
Qwen3 Coder Flash
$0.0013
142
Qwen-Plus
$0.0013
143
Qwen3 Coder 480B A35B (exacto)
$0.0013
144
Nemotron Nano 12B 2 VL
$0.0013
145
Qwen3 235B A22B
$0.0013
146
Llama 3.1 Nemotron Ultra 253B v1
$0.0014
147
R1 Distill Llama 70B
$0.0014
148
Llama 3 Euryale 70B v2.1
$0.0014
149
Qwen2.5 VL 32B Instruct
$0.0014
150
Morph V3 Large
$0.0014
151
Qwen3 Coder Next
$0.0014
152
MiniMax M2.1
$0.0015
153
Noromaid 20B
$0.0015
154
Llama 3.1 Nemotron 70B Instruct
$0.0015
155
GPT-3.5 Turbo (older v0613)
$0.0015
156
Hermes 4 405B
$0.0015
157
Qwen3 VL 32B Instruct
$0.0016
158
GPT-3.5 Turbo Instruct
$0.0016
159
Nova Pro 1.0
$0.0016
160
Kimi K2 0711
$0.0016
161
GLM 4.7 Flash
$0.0016
162
Kimi Dev 72B
$0.0017
163
GLM 4.5V
$0.0017
164
Mistral Medium 3.1
$0.0017
165
Gemini 3 Flash Preview
$0.0018
166
CodeLLaMa 7B Instruct Solidity
$0.0018
167
GLM 4.6V
$0.0018
168
Olmo 3 32B Think
$0.0019
169
Claude 3.5 Haiku
$0.0020
170
MiniMax M2
$0.0020
171
Olmo 3.1 32B Think
$0.0020
172
Grok Code Fast 1
$0.0022
173
Qwen3 VL 30B A3B Thinking
$0.0022
174
GPT-5 Mini
$0.0023
175
Gemini 2.5 Flash
$0.0025
176
DeepSeek V3.2 Speciale
$0.0026
177
GLM 4.6 (exacto)
$0.0026
178
Relace Search
$0.0026
179
Hermes 3 70B Instruct
$0.0027
180
Nova 2 Lite
$0.0028
181
Gemini 2.5 Flash Preview 09-2025
$0.0028
182
MiniMax M1
$0.0029
183
Switchpoint Router
$0.0030
184
Cogito V2 Preview Llama 405B
$0.0030
185
Seed 1.6
$0.0030
186
Qwen VL Max
$0.0031
187
Llemma 7b
$0.0031
188
Gemini 2.5 Flash Image (Nano Banana)
$0.0031
189
Llama 3.1 70B Hanami x1
$0.0032
190
Qwen3 235B A22B Thinking 2507
$0.0032
191
Step3
$0.0032
192
Kimi K2 0905
$0.0033
193
Mixtral 8x22B Instruct
$0.0033
194
GPT-5.1 Chat
$0.0037
195
GPT-5.1-Codex
$0.0037
196
GLM 4.5
$0.0037
197
Kimi K2 0905 (exacto)
$0.0039
198
Qwen3 Coder Plus
$0.0040
199
Mistral Large 2411
$0.0042
200
R1
$0.0042
201
GPT-5 Image Mini
$0.0043
202
Claude Haiku 4.5
$0.0043
203
Palmyra X5
$0.0046
204
Command A
$0.0046
205
Mistral Large
$0.0047
206
Mistral Large 2407
$0.0047
207
Pixtral Large 2411
$0.0048
208
GPT-4.1
$0.0048
209
Command R+ (08-2024)
$0.0050
210
Qwen3 Next 80B A3B Thinking
$0.0050
211
Qwen-Max
$0.0050
212
Inflection 3 Productivity
$0.0051
213
Qwen3 Max
$0.0051
214
Inflection 3 Pi
$0.0051
215
Kimi K2 Thinking
$0.0053
216
GPT-4o
$0.0053
217
GPT-4o (2024-08-06)
$0.0053
218
SorcererLM 8x22B
$0.0056
219
GPT-5 Chat
$0.0056
220
Nova Premier 1.0
$0.0057
221
GPT-5 Codex
$0.0057
222
R1 0528
$0.0057
223
GLM 4.6
$0.0058
224
Qwen3 VL 235B A22B Thinking
$0.0062
225
GLM 4.7
$0.0063
226
Goliath 120B
$0.0063
227
Sonar
$0.0063
228
Qwen3 VL 8B Thinking
$0.0066
229
o3 Mini High
$0.0068
230
o3 Mini
$0.0072
231
Kimi K2.5
$0.0073
232
o4 Mini
$0.0075
233
GPT-4o (2024-11-20)
$0.0075
234
Morph V3 Fast
$0.0079
235
Jamba Large 1.7
$0.0085
236
GPT-5.2 Chat
$0.0087
237
Qwen Plus 0728 (thinking)
$0.0091
238
GPT-4o (2024-05-13)
$0.0095
239
GPT-5.2-Codex
$0.0103
240
GPT-5.2
$0.0107
241
Aion-1.0
$0.0109
242
ChatGPT-4o
$0.0112
243
Claude Sonnet 4
$0.0112
244
GPT-5.1
$0.0115
245
o3
$0.0115
246
o4 Mini High
$0.0117
247
Claude 3.7 Sonnet
$0.0126
248
GPT-5
$0.0128
249
Claude Sonnet 4.5
$0.0132
250
Grok 3 Beta
$0.0133
251
Grok 3
$0.0139
252
GPT-5.1-Codex-Max
$0.0155
253
Sonar Pro
$0.0166
254
Claude 3.5 Sonnet
$0.0167
255
Sonar Reasoning Pro
$0.0174
256
GPT-5 Image
$0.0197
257
GPT-4 Turbo
$0.0210
258
GPT-4 Turbo Preview
$0.0221
259
Auto Router
$0.0239
260
Claude Opus 4.5
$0.0239
261
Grok 4
$0.0252
262
Claude Opus 4.6
$0.0254
263
Sonar Pro Search
$0.0280
264
Nano Banana Pro (Gemini 3 Pro Image Preview)
$0.0297
265
Gemini 2.5 Pro Preview 06-05
$0.0303
266
Gemini 2.5 Pro
$0.0305
267
Gemini 2.5 Pro Preview 05-06
$0.0305
268
Gemini 3 Pro Preview
$0.0319
269
GPT-4 (older v0314)
$0.0398
270
Claude 3.7 Sonnet (thinking)
$0.0417
271
GPT-4
$0.0427
272
Claude Opus 4
$0.0535
273
Claude Opus 4.1
$0.0566
274
o3 Pro
$0.1142
275
GPT-5.2 Pro
$0.1304
276
o1
$0.1363
277
o4 Mini Deep Research
$0.1823
278
o3 Deep Research
$0.8452
279
Sonar Deep Research
$1.1711
280
o1-pro
$1.3937
Mitjana:$0.0100
(280 modelos)
Menú de mètriques
Confiança mitjana
Nivell de confiança mitjà reportat pel model
1
o3 Pro
100.0%
2
Gemini 2.5 Pro Preview 06-05
100.0%
3
Claude Opus 4.5
100.0%
4
R1 0528
100.0%
5
o3 Deep Research
100.0%
6
GPT-5.2
100.0%
7
Auto Router
100.0%
8
o4 Mini Deep Research
99.9%
9
GPT-5.1
99.9%
10
Claude Opus 4
99.9%
11
GPT-5 Codex
99.9%
12
GPT-5.1-Codex-Max
99.9%
13
Gemini 2.5 Pro Preview 05-06
99.9%
14
Claude Opus 4.6
99.9%
15
o1-pro
99.9%
16
o4 Mini
99.9%
17
Claude Sonnet 4.5
99.9%
18
GLM 4.5V
99.9%
19
GPT-5.1-Codex-Mini
99.9%
20
o1
99.9%
21
KAT-Coder-Pro V1
99.9%
22
Grok 4 Fast
99.8%
23
GPT-5.2-Codex
99.8%
24
GPT-5 Mini
99.8%
25
Qwen3 VL 30B A3B Thinking
99.8%
26
Sonar Deep Research
99.8%
27
Claude Sonnet 4
99.8%
28
o3 Mini
99.8%
29
Qwen3 VL 8B Thinking
99.8%
30
Mistral Large 3 2512
99.8%
31
ChatGPT-4o
99.8%
32
Qwen3 Next 80B A3B Instruct
99.8%
33
gpt-oss-20b
99.8%
34
Qwen3 Coder Flash
99.8%
35
Gemini 3 Flash Preview
99.7%
36
Nano Banana Pro (Gemini 3 Pro Image Preview)
99.7%
37
Aion-1.0
99.7%
38
o3
99.5%
39
o4 Mini High
99.5%
40
gpt-oss-120b
99.5%
41
Gemini 2.5 Flash Lite Preview 09-2025
99.5%
42
GPT-5 Image
99.5%
43
Gemini 3 Pro Preview
99.5%
44
Grok 4
99.5%
45
GPT-4.1 Mini
99.5%
46
GPT-4.1
99.5%
47
GLM 4.6V
99.5%
48
Qwen-Plus
99.5%
49
Palmyra X5
99.4%
50
Relace Search
99.4%
51
GPT-5.1 Chat
99.4%
52
Gemini 2.5 Pro
99.4%
53
Kimi K2.5
99.4%
54
Qwen Plus 0728 (thinking)
99.4%
55
Claude 3.7 Sonnet (thinking)
99.4%
56
Step3
99.4%
57
Qwen3 VL 30B A3B Instruct
99.4%
58
Qwen Plus 0728
99.4%
59
Qwen3 VL 235B A22B Instruct
99.4%
60
Mistral Large 2411
99.4%
61
Gemini 2.5 Flash Preview 09-2025
99.4%
62
o3 Mini High
99.4%
63
Grok 4.1 Fast
99.4%
64
Claude Opus 4.1
99.4%
65
Qwen3 235B A22B
99.4%
66
GPT-5.1-Codex
99.3%
67
GPT-4o (2024-05-13)
99.3%
68
ERNIE 4.5 300B A47B
99.3%
69
GPT-5
99.3%
70
Qwen3 Coder 480B A35B (exacto)
99.3%
71
Seed 1.6
99.3%
72
gpt-oss-safeguard-20b
99.3%
73
Qwen3 Coder 480B A35B
99.3%
74
Ministral 3 8B 2512
99.3%
75
Qwen3 235B A22B Thinking 2507
99.3%
76
Mistral Large 2407
99.2%
77
QwQ 32B
99.2%
78
Seed 1.6 Flash
99.1%
79
MiMo-V2-Flash
99.1%
80
GPT-4.1 Nano
99.1%
81
Qwen3 30B A3B Instruct 2507
99.1%
82
Qwen2.5 VL 32B Instruct
99.1%
83
GPT-5.2 Chat
99.0%
84
GPT-5 Chat
99.0%
85
gpt-oss-120b (exacto)
99.0%
86
Nemotron 3 Nano 30B A3B
99.0%
87
GPT-5.2 Pro
99.0%
88
Claude 3.5 Sonnet
99.0%
89
Qwen3 Coder 30B A3B Instruct
99.0%
90
GLM 4.7
99.0%
91
DeepSeek V3.1 Terminus
99.0%
92
ERNIE 4.5 VL 424B A47B
99.0%
93
Mistral Large
99.0%
94
MiniMax M2
99.0%
95
Gemma 3 27B
99.0%
96
GPT-5 Image Mini
99.0%
97
Switchpoint Router
99.0%
98
Nova Premier 1.0
99.0%
99
Qwen3 VL 235B A22B Thinking
99.0%
100
Mercury Coder
98.9%
101
Devstral 2 2512
98.9%
102
R1 Distill Qwen 32B
98.9%
103
Mistral Medium 3.1
98.9%
104
Gemma 3 4B
98.9%
105
Gemini 2.5 Flash Lite
98.8%
106
GPT-3.5 Turbo
98.8%
107
Sonar
98.8%
108
Qwen3 VL 32B Instruct
98.8%
109
Command R (08-2024)
98.8%
110
Qwen3 235B A22B Instruct 2507
98.8%
111
Qwen2.5 VL 72B Instruct
98.8%
112
Llama 3.3 Nemotron Super 49B V1.5
98.7%
113
DeepSeek V3
98.7%
114
Tongyi DeepResearch 30B A3B
98.7%
115
GPT-4o-mini
98.6%
116
Claude Haiku 4.5
98.6%
117
GLM 4.6
98.6%
118
GPT-5 Nano
98.6%
119
Llama 3.1 Nemotron Ultra 253B v1
98.5%
120
GLM 4.5
98.5%
121
Command A
98.5%
122
Gemma 3 12B
98.5%
123
Mistral Medium 3
98.5%
124
GPT-3.5 Turbo (older v0613)
98.5%
125
DeepSeek V3.1 Terminus (exacto)
98.5%
126
DeepSeek V3.2 Exp
98.5%
127
Voxtral Small 24B 2507
98.5%
128
Gemini 2.5 Flash
98.5%
129
Qwen-Max
98.4%
130
ERNIE 4.5 21B A3B Thinking
98.4%
131
R1
98.4%
132
DeepSeek V3 0324
98.4%
133
GPT-4 Turbo
98.3%
134
DeepSeek V3.2
98.3%
135
GLM 4.7 Flash
98.3%
136
Qwen VL Plus
98.2%
137
Pixtral Large 2411
98.2%
138
Jamba Large 1.7
98.2%
139
Mistral Small 3.1 24B
98.2%
140
Claude 3.5 Haiku
98.2%
141
Grok 3
98.1%
142
Llama 4 Maverick
98.1%
143
GPT-4o (2024-11-20)
98.1%
144
GLM 4 32B
98.0%
145
GPT-4o-mini (2024-07-18)
98.0%
146
Solar Pro 3
98.0%
147
Gemini 2.0 Flash Lite
98.0%
148
Mistral Small Creative
98.0%
149
GLM 4.6 (exacto)
98.0%
150
Qwen VL Max
98.0%
151
Qwen3 32B
97.9%
152
Qwen3 Coder Next
97.9%
153
Llama 4 Scout
97.9%
154
Nova Lite 1.0
97.9%
155
Grok 3 Beta
97.9%
156
GPT-3.5 Turbo 16k
97.9%
157
R1 Distill Llama 70B
97.9%
158
Qwen3 Next 80B A3B Thinking
97.8%
159
Devstral Medium
97.7%
160
Nova Pro 1.0
97.7%
161
GPT-4o-mini Search Preview
97.7%
162
Ministral 3 14B 2512
97.7%
163
DeepSeek V3.1
97.6%
164
Sonar Pro
97.6%
165
Claude 3.7 Sonnet
97.6%
166
Qwen3 30B A3B Thinking 2507
97.6%
167
Qwen3 14B
97.5%
168
GPT-4 Turbo Preview
97.5%
169
Gemini 2.0 Flash
97.5%
170
Qwen3 8B
97.5%
171
Step 3.5 Flash
97.5%
172
Kimi K2 0711
97.4%
173
Grok Code Fast 1
97.4%
174
Qwen3 Max
97.4%
175
GPT-4o (2024-08-06)
97.4%
176
Gemini 2.5 Flash Image (Nano Banana)
97.3%
177
ERNIE 4.5 21B A3B
97.2%
178
Mistral Small 3.2 24B
97.2%
179
Qwen3 Coder Plus
97.2%
180
Trinity Large Preview
97.1%
181
Nova 2 Lite
97.1%
182
GPT-4o
97.1%
183
Grok 3 Mini
97.0%
184
Mercury
97.0%
185
Nemotron Nano 12B 2 VL
97.0%
186
Saba
97.0%
187
MiMo-V2-Flash
96.9%
188
GPT-4
96.9%
189
Olmo 3 7B Think
96.9%
190
MiniMax M1
96.9%
191
Grok 3 Mini Beta
96.8%
192
Hermes 4 405B
96.8%
193
Llama 3.1 70B Instruct
96.7%
194
Phi 4
96.7%
195
Qwen2.5 72B Instruct
96.7%
196
ERNIE 4.5 VL 28B A3B
96.6%
197
Mixtral 8x22B Instruct
96.5%
198
GPT-4 (older v0314)
96.5%
199
Cogito V2 Preview Llama 70B
96.4%
200
Claude 3 Haiku
96.4%
201
Ministral 3 3B 2512
96.3%
202
Qwen-Turbo
96.1%
203
DeepSeek V3.1 Nex N1
96.0%
204
Nemotron Nano 9B V2
95.8%
205
Aion-1.0-Mini
95.8%
206
Devstral Small 1.1
95.7%
207
GPT-4o Search Preview
95.6%
208
Jamba Mini 1.7
95.6%
209
Sonar Pro Search
95.6%
210
LFM2-8B-A1B
95.5%
211
Inflection 3 Productivity
95.5%
212
Codestral 2508
95.5%
213
GPT-3.5 Turbo Instruct
95.4%
214
Kimi K2 Thinking
95.4%
215
Inflection 3 Pi
95.4%
216
Lumimaid v0.2 8B
95.3%
217
DeepSeek V3.2 Speciale
95.2%
218
Llama 3.1 Nemotron 70B Instruct
95.1%
219
Cydonia 24B V4.1
95.0%
220
Mixtral 8x7B Instruct
94.9%
221
Qwen3 VL 8B Instruct
94.8%
222
Mistral Small 3
94.8%
223
Cogito v2.1 671B
94.7%
224
Granite 4.0 Micro
94.6%
225
Cogito V2 Preview Llama 405B
94.4%
226
Skyfall 36B V2
94.3%
227
GPT-4 Turbo (older v1106)
94.3%
228
Sonar Reasoning Pro
94.2%
229
MiniMax M2-her
94.2%
230
Llama 3.1 70B Hanami x1
94.1%
231
Gemma 3n 4B
94.1%
232
Olmo 3.1 32B Instruct
94.0%
233
Llama 3.3 70B Instruct
94.0%
234
Free Models Router
93.9%
235
Hermes 3 405B Instruct
93.3%
236
MiniMax M2.1
93.2%
237
GLM 4.5 Air
93.2%
238
Ministral 8B
93.2%
239
Kimi K2 0905
93.2%
240
Llama 3 Euryale 70B v2.1
93.1%
241
Trinity Mini
93.0%
242
Gemma 2 27B
92.9%
243
Nova Micro 1.0
92.5%
244
Mistral 7B Instruct v0.2
92.0%
245
Mistral Nemo
91.9%
246
SorcererLM 8x22B
91.9%
247
Llama 3.3 Euryale 70B
91.8%
248
Qwen2.5 Coder 32B Instruct
91.8%
249
Command R7B (12-2024)
91.5%
250
Llama 3.1 Euryale 70B v2.2
91.4%
251
Hermes 4 70B
91.3%
252
Kimi K2 0905 (exacto)
91.3%
253
Mistral 7B Instruct v0.3
90.8%
254
Mistral Tiny
90.6%
255
Command R+ (08-2024)
90.1%
256
Mistral 7B Instruct
90.0%
257
Olmo 3 32B Think
89.5%
258
Pixtral 12B
89.4%
259
Molmo2 8B
89.0%
260
Goliath 120B
88.6%
261
Llama 3 70B Instruct
88.5%
262
Olmo 3.1 32B Think
88.3%
263
Llama 3 8B Lunaris
87.9%
264
Rnj 1 Instruct
87.7%
265
Ministral 3B
87.0%
266
Gemma 2 9B
86.8%
267
Llama 3 8B Instruct
86.7%
268
Kimi Dev 72B
86.6%
269
Hermes 2 Pro - Llama-3 8B
86.5%
270
Olmo 3 7B Instruct
84.0%
271
Qwen2.5 7B Instruct
82.8%
272
Llama 3.2 3B Instruct
82.5%
273
Hunyuan A13B Instruct
81.7%
274
Weaver (alpha)
78.9%
275
Noromaid 20B
78.7%
276
Mistral 7B Instruct v0.1
78.2%
277
Llama 3.1 8B Instruct
77.5%
278
Qwen2.5-VL 7B Instruct
76.8%
279
ReMM SLERP 13B
76.3%
280
MythoMax 13B
70.3%
281
Rocinante 12B
66.5%
282
Hermes 3 70B Instruct
65.3%
283
UnslopNemo 12B
59.4%
284
Aion-RP 1.0 (8B)
55.5%
285
Llama 3.2 1B Instruct
47.1%
286
Llama 3.2 11B Vision Instruct
45.4%
287
Morph V3 Fast
37.4%
288
Morph V3 Large
34.7%
289
Llemma 7b
28.6%
290
CodeLLaMa 7B Instruct Solidity
17.8%
Mitjana:94.7%
(290 modelos)
Menú de mètriques
Cost total
Cost total en USD per a avaluar totes les preguntes
1
LFM2-8B-A1B
$0.00
2
Ministral 3B
$0.01
3
Gemma 3n 4B
$0.01
4
Mistral Nemo
$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
Llama 3.1 8B Instruct
$0.02
16
GLM 4 32B
$0.02
17
Nova Micro 1.0
$0.02
18
Pixtral 12B
$0.02
19
Mistral Small 3
$0.02
20
Phi 4
$0.02
21
Voxtral Small 24B 2507
$0.03
22
Gemma 3 12B
$0.03
23
Hermes 2 Pro - Llama-3 8B
$0.03
24
Llama 3.2 1B Instruct
$0.03
25
Ministral 3 3B 2512
$0.03
26
Qwen-Turbo
$0.03
27
Devstral Small 1.1
$0.03
28
Nova Lite 1.0
$0.03
29
Mistral 7B Instruct v0.1
$0.03
30
Rnj 1 Instruct
$0.04
31
Mistral Small 3.2 24B
$0.04
32
Gemma 3 27B
$0.04
33
Gemini 2.0 Flash Lite
$0.04
34
Mistral 7B Instruct v0.3
$0.04
35
Mistral 7B Instruct
$0.04
36
gpt-oss-120b (exacto)
$0.04
37
ERNIE 4.5 21B A3B
$0.04
38
Qwen2.5-VL 7B Instruct
$0.04
39
Ministral 3 8B 2512
$0.04
40
Llama 3.2 11B Vision Instruct
$0.04
41
Mistral 7B Instruct v0.2
$0.04
42
GPT-4.1 Nano
$0.05
43
Molmo2 8B
$0.05
44
gpt-oss-20b
$0.05
45
Lumimaid v0.2 8B
$0.05
46
Gemini 2.0 Flash
$0.05
47
Mistral Tiny
$0.05
48
Olmo 3 7B Instruct
$0.05
49
Qwen3 Coder 30B A3B Instruct
$0.05
50
Hermes 4 70B
$0.05
51
Nemotron Nano 9B V2
$0.06
52
Llama 4 Scout
$0.06
53
Qwen2.5 72B Instruct
$0.06
54
Ministral 3 14B 2512
$0.06
55
Jamba Mini 1.7
$0.06
56
Qwen2.5 Coder 32B Instruct
$0.06
57
Qwen3 14B
$0.06
58
Saba
$0.07
59
Command R (08-2024)
$0.07
60
gpt-oss-safeguard-20b
$0.07
61
Mistral Small 3.1 24B
$0.07
62
Qwen3 30B A3B Instruct 2507
$0.07
63
UnslopNemo 12B
$0.07
64
Rocinante 12B
$0.08
65
Hunyuan A13B Instruct
$0.08
66
MiMo-V2-Flash
$0.08
67
Qwen3 8B
$0.08
68
KAT-Coder-Pro V1
$0.08
69
Llama 3.1 70B Instruct
$0.09
70
DeepSeek V3.2 Exp
$0.09
71
Cydonia 24B V4.1
$0.09
72
Gemma 2 27B
$0.09
73
Seed 1.6 Flash
$0.09
74
Llama 3 70B Instruct
$0.09
75
DeepSeek V3.2
$0.09
76
Gemini 2.5 Flash Lite
$0.10
77
Gemini 2.5 Flash Lite Preview 09-2025
$0.10
78
Llama 3.3 70B Instruct
$0.10
79
gpt-oss-120b
$0.10
80
GPT-4o-mini (2024-07-18)
$0.10
81
Mistral Small Creative
$0.10
82
GPT-4o-mini
$0.10
83
Codestral 2508
$0.11
84
Mercury Coder
$0.11
85
Mercury
$0.11
86
ReMM SLERP 13B
$0.11
87
Qwen2.5 VL 72B Instruct
$0.12
88
Llama 4 Maverick
$0.12
89
Trinity Mini
$0.12
90
Qwen3 VL 8B Instruct
$0.12
91
Olmo 3.1 32B Instruct
$0.12
92
DeepSeek V3.1 Terminus (exacto)
$0.12
93
DeepSeek V3
$0.12
94
Mixtral 8x7B Instruct
$0.12
95
Qwen VL Plus
$0.13
96
Skyfall 36B V2
$0.13
97
Olmo 3 7B Think
$0.14
98
ERNIE 4.5 300B A47B
$0.14
99
DeepSeek V3.1
$0.14
100
Qwen3 30B A3B Thinking 2507
$0.14
101
Claude 3 Haiku
$0.14
102
Qwen3 VL 235B A22B Instruct
$0.14
103
Qwen3 32B
$0.14
104
Llama 3.3 Nemotron Super 49B V1.5
$0.14
105
ERNIE 4.5 VL 28B A3B
$0.14
106
Grok 4 Fast
$0.15
107
Qwen3 235B A22B Instruct 2507
$0.15
108
Aion-1.0-Mini
$0.15
109
GPT-3.5 Turbo
$0.15
110
Qwen3 VL 30B A3B Instruct
$0.15
111
Tongyi DeepResearch 30B A3B
$0.15
112
DeepSeek V3.1 Terminus
$0.16
113
Grok 4.1 Fast
$0.16
114
Cogito V2 Preview Llama 70B
$0.16
115
Llama 3.3 Euryale 70B
$0.16
116
Hermes 3 405B Instruct
$0.17
117
ERNIE 4.5 21B A3B Thinking
$0.17
118
Llama 3.1 Euryale 70B v2.2
$0.18
119
Nemotron 3 Nano 30B A3B
$0.18
120
GPT-5 Nano
$0.18
121
Grok 3 Mini Beta
$0.19
122
QwQ 32B
$0.19
123
Grok 3 Mini
$0.19
124
GPT-4.1 Mini
$0.20
125
DeepSeek V3 0324
$0.20
126
Qwen3 Next 80B A3B Instruct
$0.20
127
Devstral Medium
$0.21
128
Aion-RP 1.0 (8B)
$0.21
129
GLM 4.5 Air
$0.22
130
Weaver (alpha)
$0.22
131
MiniMax M2-her
$0.22
132
GPT-5.1-Codex-Mini
$0.22
133
Mistral Medium 3
$0.23
134
Cogito v2.1 671B
$0.23
135
DeepSeek V3.1 Nex N1
$0.24
136
Mistral Large 3 2512
$0.24
137
ERNIE 4.5 VL 424B A47B
$0.24
138
R1 Distill Qwen 32B
$0.25
139
Qwen3 Coder 480B A35B
$0.26
140
Qwen Plus 0728
$0.26
141
Qwen3 Coder Flash
$0.26
142
Qwen-Plus
$0.26
143
Qwen3 Coder 480B A35B (exacto)
$0.26
144
Nemotron Nano 12B 2 VL
$0.27
145
Qwen3 235B A22B
$0.27
146
Llama 3.1 Nemotron Ultra 253B v1
$0.28
147
R1 Distill Llama 70B
$0.28
148
Llama 3 Euryale 70B v2.1
$0.28
149
Qwen2.5 VL 32B Instruct
$0.28
150
Morph V3 Large
$0.28
151
Qwen3 Coder Next
$0.28
152
MiniMax M2.1
$0.29
153
Noromaid 20B
$0.29
154
Llama 3.1 Nemotron 70B Instruct
$0.30
155
GPT-3.5 Turbo (older v0613)
$0.31
156
Hermes 4 405B
$0.31
157
Qwen3 VL 32B Instruct
$0.31
158
GPT-3.5 Turbo Instruct
$0.31
159
Nova Pro 1.0
$0.32
160
Kimi K2 0711
$0.32
161
GLM 4.7 Flash
$0.33
162
Kimi Dev 72B
$0.34
163
GLM 4.5V
$0.34
164
Mistral Medium 3.1
$0.35
165
Gemini 3 Flash Preview
$0.35
166
CodeLLaMa 7B Instruct Solidity
$0.36
167
GLM 4.6V
$0.37
168
Olmo 3 32B Think
$0.38
169
Claude 3.5 Haiku
$0.40
170
MiniMax M2
$0.40
171
Olmo 3.1 32B Think
$0.41
172
Grok Code Fast 1
$0.45
173
Qwen3 VL 30B A3B Thinking
$0.45
174
GPT-5 Mini
$0.46
175
Gemini 2.5 Flash
$0.51
176
DeepSeek V3.2 Speciale
$0.51
177
GLM 4.6 (exacto)
$0.52
178
Relace Search
$0.52
179
Hermes 3 70B Instruct
$0.54
180
Nova 2 Lite
$0.56
181
Gemini 2.5 Flash Preview 09-2025
$0.57
182
MiniMax M1
$0.58
183
Switchpoint Router
$0.59
184
Cogito V2 Preview Llama 405B
$0.61
185
Seed 1.6
$0.61
186
Qwen VL Max
$0.62
187
Llemma 7b
$0.63
188
Gemini 2.5 Flash Image (Nano Banana)
$0.63
189
Llama 3.1 70B Hanami x1
$0.63
190
Qwen3 235B A22B Thinking 2507
$0.64
191
Step3
$0.64
192
Kimi K2 0905
$0.66
193
Mixtral 8x22B Instruct
$0.66
194
GPT-5.1 Chat
$0.73
195
GPT-5.1-Codex
$0.74
196
GLM 4.5
$0.74
197
Kimi K2 0905 (exacto)
$0.79
198
Qwen3 Coder Plus
$0.79
199
Mistral Large 2411
$0.83
200
R1
$0.84
201
GPT-5 Image Mini
$0.86
202
Claude Haiku 4.5
$0.87
203
Palmyra X5
$0.91
204
Command A
$0.93
205
Mistral Large
$0.93
206
Mistral Large 2407
$0.94
207
Pixtral Large 2411
$0.95
208
GPT-4.1
$0.96
209
Command R+ (08-2024)
$0.99
210
Qwen3 Next 80B A3B Thinking
$0.99
211
Qwen-Max
$1.00
212
Inflection 3 Productivity
$1.01
213
Qwen3 Max
$1.02
214
Inflection 3 Pi
$1.02
215
Kimi K2 Thinking
$1.05
216
GPT-4o
$1.05
217
GPT-4o (2024-08-06)
$1.06
218
SorcererLM 8x22B
$1.12
219
GPT-5 Chat
$1.12
220
Nova Premier 1.0
$1.14
221
GPT-5 Codex
$1.14
222
R1 0528
$1.14
223
GLM 4.6
$1.16
224
Qwen3 VL 235B A22B Thinking
$1.23
225
GLM 4.7
$1.25
226
Goliath 120B
$1.26
227
Sonar
$1.27
228
Qwen3 VL 8B Thinking
$1.32
229
o3 Mini High
$1.35
230
o3 Mini
$1.44
231
Kimi K2.5
$1.46
232
o4 Mini
$1.50
233
GPT-4o (2024-11-20)
$1.50
234
Morph V3 Fast
$1.58
235
Jamba Large 1.7
$1.71
236
GPT-5.2 Chat
$1.74
237
Qwen Plus 0728 (thinking)
$1.83
238
GPT-4o (2024-05-13)
$1.90
239
GPT-5.2-Codex
$2.06
240
GPT-5.2
$2.14
241
Aion-1.0
$2.17
242
ChatGPT-4o
$2.23
243
Claude Sonnet 4
$2.23
244
GPT-5.1
$2.29
245
o3
$2.30
246
o4 Mini High
$2.33
247
Claude 3.7 Sonnet
$2.53
248
GPT-5
$2.56
249
Claude Sonnet 4.5
$2.64
250
Grok 3 Beta
$2.67
251
Grok 3
$2.78
252
GPT-5.1-Codex-Max
$3.09
253
Sonar Pro
$3.32
254
Claude 3.5 Sonnet
$3.34
255
Sonar Reasoning Pro
$3.49
256
GPT-5 Image
$3.95
257
GPT-4 Turbo
$4.20
258
GPT-4 Turbo Preview
$4.42
259
Auto Router
$4.77
260
Claude Opus 4.5
$4.78
261
Grok 4
$5.04
262
Claude Opus 4.6
$5.09
263
Sonar Pro Search
$5.61
264
Nano Banana Pro (Gemini 3 Pro Image Preview)
$5.94
265
Gemini 2.5 Pro Preview 06-05
$6.06
266
Gemini 2.5 Pro
$6.09
267
Gemini 2.5 Pro Preview 05-06
$6.11
268
Gemini 3 Pro Preview
$6.38
269
GPT-4 (older v0314)
$7.96
270
Claude 3.7 Sonnet (thinking)
$8.35
271
GPT-4
$8.55
272
Claude Opus 4
$10.70
273
Claude Opus 4.1
$11.31
274
o3 Pro
$22.85
275
GPT-5.2 Pro
$26.08
276
o1
$27.26
277
o4 Mini Deep Research
$36.45
278
o3 Deep Research
$169.04
279
Sonar Deep Research
$234.22
280
o1-pro
$278.74
Total:$1041.37
Mitjana:$3.71
(280 modelos)
Menú de mètriques
Tokens de raonament
Tokens utilitzats en el procés de raonament
1
Hermes 4 70B
501
2
GLM 4.5 Air
6K
3
GPT-5.1 Chat
10K
4
GPT-5.2 Chat
24K
5
GPT-5.1-Codex
28K
6
DeepSeek V3.1 Terminus
33K
7
DeepSeek V3.2
39K
8
GPT-5.2 Pro
44K
9
GPT-5.2
44K
10
GPT-5.1-Codex-Mini
53K
11
DeepSeek V3.2 Exp
57K
12
GLM 4.5V
58K
13
GPT-5 Codex
66K
14
gpt-oss-120b
80K
15
gpt-oss-120b (exacto)
83K
16
o3 Pro
88K
17
o3
91K
18
GPT-5.1
94K
19
GPT-5.2-Codex
94K
20
o3 Mini High
115K
21
gpt-oss-20b
121K
22
o3 Mini
124K
23
o4 Mini
125K
24
gpt-oss-safeguard-20b
127K
25
GLM 4.6 (exacto)
127K
26
Grok 4 Fast
130K
27
Nemotron Nano 9B V2
130K
28
GPT-5 Mini
136K
29
GPT-5 Image Mini
141K
30
MiniMax M2.1
151K
31
Grok Code Fast 1
154K
32
R1 Distill Llama 70B
161K
33
MiniMax M1
161K
34
GLM 4.5
163K
35
R1 Distill Qwen 32B
166K
36
GPT-5 Image
167K
37
R1
177K
38
Qwen3 14B
178K
39
GPT-5
181K
40
Grok 4.1 Fast
181K
41
Free Models Router
183K
42
o1
185K
43
Grok 3 Mini
186K
44
Grok 3 Mini Beta
188K
45
o1-pro
189K
46
Seed 1.6
189K
47
Seed 1.6 Flash
195K
48
Qwen3 32B
195K
49
Qwen3 VL 235B A22B Thinking
201K
50
Grok 4
201K
51
Kimi Dev 72B
206K
52
o4 Mini High
219K
53
Qwen3 235B A22B
226K
54
Qwen3 8B
234K
55
R1 0528
237K
56
Step3
242K
57
MiniMax M2
250K
58
GLM 4.6V
255K
59
Tongyi DeepResearch 30B A3B
257K
60
GPT-5.1-Codex-Max
257K
61
Llama 3.3 Nemotron Super 49B V1.5
269K
62
Kimi K2 Thinking
273K
63
Qwen3 30B A3B Thinking 2507
277K
64
Solar Pro 3
291K
65
Nano Banana Pro (Gemini 3 Pro Image Preview)
305K
66
Qwen3 VL 30B A3B Thinking
311K
67
Qwen3 235B A22B Thinking 2507
315K
68
Qwen Plus 0728 (thinking)
317K
69
QwQ 32B
318K
70
Kimi K2.5
327K
71
Nemotron Nano 12B 2 VL
346K
72
Claude 3.7 Sonnet (thinking)
348K
73
Gemini 3 Pro Preview
363K
74
GPT-5 Nano
371K
75
GLM 4.6
387K
76
Gemini 2.5 Pro Preview 06-05
406K
77
Gemini 2.5 Pro
410K
78
Gemini 2.5 Pro Preview 05-06
410K
79
ERNIE 4.5 21B A3B Thinking
443K
80
DeepSeek V3.2 Speciale
445K
81
GLM 4.7
466K
82
Step 3.5 Flash
489K
83
Qwen3 VL 8B Thinking
519K
84
Olmo 3 7B Think
544K
85
Qwen3 Next 80B A3B Thinking
562K
86
Olmo 3 32B Think
669K
87
GLM 4.7 Flash
673K
88
Nemotron 3 Nano 30B A3B
710K
89
Olmo 3.1 32B Think
721K
90
Trinity Mini
750K
91
o4 Mini Deep Research
1.6M
92
o3 Deep Research
1.7M
93
Sonar Deep Research
68.0M
Total:92.7M
Mitjana:996K
(93 modelos)
Menú de mètriques
Tokens eixints
Tokens generats en les respostes
1
Gemma 2 27B
47K
2
Mistral Nemo
54K
3
Voxtral Small 24B 2507
55K
4
Aion-1.0-Mini
56K
5
Ministral 3B
57K
6
GPT-5.1 Chat
61K
7
Lumimaid v0.2 8B
62K
8
GPT-5.1-Codex
62K
9
Gemma 2 9B
62K
10
Devstral Small 1.1
63K
11
GPT-3.5 Turbo 16k
63K
12
Llama 3 70B Instruct
64K
13
Nova Premier 1.0
65K
14
GPT-3.5 Turbo
66K
15
Mistral Tiny
67K
16
Mistral Small 3.1 24B
68K
17
Hermes 3 405B Instruct
68K
18
Mistral 7B Instruct v0.3
69K
19
Hermes 4 405B
69K
20
Ministral 8B
69K
21
Command A
69K
22
Nova Pro 1.0
70K
23
Skyfall 36B V2
71K
24
Mistral 7B Instruct
71K
25
Mistral Small 3
71K
26
Command R7B (12-2024)
71K
27
Llama 3 8B Lunaris
72K
28
MythoMax 13B
73K
29
Cogito V2 Preview Llama 405B
73K
30
GPT-4o-mini (2024-07-18)
75K
31
Claude 3.5 Haiku
75K
32
GPT-4o-mini
76K
33
Command R+ (08-2024)
76K
34
Inflection 3 Productivity
77K
35
ReMM SLERP 13B
77K
36
Mistral Small 3.2 24B
78K
37
Saba
78K
38
Inflection 3 Pi
78K
39
Mixtral 8x22B Instruct
79K
40
Mistral 7B Instruct v0.1
79K
41
GPT-4o
81K
42
GPT-4o (2024-08-06)
81K
43
GPT-3.5 Turbo Instruct
83K
44
GPT-4 (older v0314)
83K
45
KAT-Coder-Pro V1
84K
46
Cogito v2.1 671B
84K
47
Mercury Coder
85K
48
Cogito V2 Preview Llama 70B
85K
49
Devstral Medium
85K
50
Aion-RP 1.0 (8B)
85K
51
DeepSeek V3
85K
52
Codestral 2508
85K
53
Mercury
86K
54
Claude 3 Haiku
86K
55
GPT-4.1 Nano
87K
56
Claude 3.5 Sonnet
87K
57
Command R (08-2024)
87K
58
Pixtral 12B
87K
59
GLM 4 32B
87K
60
Gemini 2.0 Flash
88K
61
Hermes 2 Pro - Llama-3 8B
88K
62
Hermes 4 70B
89K
63
DeepSeek V3 0324
89K
64
Noromaid 20B
89K
65
Llama 3 Euryale 70B v2.1
89K
66
Llama 3.1 70B Instruct
90K
67
Nova Lite 1.0
91K
68
UnslopNemo 12B
91K
69
Gemma 3 12B
91K
70
Kimi K2 0905
92K
71
GPT-4
93K
72
Kimi K2 0905 (exacto)
93K
73
Morph V3 Large
93K
74
Devstral 2 2512
94K
75
GPT-4o (2024-05-13)
94K
76
Gemini 2.0 Flash Lite
95K
77
Mixtral 8x7B Instruct
95K
78
Mistral Medium 3
95K
79
GPT-4.1
95K
80
Mistral 7B Instruct v0.2
95K
81
ERNIE 4.5 300B A47B
96K
82
Cydonia 24B V4.1
96K
83
Granite 4.0 Micro
96K
84
GPT-4o Search Preview
97K
85
Gemma 3 4B
97K
86
Mistral Large 2411
97K
87
Gemini 3 Flash Preview
98K
88
GPT-5.1-Codex-Mini
98K
89
GPT-4.1 Mini
99K
90
GPT-4 Turbo (older v1106)
99K
91
Gemma 3 27B
100K
92
GPT-4o-mini Search Preview
100K
93
GPT-5 Chat
100K
94
Sonar Pro Search
102K
95
GPT-5 Codex
102K
96
Trinity Large Preview
103K
97
Qwen2.5 VL 72B Instruct
104K
98
GPT-4 Turbo
104K
99
Llama 3.1 70B Hanami x1
105K
100
Goliath 120B
105K
101
LFM2-8B-A1B
105K
102
Jamba Mini 1.7
106K
103
Qwen2.5-VL 7B Instruct
107K
104
Llama 4 Scout
107K
105
Qwen2.5 72B Instruct
108K
106
GPT-3.5 Turbo (older v0613)
109K
107
Molmo2 8B
109K
108
Hunyuan A13B Instruct
110K
109
Pixtral Large 2411
110K
110
Llama 3.3 70B Instruct
110K
111
Kimi K2 0711
112K
112
Llama 3.1 Euryale 70B v2.2
112K
113
Sonar
112K
114
GPT-5.2 Chat
112K
115
Llama 3.2 3B Instruct
113K
116
Nova Micro 1.0
113K
117
Llama 4 Maverick
114K
118
GPT-4 Turbo Preview
114K
119
ERNIE 4.5 21B A3B
115K
120
Qwen-Turbo
116K
121
ChatGPT-4o
116K
122
SorcererLM 8x22B
116K
123
Sonar Pro
116K
124
Weaver (alpha)
117K
125
Claude Opus 4
118K
126
Llama 3.3 Euryale 70B
119K
127
Llama 3.1 Nemotron Ultra 253B v1
120K
128
Qwen3 VL 235B A22B Instruct
120K
129
Qwen2.5 7B Instruct
120K
130
Llama 3.2 1B Instruct
121K
131
Gemma 3n 4B
124K
132
Claude Sonnet 4
124K
133
Mistral Large
124K
134
Mistral Large 2407
125K
135
Qwen2.5 Coder 32B Instruct
125K
136
DeepSeek V3.1 Terminus (exacto)
126K
137
GPT-4o (2024-11-20)
126K
138
Claude Opus 4.1
126K
139
Rocinante 12B
127K
140
Mistral Large 3 2512
127K
141
Rnj 1 Instruct
131K
142
Qwen-Max
132K
143
DeepSeek V3.1
133K
144
Phi 4
133K
145
GPT-5.2-Codex
135K
146
Qwen3 Coder 480B A35B
136K
147
Palmyra X5
137K
148
Qwen3 Coder Plus
138K
149
Qwen3 Coder 480B A35B (exacto)
139K
150
Llama 3 8B Instruct
139K
151
GPT-5.2
141K
152
Relace Search
141K
153
GPT-5.2 Pro
143K
154
Claude 3.7 Sonnet
144K
155
Qwen3 Coder 30B A3B Instruct
145K
156
Llama 3.1 Nemotron 70B Instruct
146K
157
DeepSeek V3.1 Nex N1
148K
158
Claude Haiku 4.5
149K
159
Qwen3 Max
149K
160
ERNIE 4.5 VL 424B A47B
150K
161
DeepSeek V3.1 Terminus
150K
162
DeepSeek V3.2
151K
163
Claude Sonnet 4.5
151K
164
MiniMax M2-her
152K
165
Qwen3 Coder Flash
152K
166
Switchpoint Router
152K
167
Mistral Medium 3.1
154K
168
Qwen VL Plus
155K
169
GLM 4.5V
156K
170
Qwen3 Next 80B A3B Instruct
156K
171
DeepSeek V3.2 Exp
161K
172
Qwen VL Max
161K
173
Olmo 3.1 32B Instruct
163K
174
gpt-oss-120b
164K
175
Ministral 3 14B 2512
164K
176
gpt-oss-120b (exacto)
166K
177
Claude Opus 4.5
167K
178
Gemini 2.5 Flash Image (Nano Banana)
167K
179
Qwen3 235B A22B Instruct 2507
168K
180
Auto Router
168K
181
Ministral 3 3B 2512
168K
182
o3 Mini High
171K
183
Grok 3
171K
184
Llama 3.2 11B Vision Instruct
171K
185
Grok 3 Beta
171K
186
o3
172K
187
Qwen3 VL 32B Instruct
172K
188
o3 Pro
173K
189
Qwen3 VL 8B Instruct
177K
190
Ministral 3 8B 2512
178K
191
Claude Opus 4.6
179K
192
o3 Mini
180K
193
Qwen Plus 0728
182K
194
Qwen-Plus
182K
195
Qwen3 30B A3B Instruct 2507
186K
196
Olmo 3 7B Instruct
187K
197
Jamba Large 1.7
187K
198
Gemini 2.5 Flash
187K
199
R1 Distill Llama 70B
188K
200
o4 Mini
192K
201
MiMo-V2-Flash
194K
202
R1 Distill Qwen 32B
203K
203
gpt-oss-20b
205K
204
Gemini 2.5 Flash Lite
208K
205
Nova 2 Lite
213K
206
gpt-oss-safeguard-20b
213K
207
Gemini 2.5 Flash Preview 09-2025
214K
208
Qwen2.5 VL 32B Instruct
215K
209
CodeLLaMa 7B Instruct Solidity
215K
210
Gemini 2.5 Flash Lite Preview 09-2025
217K
211
GPT-5.1
217K
212
GPT-5 Mini
217K
213
GPT-5 Image Mini
220K
214
Aion-1.0
223K
215
ERNIE 4.5 VL 28B A3B
224K
216
GPT-5 Image
226K
217
Qwen3 VL 30B A3B Instruct
228K
218
GLM 4.6 (exacto)
229K
219
MiniMax M2.1
230K
220
MiMo-V2-Flash
231K
221
Llama 3.1 8B Instruct
234K
222
GLM 4.5 Air
236K
223
Qwen3 14B
240K
224
MiniMax M1
243K
225
GPT-5
244K
226
o1
247K
227
Sonar Reasoning Pro
252K
228
o1-pro
253K
229
Grok 4 Fast
254K
230
Free Models Router
256K
231
Nemotron Nano 9B V2
265K
232
Kimi Dev 72B
266K
233
Qwen3 Coder Next
271K
234
Seed 1.6 Flash
276K
235
Grok 4.1 Fast
280K
236
Qwen3 32B
280K
237
o4 Mini High
286K
238
Grok Code Fast 1
288K
239
Seed 1.6
289K
240
GPT-5.1-Codex-Max
297K
241
Qwen3 VL 235B A22B Thinking
298K
242
Qwen3 235B A22B
299K
243
R1
307K
244
Mistral Small Creative
309K
245
Qwen3 8B
310K
246
Grok 4
312K
247
MiniMax M2
315K
248
Llama 3.3 Nemotron Super 49B V1.5
330K
249
Tongyi DeepResearch 30B A3B
336K
250
GLM 4.5
339K
251
Qwen3 30B A3B Thinking 2507
349K
252
Grok 3 Mini
351K
253
Grok 3 Mini Beta
357K
254
GLM 4.6V
375K
255
R1 0528
375K
256
QwQ 32B
389K
257
Kimi K2 Thinking
394K
258
Nemotron Nano 12B 2 VL
394K
259
Step3
408K
260
Qwen3 VL 30B A3B Thinking
423K
261
Llemma 7b
437K
262
Qwen3 235B A22B Thinking 2507
441K
263
GPT-5 Nano
443K
264
Qwen Plus 0728 (thinking)
447K
265
Solar Pro 3
452K
266
Nano Banana Pro (Gemini 3 Pro Image Preview)
479K
267
Kimi K2.5
497K
268
DeepSeek V3.2 Speciale
508K
269
Gemini 3 Pro Preview
512K
270
GLM 4.6
516K
271
Claude 3.7 Sonnet (thinking)
531K
272
ERNIE 4.5 21B A3B Thinking
586K
273
Gemini 2.5 Pro Preview 06-05
590K
274
Gemini 2.5 Pro
594K
275
Gemini 2.5 Pro Preview 05-06
596K
276
GLM 4.7
599K
277
Olmo 3 7B Think
610K
278
Qwen3 VL 8B Thinking
615K
279
Step 3.5 Flash
615K
280
Qwen3 Next 80B A3B Thinking
641K
281
Nemotron 3 Nano 30B A3B
727K
282
Olmo 3 32B Think
733K
283
Trinity Mini
772K
284
GLM 4.7 Flash
785K
285
Olmo 3.1 32B Think
787K
286
Morph V3 Fast
1.2M
287
o4 Mini Deep Research
1.7M
288
Hermes 3 70B Instruct
1.7M
289
o3 Deep Research
1.8M
290
Sonar Deep Research
68.3M
Total:128.3M
Mitjana:443K
(290 modelos)