Ranking for MIR 2024
20 January 2024
210questions
5invalidated
Compare with:
Jump to metric:
Metrics menu
Net Score
MIR scoring: (3 × correct - incorrect) / 3
1
ALMA
200.00 pts
2
Miri
197.33 pts
3
Qwen3.5 397B A17B
194.66 pts
4
Sonar Deep Research
193.66 pts
5
Gemini 3.1 Pro Preview
193.33 pts
6
Gemini 3 Flash Preview
193.33 pts
7
GPT-5 Mini
193.33 pts
8
Qwen3 235B A22B Thinking 2507
193.33 pts
9
GPT-5 Chat
193.33 pts
10
GPT-5.1
193.33 pts
11
Gemini 2.5 Pro
193.33 pts
12
Gemini 2.5 Pro Preview 05-06
193.33 pts
13
o3 Pro
193.33 pts
14
o3 Deep Research
193.33 pts
15
Gemini 3.1 Pro Preview Custom Tools
192.33 pts
16
DeepSeek V3.2 Speciale
192.33 pts
17
GPT-5.1-Codex-Mini
192.00 pts
18
GPT-5.1 Chat
192.00 pts
19
R1 0528
192.00 pts
20
o4 Mini
192.00 pts
21
GPT-5.2-Codex
192.00 pts
22
Claude Sonnet 4.5
192.00 pts
23
Claude 3.5 Sonnet
192.00 pts
24
Gemini 2.5 Pro Preview 06-05
192.00 pts
25
Gemini 3 Pro Preview
192.00 pts
26
GPT-5.2 Pro
192.00 pts
27
o3
191.00 pts
28
GPT-5 Codex
190.66 pts
29
GPT-5.2 Chat
190.66 pts
30
GPT-5.2
190.66 pts
31
o4 Mini High
190.66 pts
32
Grok 3
190.66 pts
33
o1
190.66 pts
34
Gemini 2.5 Flash
190.33 pts
35
Qwen3.5-122B-A10B
190.33 pts
36
Aion-2.0
190.00 pts
37
Gemini 3.1 Flash Lite Preview
189.66 pts
38
Gemini 2.5 Flash Preview 09-2025
189.66 pts
39
GPT-5 Image Mini
189.66 pts
40
GPT-5.3-Codex
189.33 pts
41
Mistral Large 3 2512
189.33 pts
42
GPT-5.1-Codex
189.33 pts
43
GPT-4.1
189.33 pts
44
Kimi K2.5
189.33 pts
45
GLM 5
189.33 pts
46
Aion-1.0
189.33 pts
47
GPT-5
189.33 pts
48
GPT-5.1-Codex-Max
189.33 pts
49
Auto Router
189.33 pts
50
Grok 4
189.33 pts
51
Claude Opus 4.5
189.33 pts
52
GPT-5.3 Chat
189.00 pts
53
GPT-5.4
188.66 pts
54
DeepSeek V3.2
188.33 pts
55
R1
188.33 pts
56
Claude 3.7 Sonnet (thinking)
188.33 pts
57
Gemini 2.0 Flash
188.00 pts
58
Switchpoint Router
188.00 pts
59
Mistral Large
188.00 pts
60
GPT-4o (2024-11-20)
188.00 pts
61
GPT-4o (2024-05-13)
188.00 pts
62
ChatGPT-4o
188.00 pts
63
Claude 3.7 Sonnet
188.00 pts
64
Claude Sonnet 4.6
188.00 pts
65
GPT-5 Image
188.00 pts
66
Nano Banana Pro (Gemini 3 Pro Image Preview)
188.00 pts
67
o1-pro
188.00 pts
68
DeepSeek V3 0324
187.66 pts
69
GPT-4o Search Preview
187.00 pts
70
Mercury 2
187.00 pts
71
Qwen3 235B A22B
187.00 pts
72
GLM 4.7
187.00 pts
73
Qwen3 VL 235B A22B Instruct
186.66 pts
74
Mistral Medium 3.1
186.66 pts
75
Qwen Plus 0728 (thinking)
186.66 pts
76
Claude Sonnet 4
186.66 pts
77
Claude Opus 4.6
186.66 pts
78
o4 Mini Deep Research
186.66 pts
Best human
186.66 pts
79
GPT-5.4 Pro
186.33 pts
80
GPT-5 Nano
186.00 pts
81
Qwen3.5-35B-A3B
186.00 pts
82
Llama 4 Maverick
185.66 pts
83
DeepSeek V3.1 Terminus
185.66 pts
84
GPT-3.5 Turbo (older v0613)
185.66 pts
85
GLM 4.5
185.33 pts
86
Qwen3 Max
185.33 pts
87
Qwen3 Max Thinking
185.33 pts
88
Qwen3 VL 235B A22B Thinking
185.33 pts
89
Grok 3 Beta
185.33 pts
90
Claude Opus 4
185.33 pts
91
Claude Opus 4.1
185.33 pts
92
DeepSeek V3.2 Exp
185.00 pts
93
Qwen-Plus
185.00 pts
94
GPT-4o (2024-08-06)
185.00 pts
95
Nano Banana (Gemini 2.5 Flash Image)
184.66 pts
96
DeepSeek V3
184.33 pts
97
GPT-4.1 Mini
184.33 pts
98
Qwen Plus 0728
184.33 pts
99
Mistral Large 2407
184.00 pts
100
Qwen3.5-27B
184.00 pts
101
DeepSeek V3.1 Terminus (exacto)
183.33 pts
102
Seed 1.6
183.00 pts
103
GLM 4.6 (exacto)
183.00 pts
104
Mistral Medium 3
182.66 pts
105
Kimi K2 Thinking
182.66 pts
106
Grok 3 Mini Beta
182.33 pts
107
GLM 4.6
182.33 pts
108
DeepSeek V3.1
182.00 pts
109
Grok 3 Mini
182.00 pts
110
Qwen3.5 Plus 2026-02-15
182.00 pts
111
Qwen3 Next 80B A3B Thinking
182.00 pts
112
o3 Mini High
182.00 pts
113
GPT-4o
181.66 pts
114
o3 Mini
181.33 pts
115
Step 3.5 Flash
180.66 pts
116
Qwen3 Coder Next
180.33 pts
117
Qwen3 VL 32B Instruct
180.33 pts
118
gpt-oss-120b
180.00 pts
119
Grok 4 Fast
180.00 pts
120
Step 3.5 Flash
180.00 pts
121
Qwen3 VL 30B A3B Thinking
180.00 pts
122
GPT-4 Turbo
180.00 pts
123
Sonar Pro Search
179.66 pts
124
Devstral 2 2512
179.33 pts
125
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
179.33 pts
126
Qwen3 Coder 480B A35B (exacto)
179.33 pts
127
Palmyra X5
179.33 pts
128
gpt-oss-120b (exacto)
179.00 pts
129
Cogito v2.1 671B
179.00 pts
130
Grok 4.1 Fast
178.66 pts
131
Claude Haiku 4.5
178.66 pts
132
Llama 3.3 Nemotron Super 49B V1.5
178.33 pts
133
Nova Pro 1.0
178.33 pts
134
Qwen3 Coder Plus
178.33 pts
135
Aurora Alpha
178.00 pts
136
Gemini 2.5 Flash Lite Preview 09-2025
178.00 pts
137
Qwen3 235B A22B Instruct 2507
178.00 pts
138
Kimi K2 0711
177.66 pts
139
MiniMax M2.5
177.33 pts
140
MiniMax M2
176.66 pts
141
Devstral Medium
176.33 pts
142
DeepSeek V3.1 Nex N1
176.33 pts
143
Qwen3 Next 80B A3B Instruct
176.33 pts
144
Qwen3 Coder 480B A35B
176.33 pts
145
gpt-oss-20b
176.00 pts
146
Gemini 2.5 Flash Lite
176.00 pts
147
GPT-4 Turbo Preview
175.33 pts
148
KAT-Coder-Pro V1
175.00 pts
149
Seed-2.0-Mini
174.33 pts
150
GPT-4 Turbo (older v1106)
174.00 pts
151
Qwen2.5 VL 72B Instruct
174.00 pts
152
ERNIE 4.5 VL 424B A47B
173.66 pts
153
Tongyi DeepResearch 30B A3B
173.33 pts
154
Mistral Large 2411
173.33 pts
155
Grok Code Fast 1
173.00 pts
156
Sonar Pro
173.00 pts
157
GPT-4
173.00 pts
158
Pixtral Large 2411
172.66 pts
159
Llama 4 Scout
172.33 pts
160
GLM 4.6V
172.33 pts
161
Trinity Large Preview
172.00 pts
162
ERNIE 4.5 300B A47B
172.00 pts
163
Kimi K2 0905
172.00 pts
164
Kimi K2 0905 (exacto)
171.33 pts
165
Gemini 2.0 Flash Lite
170.66 pts
166
Mistral Small Creative
170.66 pts
167
Solar Pro 3
170.33 pts
168
Aion-1.0-Mini
170.33 pts
169
Nova Premier 1.0
170.33 pts
170
Sonar Reasoning Pro
170.00 pts
171
gpt-oss-safeguard-20b
169.66 pts
172
Mistral Small 3.2 24B
169.33 pts
173
GPT-4 (older v0314)
169.00 pts
174
Llama 3.1 Nemotron Ultra 253B v1
168.66 pts
175
Jamba Large 1.7
168.66 pts
176
Qwen3 32B
168.33 pts
177
Qwen3 30B A3B Thinking 2507
168.33 pts
178
Qwen3 VL 30B A3B Instruct
168.33 pts
179
Qwen VL Max
168.33 pts
180
Qwen2.5 72B Instruct
168.00 pts
181
Hermes 3 405B Instruct
168.00 pts
182
Sonar
168.00 pts
183
Qwen3 30B A3B Instruct 2507
167.33 pts
184
GLM 4.5V
167.33 pts
185
R1 Distill Llama 70B
167.00 pts
186
Qwen3.5-Flash
167.00 pts
187
Mixtral 8x22B Instruct
167.00 pts
188
Kimi Dev 72B
166.33 pts
189
Cogito V2 Preview Llama 405B
166.00 pts
190
QwQ 32B
165.33 pts
191
Mercury Coder
164.66 pts
192
Seed 1.6 Flash
164.00 pts
193
Nemotron 3 Nano 30B A3B
164.00 pts
194
Qwen3 14B
163.66 pts
195
MiniMax M2.1
163.66 pts
196
Saba
163.33 pts
197
MiMo-V2-Flash
163.33 pts
198
Hermes 4 405B
162.66 pts
199
Step3
162.66 pts
200
MiniMax M2-her
162.33 pts
201
Llama 3.3 70B Instruct
162.00 pts
202
Mercury
162.00 pts
203
Llama 3.1 70B Instruct
160.66 pts
204
MiniMax M1
160.66 pts
205
Cydonia 24B V4.1
159.33 pts
206
Command A
159.00 pts
207
GPT-4o-mini (2024-07-18)
158.33 pts
208
Qwen3 VL 8B Thinking
158.00 pts
209
GPT-4o-mini Search Preview
157.33 pts
210
Medgemma
157.33 pts
211
GPT-4o-mini
157.33 pts
212
Llama 3.3 Euryale 70B
156.33 pts
213
Cogito V2 Preview Llama 70B
155.66 pts
214
Llama 3.1 Nemotron 70B Instruct
155.00 pts
215
Ministral 3 14B 2512
154.66 pts
216
Nemotron Nano 12B 2 VL
154.66 pts
217
Qwen-Max
154.66 pts
218
GLM 4 32B
154.33 pts
219
Mistral Small 3.1 24B
154.33 pts
220
Nova 2 Lite
154.33 pts
221
Devstral Small 1.1
154.00 pts
222
GPT-4.1 Nano
153.33 pts
223
Voxtral Small 24B 2507
153.00 pts
224
Inflection 3 Pi
153.00 pts
225
MiMo-V2-Flash
152.66 pts
226
GLM 4.5 Air
152.66 pts
227
Qwen-Turbo
152.33 pts
228
Qwen3 Coder 30B A3B Instruct
149.66 pts
229
Mistral Small 3
149.33 pts
230
Gemma 3 27B
148.00 pts
231
Claude 3.5 Haiku
147.66 pts
232
Qwen3 8B
147.33 pts
233
Qwen3 Coder Flash
147.33 pts
234
Hermes 4 70B
146.66 pts
235
Qwen VL Plus
146.66 pts
236
Inflection 3 Productivity
146.33 pts
237
R1 Distill Qwen 32B
146.00 pts
238
GLM 4.7 Flash
146.00 pts
239
Llama 3 70B Instruct
144.66 pts
240
Ministral 3 8B 2512
144.33 pts
241
Qwen2.5 VL 32B Instruct
144.00 pts
242
Llama 3.1 70B Hanami x1
143.66 pts
243
Qwen3 VL 8B Instruct
141.66 pts
244
Olmo 3 32B Think
140.00 pts
245
Olmo 3.1 32B Think
140.00 pts
246
Relace Search
140.00 pts
247
Nemotron Nano 9B V2
139.66 pts
248
Free Models Router
138.66 pts
249
Claude 3 Haiku
138.00 pts
250
Nova Micro 1.0
136.66 pts
251
Skyfall 36B V2
136.33 pts
252
Llama 3 Euryale 70B v2.1
135.33 pts
253
Trinity Mini
130.00 pts
254
Nova Lite 1.0
127.66 pts
255
ERNIE 4.5 VL 28B A3B
127.33 pts
256
SorcererLM 8x22B
126.66 pts
257
ERNIE 4.5 21B A3B
125.66 pts
258
Llama 3.1 Euryale 70B v2.2
125.00 pts
259
Gemma 3 12B
121.66 pts
260
Unknown
119.66 pts
261
Ministral 3 3B 2512
118.66 pts
262
Command R+ (08-2024)
118.33 pts
263
Qwen3 4B
115.66 pts
264
Gemma 2 27B
115.66 pts
265
Mixtral 8x7B Instruct
111.66 pts
266
ERNIE 4.5 21B A3B Thinking
107.66 pts
267
Molmo2 8B
106.33 pts
268
GPT-3.5 Turbo
105.66 pts
269
Gemma 2 9B
105.33 pts
270
Command R (08-2024)
104.00 pts
271
Phi 4
100.66 pts
272
Gemma 3n 4B
99.66 pts
273
Pixtral 12B
98.66 pts
274
LFM2-24B-A2B
98.00 pts
275
Hunyuan A13B Instruct
94.66 pts
276
Mistral Nemo
93.33 pts
277
Qwen2.5 Coder 32B Instruct
92.33 pts
278
Ministral 8B
91.33 pts
279
Olmo 3.1 32B Instruct
90.66 pts
280
GPT-3.5 Turbo 16k
88.33 pts
281
Jamba Mini 1.7
87.33 pts
282
Olmo 3 7B Think
84.00 pts
283
Codestral 2508
79.33 pts
284
LFM2-8B-A1B
74.33 pts
285
Qwen2.5 7B Instruct
73.00 pts
286
GPT-3.5 Turbo Instruct
71.00 pts
287
Command R7B (12-2024)
67.66 pts
288
Llama 3 8B Instruct
65.33 pts
289
Rocinante 12B
64.33 pts
290
Gemma 3 4B
62.00 pts
291
Mistral 7B Instruct
61.33 pts
292
Qwen2.5-VL 7B Instruct
60.66 pts
293
Hermes 3 70B Instruct
59.00 pts
294
Goliath 120B
58.66 pts
295
Ministral 3B
55.00 pts
296
Mistral 7B Instruct v0.2
54.33 pts
297
Llama 3 8B Lunaris
53.33 pts
298
Mistral 7B Instruct v0.3
52.66 pts
299
Mistral Tiny
52.66 pts
300
UnslopNemo 12B
52.33 pts
301
Mistral 7B Instruct v0.1
45.00 pts
302
Llama 3.2 11B Vision Instruct
44.66 pts
303
Llama 3.1 8B Instruct
44.00 pts
304
Lumimaid v0.2 8B
40.00 pts
305
Granite 4.0 Micro
39.00 pts
306
Llama 3.2 3B Instruct
38.66 pts
307
Rnj 1 Instruct
38.66 pts
308
Noromaid 20B
38.00 pts
309
Hermes 2 Pro - Llama-3 8B
37.00 pts
310
Aion-RP 1.0 (8B)
33.00 pts
311
Morph V3 Large
29.66 pts
312
ReMM SLERP 13B
26.66 pts
313
Olmo 3 7B Instruct
25.66 pts
314
Weaver (alpha)
23.66 pts
315
MythoMax 13B
17.00 pts
316
Morph V3 Fast
9.33 pts
317
Llama 3.2 1B Instruct
7.33 pts
318
CodeLLaMa 7B Instruct Solidity
2.33 pts
319
Solar Pro 3
0.00 pts
320
Llemma 7b
0.00 pts
Average:153.10 pts
(320 modelos)
Metrics menu
Correct Answers
Total number of correct answers
1
ALMA
200
2
Miri
198
3
Qwen3.5 397B A17B
196
4
Sonar Deep Research
195
5
Gemini 3.1 Pro Preview
195
6
Gemini 3 Flash Preview
195
7
GPT-5 Mini
195
8
Qwen3 235B A22B Thinking 2507
195
9
GPT-5 Chat
195
10
GPT-5.1
195
11
Gemini 2.5 Pro
195
12
Gemini 2.5 Pro Preview 05-06
195
13
o3 Pro
195
14
o3 Deep Research
195
15
Gemini 3.1 Pro Preview Custom Tools
194
16
DeepSeek V3.2 Speciale
194
17
GPT-5.1-Codex-Mini
194
18
GPT-5.1 Chat
194
19
R1 0528
194
20
o4 Mini
194
21
GPT-5.2-Codex
194
22
Claude Sonnet 4.5
194
23
Claude 3.5 Sonnet
194
24
Gemini 2.5 Pro Preview 06-05
194
25
Gemini 3 Pro Preview
194
26
GPT-5.2 Pro
194
27
o3
193
28
GPT-5 Codex
193
29
GPT-5.2 Chat
193
30
GPT-5.2
193
31
o4 Mini High
193
32
Grok 3
193
33
o1
193
34
Gemini 2.5 Flash
192
35
Qwen3.5-122B-A10B
192
36
Aion-2.0
192
37
Gemini 3.1 Flash Lite Preview
192
38
Gemini 2.5 Flash Preview 09-2025
192
39
GPT-5 Image Mini
192
40
Mistral Large 3 2512
192
41
GPT-5.1-Codex
192
42
GPT-4.1
192
43
Kimi K2.5
192
44
GLM 5
192
45
Aion-1.0
192
46
GPT-5
192
47
GPT-5.1-Codex-Max
192
48
Auto Router
192
49
Grok 4
192
50
Claude Opus 4.5
192
51
GPT-5.3-Codex
191
52
GPT-5.3 Chat
191
53
GPT-5.4
191
54
DeepSeek V3.2
191
55
R1
191
56
Claude 3.7 Sonnet (thinking)
191
57
Gemini 2.0 Flash
191
58
Switchpoint Router
191
59
Mistral Large
191
60
GPT-4o (2024-11-20)
191
61
GPT-4o (2024-05-13)
191
62
ChatGPT-4o
191
63
Claude 3.7 Sonnet
191
64
Claude Sonnet 4.6
191
65
GPT-5 Image
191
66
Nano Banana Pro (Gemini 3 Pro Image Preview)
191
67
o1-pro
191
68
DeepSeek V3 0324
190
69
GPT-4o Search Preview
190
70
Mercury 2
190
71
Qwen3 235B A22B
190
72
GLM 4.7
190
73
Qwen3 VL 235B A22B Instruct
190
74
Mistral Medium 3.1
190
75
Qwen Plus 0728 (thinking)
190
76
Claude Sonnet 4
190
77
Claude Opus 4.6
190
78
o4 Mini Deep Research
190
Best human
190
79
GPT-5.4 Pro
189
80
GPT-5 Nano
189
81
Qwen3.5-35B-A3B
189
82
Llama 4 Maverick
189
83
DeepSeek V3.1 Terminus
189
84
GPT-3.5 Turbo (older v0613)
189
85
GLM 4.5
189
86
Qwen3 VL 235B A22B Thinking
189
87
Grok 3 Beta
189
88
Claude Opus 4
189
89
Claude Opus 4.1
189
90
Qwen3 Max
188
91
Qwen3 Max Thinking
188
92
DeepSeek V3.2 Exp
188
93
Qwen-Plus
188
94
DeepSeek V3
188
95
GPT-4.1 Mini
188
96
Qwen Plus 0728
188
97
Mistral Large 2407
188
98
GPT-4o (2024-08-06)
187
99
Nano Banana (Gemini 2.5 Flash Image)
187
100
DeepSeek V3.1 Terminus (exacto)
187
101
Seed 1.6
187
102
GLM 4.6 (exacto)
187
103
Mistral Medium 3
187
104
Qwen3.5-27B
186
105
Kimi K2 Thinking
186
106
Grok 3 Mini Beta
186
107
GLM 4.6
186
108
Grok 3 Mini
186
109
Qwen3.5 Plus 2026-02-15
186
110
Qwen3 Next 80B A3B Thinking
186
111
o3 Mini High
186
112
o3 Mini
186
113
DeepSeek V3.1
185
114
Step 3.5 Flash
185
115
Qwen3 Coder Next
185
116
Qwen3 VL 32B Instruct
185
117
gpt-oss-120b
185
118
Grok 4 Fast
185
119
Qwen3 VL 30B A3B Thinking
185
120
GPT-4 Turbo
185
121
GPT-4o
184
122
Step 3.5 Flash
184
123
Sonar Pro Search
184
124
Devstral 2 2512
184
125
Qwen3 Coder 480B A35B (exacto)
184
126
Palmyra X5
184
127
gpt-oss-120b (exacto)
184
128
Grok 4.1 Fast
184
129
Claude Haiku 4.5
184
130
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
183
131
Llama 3.3 Nemotron Super 49B V1.5
183
132
Nova Pro 1.0
183
133
Qwen3 Coder Plus
183
134
Aurora Alpha
183
135
Gemini 2.5 Flash Lite Preview 09-2025
183
136
Qwen3 235B A22B Instruct 2507
183
137
Cogito v2.1 671B
182
138
Kimi K2 0711
182
139
MiniMax M2.5
182
140
Devstral Medium
182
141
Qwen3 Next 80B A3B Instruct
182
142
Qwen3 Coder 480B A35B
182
143
gpt-oss-20b
182
144
Gemini 2.5 Flash Lite
182
145
MiniMax M2
181
146
DeepSeek V3.1 Nex N1
181
147
GPT-4 Turbo Preview
181
148
KAT-Coder-Pro V1
180
149
Qwen2.5 VL 72B Instruct
180
150
ERNIE 4.5 VL 424B A47B
180
151
Tongyi DeepResearch 30B A3B
180
152
Mistral Large 2411
180
153
Sonar Pro
179
154
Pixtral Large 2411
179
155
Llama 4 Scout
179
156
GLM 4.6V
179
157
ERNIE 4.5 300B A47B
179
158
Seed-2.0-Mini
178
159
GPT-4 Turbo (older v1106)
178
160
Grok Code Fast 1
178
161
GPT-4
178
162
Trinity Large Preview
178
163
Mistral Small Creative
178
164
Gemini 2.0 Flash Lite
177
165
Solar Pro 3
177
166
Nova Premier 1.0
177
167
gpt-oss-safeguard-20b
177
168
Mistral Small 3.2 24B
177
169
Aion-1.0-Mini
176
170
Llama 3.1 Nemotron Ultra 253B v1
176
171
Jamba Large 1.7
176
172
Qwen3 32B
176
173
Qwen3 30B A3B Thinking 2507
176
174
Qwen3 VL 30B A3B Instruct
176
175
Qwen2.5 72B Instruct
176
176
Kimi K2 0905
175
177
GPT-4 (older v0314)
175
178
Qwen VL Max
175
179
Hermes 3 405B Instruct
175
180
Sonar
175
181
Qwen3 30B A3B Instruct 2507
175
182
GLM 4.5V
175
183
R1 Distill Llama 70B
175
184
Mixtral 8x22B Instruct
175
185
Kimi K2 0905 (exacto)
174
186
Sonar Reasoning Pro
174
187
QwQ 32B
174
188
Qwen3.5-Flash
173
189
Kimi Dev 72B
173
190
Cogito V2 Preview Llama 405B
173
191
Mercury Coder
173
192
Nemotron 3 Nano 30B A3B
173
193
Seed 1.6 Flash
172
194
Qwen3 14B
172
195
Saba
172
196
MiMo-V2-Flash
172
197
Step3
172
198
Llama 3.3 70B Instruct
171
199
Mercury
171
200
MiniMax M2.1
170
201
MiniMax M2-her
170
202
Llama 3.1 70B Instruct
170
203
Hermes 4 405B
169
204
MiniMax M1
169
205
Command A
169
206
Cydonia 24B V4.1
168
207
GPT-4o-mini (2024-07-18)
168
208
Qwen3 VL 8B Thinking
168
209
Medgemma
168
210
GPT-4o-mini Search Preview
167
211
GPT-4o-mini
167
212
Ministral 3 14B 2512
166
213
Qwen-Max
166
214
Llama 3.3 Euryale 70B
165
215
Cogito V2 Preview Llama 70B
165
216
Llama 3.1 Nemotron 70B Instruct
165
217
Nemotron Nano 12B 2 VL
165
218
Mistral Small 3.1 24B
165
219
Nova 2 Lite
165
220
Devstral Small 1.1
165
221
GPT-4.1 Nano
165
222
Voxtral Small 24B 2507
164
223
Inflection 3 Pi
164
224
MiMo-V2-Flash
164
225
GLM 4 32B
163
226
Qwen-Turbo
163
227
GLM 4.5 Air
162
228
Qwen3 Coder 30B A3B Instruct
162
229
Mistral Small 3
161
230
Gemma 3 27B
161
231
Claude 3.5 Haiku
160
232
Qwen3 8B
160
233
Qwen3 Coder Flash
160
234
Hermes 4 70B
159
235
Qwen VL Plus
159
236
Inflection 3 Productivity
159
237
R1 Distill Qwen 32B
159
238
GLM 4.7 Flash
158
239
Llama 3 70B Instruct
158
240
Ministral 3 8B 2512
158
241
Qwen2.5 VL 32B Instruct
157
242
Llama 3.1 70B Hanami x1
155
243
Qwen3 VL 8B Instruct
155
244
Relace Search
155
245
Free Models Router
153
246
Olmo 3 32B Think
152
247
Claude 3 Haiku
152
248
Nemotron Nano 9B V2
151
249
Olmo 3.1 32B Think
150
250
Skyfall 36B V2
150
251
Nova Micro 1.0
149
252
Llama 3 Euryale 70B v2.1
149
253
Trinity Mini
145
254
Nova Lite 1.0
145
255
ERNIE 4.5 VL 28B A3B
145
256
ERNIE 4.5 21B A3B
143
257
SorcererLM 8x22B
141
258
Gemma 3 12B
141
259
Llama 3.1 Euryale 70B v2.2
140
260
Ministral 3 3B 2512
138
261
Command R+ (08-2024)
138
262
Gemma 2 27B
133
263
Qwen3 4B
131
264
Mixtral 8x7B Instruct
131
265
ERNIE 4.5 21B A3B Thinking
130
266
GPT-3.5 Turbo
129
267
Molmo2 8B
127
268
Command R (08-2024)
127
269
Unknown
125
270
Phi 4
125
271
Gemma 3n 4B
123
272
Gemma 2 9B
122
273
Pixtral 12B
122
274
LFM2-24B-A2B
122
275
Mistral Nemo
118
276
Ministral 8B
116
277
Olmo 3.1 32B Instruct
116
278
GPT-3.5 Turbo 16k
116
279
Jamba Mini 1.7
114
280
Qwen2.5 Coder 32B Instruct
113
281
Olmo 3 7B Think
112
282
Hunyuan A13B Instruct
111
283
Codestral 2508
107
284
LFM2-8B-A1B
104
285
GPT-3.5 Turbo Instruct
102
286
Qwen2.5 7B Instruct
100
287
Command R7B (12-2024)
99
288
Gemma 3 4B
96
289
Llama 3 8B Instruct
93
290
Mistral 7B Instruct
93
291
Goliath 120B
91
292
Qwen2.5-VL 7B Instruct
90
293
Llama 3 8B Lunaris
88
294
Mistral 7B Instruct v0.2
87
295
Mistral 7B Instruct v0.3
87
296
Rocinante 12B
86
297
Mistral Tiny
86
298
Ministral 3B
83
299
Hermes 3 70B Instruct
78
300
Granite 4.0 Micro
78
301
Lumimaid v0.2 8B
77
302
Mistral 7B Instruct v0.1
75
303
UnslopNemo 12B
74
304
Llama 3.1 8B Instruct
74
305
Llama 3.2 3B Instruct
72
306
Rnj 1 Instruct
72
307
Hermes 2 Pro - Llama-3 8B
72
308
Noromaid 20B
67
309
Olmo 3 7B Instruct
67
310
Llama 3.2 11B Vision Instruct
61
311
ReMM SLERP 13B
59
312
Weaver (alpha)
57
313
Aion-RP 1.0 (8B)
51
314
MythoMax 13B
49
315
Morph V3 Large
43
316
Llama 3.2 1B Instruct
29
317
Morph V3 Fast
26
318
CodeLLaMa 7B Instruct Solidity
11
319
Llemma 7b
7
320
Solar Pro 3
0
Total:52045
Average:162.64
(320 modelos)
Metrics menu
Incorrect Answers
Total number of incorrect answers
1
ALMA
0
2
Solar Pro 3
0
3
Miri
2
4
Qwen3.5 397B A17B
4
5
Sonar Deep Research
4
6
Gemini 3.1 Pro Preview
5
7
Gemini 3 Flash Preview
5
8
GPT-5 Mini
5
9
Qwen3 235B A22B Thinking 2507
5
10
GPT-5 Chat
5
11
GPT-5.1
5
12
Gemini 2.5 Pro
5
13
Gemini 2.5 Pro Preview 05-06
5
14
o3 Pro
5
15
o3 Deep Research
5
16
Gemini 3.1 Pro Preview Custom Tools
5
17
DeepSeek V3.2 Speciale
5
18
Gemini 2.5 Flash
5
19
Qwen3.5-122B-A10B
5
20
GPT-5.3-Codex
5
21
GPT-5.1-Codex-Mini
6
22
GPT-5.1 Chat
6
23
R1 0528
6
24
o4 Mini
6
25
GPT-5.2-Codex
6
26
Claude Sonnet 4.5
6
27
Claude 3.5 Sonnet
6
28
Gemini 2.5 Pro Preview 06-05
6
29
Gemini 3 Pro Preview
6
30
GPT-5.2 Pro
6
31
o3
6
32
Aion-2.0
6
33
GPT-5.3 Chat
6
34
GPT-4o (2024-08-06)
6
35
Qwen3.5-27B
6
36
GPT-5 Codex
7
37
GPT-5.2 Chat
7
38
GPT-5.2
7
39
o4 Mini High
7
40
Grok 3
7
41
o1
7
42
Gemini 3.1 Flash Lite Preview
7
43
Gemini 2.5 Flash Preview 09-2025
7
44
GPT-5 Image Mini
7
45
GPT-5.4
7
46
DeepSeek V3 0324
7
47
Nano Banana (Gemini 2.5 Flash Image)
7
48
GPT-4o
7
49
Mistral Large 3 2512
8
50
GPT-5.1-Codex
8
51
GPT-4.1
8
52
Kimi K2.5
8
53
GLM 5
8
54
Aion-1.0
8
55
GPT-5
8
56
GPT-5.1-Codex-Max
8
57
Auto Router
8
58
Grok 4
8
59
Claude Opus 4.5
8
60
DeepSeek V3.2
8
61
R1
8
62
Claude 3.7 Sonnet (thinking)
8
63
GPT-5.4 Pro
8
64
Qwen3 Max
8
65
Qwen3 Max Thinking
8
66
Kimi K2 0905 (exacto)
8
67
Gemini 2.0 Flash
9
68
Switchpoint Router
9
69
Mistral Large
9
70
GPT-4o (2024-11-20)
9
71
GPT-4o (2024-05-13)
9
72
ChatGPT-4o
9
73
Claude 3.7 Sonnet
9
74
Claude Sonnet 4.6
9
75
GPT-5 Image
9
76
Nano Banana Pro (Gemini 3 Pro Image Preview)
9
77
o1-pro
9
78
GPT-4o Search Preview
9
79
Mercury 2
9
80
Qwen3 235B A22B
9
81
GLM 4.7
9
82
GPT-5 Nano
9
83
Qwen3.5-35B-A3B
9
84
DeepSeek V3.2 Exp
9
85
Qwen-Plus
9
86
DeepSeek V3.1
9
87
Cogito v2.1 671B
9
88
Kimi K2 0905
9
89
Qwen3 VL 235B A22B Instruct
10
90
Mistral Medium 3.1
10
91
Qwen Plus 0728 (thinking)
10
92
Claude Sonnet 4
10
93
Claude Opus 4.6
10
94
o4 Mini Deep Research
10
95
Llama 4 Maverick
10
96
DeepSeek V3.1 Terminus
10
97
GPT-3.5 Turbo (older v0613)
10
98
Kimi K2 Thinking
10
Best human
10
99
GLM 4.5
11
100
Qwen3 VL 235B A22B Thinking
11
101
Grok 3 Beta
11
102
Claude Opus 4
11
103
Claude Opus 4.1
11
104
DeepSeek V3
11
105
GPT-4.1 Mini
11
106
Qwen Plus 0728
11
107
DeepSeek V3.1 Terminus (exacto)
11
108
Grok 3 Mini Beta
11
109
GLM 4.6
11
110
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
11
111
Seed-2.0-Mini
11
112
Mistral Large 2407
12
113
Seed 1.6
12
114
GLM 4.6 (exacto)
12
115
Grok 3 Mini
12
116
Qwen3.5 Plus 2026-02-15
12
117
Qwen3 Next 80B A3B Thinking
12
118
o3 Mini High
12
119
Step 3.5 Flash
12
120
GPT-4 Turbo (older v1106)
12
121
Sonar Reasoning Pro
12
122
Mistral Medium 3
13
123
Step 3.5 Flash
13
124
Sonar Pro Search
13
125
Kimi K2 0711
13
126
MiniMax M2
13
127
o3 Mini
14
128
Qwen3 Coder Next
14
129
Qwen3 VL 32B Instruct
14
130
Devstral 2 2512
14
131
Qwen3 Coder 480B A35B (exacto)
14
132
Palmyra X5
14
133
Llama 3.3 Nemotron Super 49B V1.5
14
134
Nova Pro 1.0
14
135
Qwen3 Coder Plus
14
136
MiniMax M2.5
14
137
DeepSeek V3.1 Nex N1
14
138
gpt-oss-120b
15
139
Grok 4 Fast
15
140
Qwen3 VL 30B A3B Thinking
15
141
GPT-4 Turbo
15
142
gpt-oss-120b (exacto)
15
143
Aurora Alpha
15
144
Gemini 2.5 Flash Lite Preview 09-2025
15
145
Qwen3 235B A22B Instruct 2507
15
146
KAT-Coder-Pro V1
15
147
Grok Code Fast 1
15
148
GPT-4
15
149
Grok 4.1 Fast
16
150
Claude Haiku 4.5
16
151
Unknown
16
152
Devstral Medium
17
153
Qwen3 Next 80B A3B Instruct
17
154
Qwen3 Coder 480B A35B
17
155
GPT-4 Turbo Preview
17
156
Aion-1.0-Mini
17
157
gpt-oss-20b
18
158
Gemini 2.5 Flash Lite
18
159
Qwen2.5 VL 72B Instruct
18
160
Sonar Pro
18
161
Trinity Large Preview
18
162
GPT-4 (older v0314)
18
163
Qwen3.5-Flash
18
164
ERNIE 4.5 VL 424B A47B
19
165
Pixtral Large 2411
19
166
Gemini 2.0 Flash Lite
19
167
MiniMax M2.1
19
168
Hermes 4 405B
19
169
Tongyi DeepResearch 30B A3B
20
170
Mistral Large 2411
20
171
Llama 4 Scout
20
172
GLM 4.6V
20
173
Solar Pro 3
20
174
Nova Premier 1.0
20
175
Qwen VL Max
20
176
Kimi Dev 72B
20
177
ERNIE 4.5 300B A47B
21
178
Hermes 3 405B Instruct
21
179
Sonar
21
180
Cogito V2 Preview Llama 405B
21
181
Mistral Small Creative
22
182
gpt-oss-safeguard-20b
22
183
Llama 3.1 Nemotron Ultra 253B v1
22
184
Jamba Large 1.7
22
185
Mistral Small 3.2 24B
23
186
Qwen3 32B
23
187
Qwen3 30B A3B Thinking 2507
23
188
Qwen3 VL 30B A3B Instruct
23
189
Qwen3 30B A3B Instruct 2507
23
190
GLM 4.5V
23
191
MiniMax M2-her
23
192
Qwen2.5 72B Instruct
24
193
R1 Distill Llama 70B
24
194
Mixtral 8x22B Instruct
24
195
Seed 1.6 Flash
24
196
Mercury Coder
25
197
Qwen3 14B
25
198
MiniMax M1
25
199
QwQ 32B
26
200
Saba
26
201
MiMo-V2-Flash
26
202
Cydonia 24B V4.1
26
203
Llama 3.3 Euryale 70B
26
204
GLM 4 32B
26
205
CodeLLaMa 7B Instruct Solidity
26
206
Nemotron 3 Nano 30B A3B
27
207
Llama 3.3 70B Instruct
27
208
Mercury
27
209
Step3
28
210
Llama 3.1 70B Instruct
28
211
Cogito V2 Preview Llama 70B
28
212
GLM 4.5 Air
28
213
GPT-4o-mini (2024-07-18)
29
214
GPT-4o-mini Search Preview
29
215
GPT-4o-mini
29
216
Command A
30
217
Qwen3 VL 8B Thinking
30
218
Llama 3.1 Nemotron 70B Instruct
30
219
Olmo 3.1 32B Think
30
220
Nemotron Nano 12B 2 VL
31
221
Medgemma
32
222
Mistral Small 3.1 24B
32
223
Nova 2 Lite
32
224
Qwen-Turbo
32
225
Devstral Small 1.1
33
226
Voxtral Small 24B 2507
33
227
Inflection 3 Pi
33
228
Ministral 3 14B 2512
34
229
Qwen-Max
34
230
MiMo-V2-Flash
34
231
Llama 3.1 70B Hanami x1
34
232
Nemotron Nano 9B V2
34
233
GPT-4.1 Nano
35
234
Mistral Small 3
35
235
GLM 4.7 Flash
36
236
Olmo 3 32B Think
36
237
Qwen3 Coder 30B A3B Instruct
37
238
Claude 3.5 Haiku
37
239
Hermes 4 70B
37
240
Qwen VL Plus
37
241
Nova Micro 1.0
37
242
Llemma 7b
37
243
Qwen3 8B
38
244
Qwen3 Coder Flash
38
245
Inflection 3 Productivity
38
246
Gemma 3 27B
39
247
R1 Distill Qwen 32B
39
248
Qwen2.5 VL 32B Instruct
39
249
Llama 3 70B Instruct
40
250
Qwen3 VL 8B Instruct
40
251
Morph V3 Large
40
252
Ministral 3 8B 2512
41
253
Skyfall 36B V2
41
254
Llama 3 Euryale 70B v2.1
41
255
Claude 3 Haiku
42
256
Free Models Router
43
257
SorcererLM 8x22B
43
258
Relace Search
45
259
Trinity Mini
45
260
Llama 3.1 Euryale 70B v2.2
45
261
Qwen3 4B
46
262
Hunyuan A13B Instruct
49
263
Llama 3.2 11B Vision Instruct
49
264
Gemma 2 9B
50
265
Morph V3 Fast
50
266
Nova Lite 1.0
52
267
ERNIE 4.5 21B A3B
52
268
Gemma 2 27B
52
269
ERNIE 4.5 VL 28B A3B
53
270
Aion-RP 1.0 (8B)
54
271
Hermes 3 70B Instruct
57
272
Gemma 3 12B
58
273
Ministral 3 3B 2512
58
274
Mixtral 8x7B Instruct
58
275
Command R+ (08-2024)
59
276
Molmo2 8B
62
277
Qwen2.5 Coder 32B Instruct
62
278
Rocinante 12B
65
279
UnslopNemo 12B
65
280
Llama 3.2 1B Instruct
65
281
ERNIE 4.5 21B A3B Thinking
67
282
Command R (08-2024)
69
283
GPT-3.5 Turbo
70
284
Gemma 3n 4B
70
285
Pixtral 12B
70
286
LFM2-24B-A2B
72
287
Phi 4
73
288
Mistral Nemo
74
289
Ministral 8B
74
290
Olmo 3.1 32B Instruct
76
291
Jamba Mini 1.7
80
292
Qwen2.5 7B Instruct
81
293
GPT-3.5 Turbo 16k
83
294
Codestral 2508
83
295
Llama 3 8B Instruct
83
296
Olmo 3 7B Think
84
297
Ministral 3B
84
298
Noromaid 20B
87
299
Qwen2.5-VL 7B Instruct
88
300
LFM2-8B-A1B
89
301
Mistral 7B Instruct v0.1
90
302
Llama 3.1 8B Instruct
90
303
GPT-3.5 Turbo Instruct
93
304
Command R7B (12-2024)
94
305
Mistral 7B Instruct
95
306
MythoMax 13B
96
307
Goliath 120B
97
308
ReMM SLERP 13B
97
309
Mistral 7B Instruct v0.2
98
310
Mistral Tiny
100
311
Llama 3.2 3B Instruct
100
312
Rnj 1 Instruct
100
313
Weaver (alpha)
100
314
Gemma 3 4B
102
315
Mistral 7B Instruct v0.3
103
316
Llama 3 8B Lunaris
104
317
Hermes 2 Pro - Llama-3 8B
105
318
Lumimaid v0.2 8B
111
319
Granite 4.0 Micro
117
320
Olmo 3 7B Instruct
124
Total:9173
Average:28.66
(320 modelos)
Metrics menu
Accuracy Percentage
Proportion of correct answers over total
1
ALMA
100.0%
2
Miri
99.0%
3
Qwen3.5 397B A17B
98.0%
4
Sonar Deep Research
97.5%
5
Gemini 3.1 Pro Preview
97.5%
6
Gemini 3 Flash Preview
97.5%
7
GPT-5 Mini
97.5%
8
Qwen3 235B A22B Thinking 2507
97.5%
9
GPT-5 Chat
97.5%
10
GPT-5.1
97.5%
11
Gemini 2.5 Pro
97.5%
12
Gemini 2.5 Pro Preview 05-06
97.5%
13
o3 Pro
97.5%
14
o3 Deep Research
97.5%
15
Gemini 3.1 Pro Preview Custom Tools
97.0%
16
DeepSeek V3.2 Speciale
97.0%
17
GPT-5.1-Codex-Mini
97.0%
18
GPT-5.1 Chat
97.0%
19
R1 0528
97.0%
20
o4 Mini
97.0%
21
GPT-5.2-Codex
97.0%
22
Claude Sonnet 4.5
97.0%
23
Claude 3.5 Sonnet
97.0%
24
Gemini 2.5 Pro Preview 06-05
97.0%
25
Gemini 3 Pro Preview
97.0%
26
GPT-5.2 Pro
97.0%
27
o3
96.5%
28
GPT-5 Codex
96.5%
29
GPT-5.2 Chat
96.5%
30
GPT-5.2
96.5%
31
o4 Mini High
96.5%
32
Grok 3
96.5%
33
o1
96.5%
34
Gemini 2.5 Flash
96.0%
35
Qwen3.5-122B-A10B
96.0%
36
Aion-2.0
96.0%
37
Gemini 3.1 Flash Lite Preview
96.0%
38
Gemini 2.5 Flash Preview 09-2025
96.0%
39
GPT-5 Image Mini
96.0%
40
Mistral Large 3 2512
96.0%
41
GPT-5.1-Codex
96.0%
42
GPT-4.1
96.0%
43
Kimi K2.5
96.0%
44
GLM 5
96.0%
45
Aion-1.0
96.0%
46
GPT-5
96.0%
47
GPT-5.1-Codex-Max
96.0%
48
Auto Router
96.0%
49
Grok 4
96.0%
50
Claude Opus 4.5
96.0%
51
GPT-5.3-Codex
95.5%
52
GPT-5.3 Chat
95.5%
53
GPT-5.4
95.5%
54
DeepSeek V3.2
95.5%
55
R1
95.5%
56
Claude 3.7 Sonnet (thinking)
95.5%
57
Gemini 2.0 Flash
95.5%
58
Switchpoint Router
95.5%
59
Mistral Large
95.5%
60
GPT-4o (2024-11-20)
95.5%
61
GPT-4o (2024-05-13)
95.5%
62
ChatGPT-4o
95.5%
63
Claude 3.7 Sonnet
95.5%
64
Claude Sonnet 4.6
95.5%
65
GPT-5 Image
95.5%
66
Nano Banana Pro (Gemini 3 Pro Image Preview)
95.5%
67
o1-pro
95.5%
68
DeepSeek V3 0324
95.0%
69
GPT-4o Search Preview
95.0%
70
Mercury 2
95.0%
71
Qwen3 235B A22B
95.0%
72
GLM 4.7
95.0%
73
Qwen3 VL 235B A22B Instruct
95.0%
74
Mistral Medium 3.1
95.0%
75
Qwen Plus 0728 (thinking)
95.0%
76
Claude Sonnet 4
95.0%
77
Claude Opus 4.6
95.0%
78
o4 Mini Deep Research
95.0%
Best human
95.0%
79
GPT-5.4 Pro
94.5%
80
GPT-5 Nano
94.5%
81
Qwen3.5-35B-A3B
94.5%
82
Llama 4 Maverick
94.5%
83
DeepSeek V3.1 Terminus
94.5%
84
GPT-3.5 Turbo (older v0613)
94.5%
85
GLM 4.5
94.5%
86
Qwen3 VL 235B A22B Thinking
94.5%
87
Grok 3 Beta
94.5%
88
Claude Opus 4
94.5%
89
Claude Opus 4.1
94.5%
90
Qwen3 Max
94.0%
91
Qwen3 Max Thinking
94.0%
92
DeepSeek V3.2 Exp
94.0%
93
Qwen-Plus
94.0%
94
DeepSeek V3
94.0%
95
GPT-4.1 Mini
94.0%
96
Qwen Plus 0728
94.0%
97
Mistral Large 2407
94.0%
98
GPT-4o (2024-08-06)
93.5%
99
Nano Banana (Gemini 2.5 Flash Image)
93.5%
100
DeepSeek V3.1 Terminus (exacto)
93.5%
101
Seed 1.6
93.5%
102
GLM 4.6 (exacto)
93.5%
103
Mistral Medium 3
93.5%
104
Qwen3.5-27B
93.0%
105
Kimi K2 Thinking
93.0%
106
Grok 3 Mini Beta
93.0%
107
GLM 4.6
93.0%
108
Grok 3 Mini
93.0%
109
Qwen3.5 Plus 2026-02-15
93.0%
110
Qwen3 Next 80B A3B Thinking
93.0%
111
o3 Mini High
93.0%
112
o3 Mini
93.0%
113
DeepSeek V3.1
92.5%
114
Step 3.5 Flash
92.5%
115
Qwen3 Coder Next
92.5%
116
Qwen3 VL 32B Instruct
92.5%
117
gpt-oss-120b
92.5%
118
Grok 4 Fast
92.5%
119
Qwen3 VL 30B A3B Thinking
92.5%
120
GPT-4 Turbo
92.5%
121
GPT-4o
92.0%
122
Step 3.5 Flash
92.0%
123
Sonar Pro Search
92.0%
124
Devstral 2 2512
92.0%
125
Qwen3 Coder 480B A35B (exacto)
92.0%
126
Palmyra X5
92.0%
127
gpt-oss-120b (exacto)
92.0%
128
Grok 4.1 Fast
92.0%
129
Claude Haiku 4.5
92.0%
130
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
91.5%
131
Llama 3.3 Nemotron Super 49B V1.5
91.5%
132
Nova Pro 1.0
91.5%
133
Qwen3 Coder Plus
91.5%
134
Aurora Alpha
91.5%
135
Gemini 2.5 Flash Lite Preview 09-2025
91.5%
136
Qwen3 235B A22B Instruct 2507
91.5%
137
Cogito v2.1 671B
91.0%
138
Kimi K2 0711
91.0%
139
MiniMax M2.5
91.0%
140
Devstral Medium
91.0%
141
Qwen3 Next 80B A3B Instruct
91.0%
142
Qwen3 Coder 480B A35B
91.0%
143
gpt-oss-20b
91.0%
144
Gemini 2.5 Flash Lite
91.0%
145
MiniMax M2
90.5%
146
DeepSeek V3.1 Nex N1
90.5%
147
GPT-4 Turbo Preview
90.5%
148
KAT-Coder-Pro V1
90.0%
149
Qwen2.5 VL 72B Instruct
90.0%
150
ERNIE 4.5 VL 424B A47B
90.0%
151
Tongyi DeepResearch 30B A3B
90.0%
152
Mistral Large 2411
90.0%
153
Sonar Pro
89.5%
154
Pixtral Large 2411
89.5%
155
Llama 4 Scout
89.5%
156
GLM 4.6V
89.5%
157
ERNIE 4.5 300B A47B
89.5%
158
Seed-2.0-Mini
89.0%
159
GPT-4 Turbo (older v1106)
89.0%
160
Grok Code Fast 1
89.0%
161
GPT-4
89.0%
162
Trinity Large Preview
89.0%
163
Mistral Small Creative
89.0%
164
Gemini 2.0 Flash Lite
88.5%
165
Solar Pro 3
88.5%
166
Nova Premier 1.0
88.5%
167
gpt-oss-safeguard-20b
88.5%
168
Mistral Small 3.2 24B
88.5%
169
Aion-1.0-Mini
88.0%
170
Llama 3.1 Nemotron Ultra 253B v1
88.0%
171
Jamba Large 1.7
88.0%
172
Qwen3 32B
88.0%
173
Qwen3 30B A3B Thinking 2507
88.0%
174
Qwen3 VL 30B A3B Instruct
88.0%
175
Qwen2.5 72B Instruct
88.0%
176
Kimi K2 0905
87.5%
177
GPT-4 (older v0314)
87.5%
178
Qwen VL Max
87.5%
179
Hermes 3 405B Instruct
87.5%
180
Sonar
87.5%
181
Qwen3 30B A3B Instruct 2507
87.5%
182
GLM 4.5V
87.5%
183
R1 Distill Llama 70B
87.5%
184
Mixtral 8x22B Instruct
87.5%
185
Kimi K2 0905 (exacto)
87.0%
186
Sonar Reasoning Pro
87.0%
187
QwQ 32B
87.0%
188
Qwen3.5-Flash
86.5%
189
Kimi Dev 72B
86.5%
190
Cogito V2 Preview Llama 405B
86.5%
191
Mercury Coder
86.5%
192
Nemotron 3 Nano 30B A3B
86.5%
193
Seed 1.6 Flash
86.0%
194
Qwen3 14B
86.0%
195
Saba
86.0%
196
MiMo-V2-Flash
86.0%
197
Step3
86.0%
198
Llama 3.3 70B Instruct
85.5%
199
Mercury
85.5%
200
MiniMax M2.1
85.0%
201
MiniMax M2-her
85.0%
202
Llama 3.1 70B Instruct
85.0%
203
Hermes 4 405B
84.5%
204
MiniMax M1
84.5%
205
Command A
84.5%
206
Cydonia 24B V4.1
84.0%
207
GPT-4o-mini (2024-07-18)
84.0%
208
Qwen3 VL 8B Thinking
84.0%
209
Medgemma
84.0%
210
GPT-4o-mini Search Preview
83.5%
211
GPT-4o-mini
83.5%
212
Ministral 3 14B 2512
83.0%
213
Qwen-Max
83.0%
214
Llama 3.3 Euryale 70B
82.5%
215
Cogito V2 Preview Llama 70B
82.5%
216
Llama 3.1 Nemotron 70B Instruct
82.5%
217
Nemotron Nano 12B 2 VL
82.5%
218
Mistral Small 3.1 24B
82.5%
219
Nova 2 Lite
82.5%
220
Devstral Small 1.1
82.5%
221
GPT-4.1 Nano
82.5%
222
Voxtral Small 24B 2507
82.0%
223
Inflection 3 Pi
82.0%
224
MiMo-V2-Flash
82.0%
225
GLM 4 32B
81.5%
226
Qwen-Turbo
81.5%
227
GLM 4.5 Air
81.0%
228
Qwen3 Coder 30B A3B Instruct
81.0%
229
Mistral Small 3
80.5%
230
Gemma 3 27B
80.5%
231
Claude 3.5 Haiku
80.0%
232
Qwen3 8B
80.0%
233
Qwen3 Coder Flash
80.0%
234
Hermes 4 70B
79.5%
235
Qwen VL Plus
79.5%
236
Inflection 3 Productivity
79.5%
237
R1 Distill Qwen 32B
79.5%
238
GLM 4.7 Flash
79.0%
239
Llama 3 70B Instruct
79.0%
240
Ministral 3 8B 2512
79.0%
241
Qwen2.5 VL 32B Instruct
78.5%
242
Llama 3.1 70B Hanami x1
77.5%
243
Qwen3 VL 8B Instruct
77.5%
244
Relace Search
77.5%
245
Free Models Router
76.5%
246
Olmo 3 32B Think
76.0%
247
Claude 3 Haiku
76.0%
248
Nemotron Nano 9B V2
75.5%
249
Olmo 3.1 32B Think
75.0%
250
Skyfall 36B V2
75.0%
251
Nova Micro 1.0
74.5%
252
Llama 3 Euryale 70B v2.1
74.5%
253
Trinity Mini
72.5%
254
Nova Lite 1.0
72.5%
255
ERNIE 4.5 VL 28B A3B
72.5%
256
ERNIE 4.5 21B A3B
71.5%
257
SorcererLM 8x22B
70.5%
258
Gemma 3 12B
70.5%
259
Llama 3.1 Euryale 70B v2.2
70.0%
260
Ministral 3 3B 2512
69.0%
261
Command R+ (08-2024)
69.0%
262
Gemma 2 27B
66.5%
263
Qwen3 4B
65.5%
264
Mixtral 8x7B Instruct
65.5%
265
ERNIE 4.5 21B A3B Thinking
65.0%
266
GPT-3.5 Turbo
64.5%
267
Molmo2 8B
63.5%
268
Command R (08-2024)
63.5%
269
Unknown
62.5%
270
Phi 4
62.5%
271
Gemma 3n 4B
61.5%
272
Gemma 2 9B
61.0%
273
Pixtral 12B
61.0%
274
LFM2-24B-A2B
61.0%
275
Mistral Nemo
59.0%
276
Ministral 8B
58.0%
277
Olmo 3.1 32B Instruct
58.0%
278
GPT-3.5 Turbo 16k
58.0%
279
Jamba Mini 1.7
57.0%
280
Qwen2.5 Coder 32B Instruct
56.5%
281
Olmo 3 7B Think
56.0%
282
Hunyuan A13B Instruct
55.5%
283
Codestral 2508
53.5%
284
LFM2-8B-A1B
52.0%
285
GPT-3.5 Turbo Instruct
51.0%
286
Qwen2.5 7B Instruct
50.0%
287
Command R7B (12-2024)
49.5%
288
Gemma 3 4B
48.0%
289
Llama 3 8B Instruct
46.5%
290
Mistral 7B Instruct
46.5%
291
Goliath 120B
45.5%
292
Qwen2.5-VL 7B Instruct
45.0%
293
Llama 3 8B Lunaris
44.0%
294
Mistral 7B Instruct v0.2
43.5%
295
Mistral 7B Instruct v0.3
43.5%
296
Rocinante 12B
43.0%
297
Mistral Tiny
43.0%
298
Ministral 3B
41.5%
299
Hermes 3 70B Instruct
39.0%
300
Granite 4.0 Micro
39.0%
301
Lumimaid v0.2 8B
38.5%
302
Mistral 7B Instruct v0.1
37.5%
303
UnslopNemo 12B
37.0%
304
Llama 3.1 8B Instruct
37.0%
305
Llama 3.2 3B Instruct
36.0%
306
Rnj 1 Instruct
36.0%
307
Hermes 2 Pro - Llama-3 8B
36.0%
308
Noromaid 20B
33.5%
309
Olmo 3 7B Instruct
33.5%
310
Llama 3.2 11B Vision Instruct
30.5%
311
ReMM SLERP 13B
29.5%
312
Weaver (alpha)
28.5%
313
Aion-RP 1.0 (8B)
25.5%
314
MythoMax 13B
24.5%
315
Morph V3 Large
21.5%
316
Llama 3.2 1B Instruct
14.5%
317
Morph V3 Fast
13.0%
318
CodeLLaMa 7B Instruct Solidity
5.5%
319
Llemma 7b
3.5%
320
Solar Pro 3
0.0%
Average:81.3%
(320 modelos)
Metrics menu
Average response time
Average time for the model to respond to each question
1
Ministral 3B
1.5s
2
Devstral Small 1.1
1.5s
3
Mercury 2
1.5s
4
Ministral 8B
1.6s
5
gpt-oss-safeguard-20b
1.8s
6
Voxtral Small 24B 2507
1.9s
7
Mistral 7B Instruct v0.3
1.9s
8
Morph V3 Large
2.0s
9
Mercury Coder
2.1s
10
Aurora Alpha
2.1s
11
Mistral 7B Instruct
2.1s
12
LFM2-8B-A1B
2.2s
13
Codestral 2508
2.2s
14
Mercury
2.3s
15
Mistral 7B Instruct v0.2
2.3s
16
Morph V3 Fast
2.3s
17
GPT-3.5 Turbo 16k
2.3s
18
GPT-3.5 Turbo
2.4s
19
Nova Micro 1.0
2.6s
20
Gemini 3.1 Flash Lite Preview
2.7s
21
GPT-4o (2024-05-13)
2.9s
22
Mistral Tiny
3.0s
23
Kimi K2 0905
3.0s
24
Gemini 2.5 Flash Lite Preview 09-2025
3.1s
25
Gemini 2.0 Flash
3.1s
26
GPT-4.1 Nano
3.2s
27
Gemini 2.0 Flash Lite
3.2s
28
GPT-5.1-Codex
3.2s
29
Mixtral 8x22B Instruct
3.3s
30
Devstral Medium
3.4s
31
Saba
3.4s
32
Claude 3 Haiku
3.4s
33
Command R7B (12-2024)
3.4s
34
Nova Pro 1.0
3.4s
35
Nova Lite 1.0
3.5s
36
Gemini 2.5 Flash Lite
3.5s
37
Ministral 3 3B 2512
3.5s
38
Jamba Mini 1.7
3.6s
39
Llama 3.2 1B Instruct
3.6s
40
GPT-3.5 Turbo Instruct
3.6s
41
LFM2-24B-A2B
3.7s
42
Qwen3 Coder 480B A35B (exacto)
3.8s
43
GPT-5.1 Chat
3.8s
44
GPT-5 Chat
3.9s
45
Hermes 2 Pro - Llama-3 8B
4.0s
46
Pixtral 12B
4.1s
47
Lumimaid v0.2 8B
4.1s
48
Gemini 3 Flash Preview
4.2s
49
Aion-1.0-Mini
4.3s
50
Trinity Mini
4.3s
51
GPT-5.1-Codex-Mini
4.4s
52
GPT-4o-mini Search Preview
4.4s
53
Gemma 2 9B
4.4s
54
Relace Search
4.4s
55
Llama 3 8B Lunaris
4.5s
56
Gemini 2.5 Flash Preview 09-2025
4.7s
57
GPT-5 Codex
4.7s
58
Gemini 2.5 Flash
4.8s
59
Hermes 4 70B
4.9s
60
Cogito v2.1 671B
5.0s
61
Ministral 3 8B 2512
5.1s
62
Qwen3 Next 80B A3B Instruct
5.1s
63
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
5.1s
64
ChatGPT-4o
5.2s
65
Rnj 1 Instruct
5.3s
66
Molmo2 8B
5.3s
67
GPT-4o (2024-11-20)
5.3s
68
Gemma 2 27B
5.3s
69
Mistral Medium 3
5.8s
70
Sonar Pro
5.9s
71
Claude Haiku 4.5
6.0s
72
gpt-oss-120b
6.0s
73
Sonar
6.0s
74
Skyfall 36B V2
6.0s
75
Kimi K2 0905 (exacto)
6.4s
76
GPT-5.3 Chat
6.4s
77
gpt-oss-20b
6.5s
78
Mistral Medium 3.1
6.5s
79
Hunyuan A13B Instruct
6.6s
80
Ministral 3 14B 2512
6.6s
81
Qwen3 Coder Flash
6.6s
82
ERNIE 4.5 21B A3B
6.7s
83
o3 Mini
6.8s
84
Llama 4 Scout
6.8s
85
o3 Mini High
6.9s
86
Claude 3.5 Haiku
7.0s
87
Mistral Small Creative
7.0s
88
Mistral Small 3.1 24B
7.1s
89
GPT-4o-mini
7.1s
90
GPT-4.1 Mini
7.2s
91
Qwen2.5-VL 7B Instruct
7.3s
92
GPT-4o-mini (2024-07-18)
7.3s
93
Nova 2 Lite
7.3s
94
GPT-3.5 Turbo (older v0613)
7.4s
95
KAT-Coder-Pro V1
7.5s
96
GPT-4o
7.6s
97
Mistral Large 2411
7.6s
98
Qwen-Turbo
7.7s
99
Command A
7.8s
100
Mistral Nemo
7.8s
101
Cogito V2 Preview Llama 70B
7.8s
102
MiniMax M2-her
7.9s
103
GPT-5.2 Chat
7.9s
104
Hermes 4 405B
7.9s
105
o4 Mini
8.0s
106
Mistral Small 3
8.2s
107
Command R+ (08-2024)
8.2s
108
Qwen VL Plus
8.3s
109
Llama 4 Maverick
8.4s
110
GPT-4o (2024-08-06)
8.6s
111
Mistral Small 3.2 24B
8.6s
112
Cydonia 24B V4.1
8.6s
113
GLM 4 32B
8.6s
114
Palmyra X5
8.6s
115
GPT-5.4
8.7s
116
Grok 4 Fast
8.8s
117
o3
8.9s
118
GPT-4.1
8.9s
119
Aion-RP 1.0 (8B)
8.9s
120
Seed 1.6 Flash
9.0s
121
Llama 3 Euryale 70B v2.1
9.0s
122
Step 3.5 Flash
9.1s
123
o1
9.3s
124
GPT-5.1-Codex-Max
9.5s
125
Sonar Pro Search
9.5s
126
UnslopNemo 12B
9.6s
127
GPT-4o Search Preview
9.7s
128
Nemotron Nano 9B V2
9.8s
129
GPT-5.3-Codex
9.8s
130
Mixtral 8x7B Instruct
9.9s
131
Qwen-Max
10.0s
132
Inflection 3 Pi
10.0s
133
Inflection 3 Productivity
10.1s
134
Kimi K2 0711
10.1s
135
Rocinante 12B
10.2s
136
Claude 3.7 Sonnet
10.3s
137
Grok Code Fast 1
10.3s
138
Claude Sonnet 4
10.3s
139
Qwen2.5 7B Instruct
10.5s
140
Llama 3.1 70B Instruct
10.6s
141
Qwen-Plus
10.6s
142
Gemma 3n 4B
10.7s
143
gpt-oss-120b (exacto)
10.7s
144
GPT-4 Turbo (older v1106)
10.7s
145
Grok 4.1 Fast
10.8s
146
Qwen Plus 0728
10.8s
147
GPT-4
11.0s
148
GPT-4 Turbo
11.1s
149
Qwen3 Coder Plus
11.1s
150
GPT-5.2-Codex
11.1s
151
DeepSeek V3
11.2s
152
Gemma 3 27B
11.2s
153
o4 Mini High
11.2s
154
Pixtral Large 2411
11.3s
155
Mistral Large
11.7s
156
Qwen3 Coder Next
11.7s
157
Nova Premier 1.0
11.7s
158
GPT-4 (older v0314)
11.8s
159
Qwen3 Coder 480B A35B
11.8s
160
Mistral Large 3 2512
11.9s
161
SorcererLM 8x22B
12.0s
162
Claude Sonnet 4.6
12.0s
163
Mistral Large 2407
12.0s
164
Qwen3 Coder 30B A3B Instruct
12.2s
165
Sonar Reasoning Pro
12.3s
166
Weaver (alpha)
12.5s
167
Claude Sonnet 4.5
12.6s
168
Gemma 3 12B
12.7s
169
Nemotron Nano 12B 2 VL
12.7s
170
ReMM SLERP 13B
12.8s
171
Olmo 3.1 32B Instruct
12.8s
172
Gemma 3 4B
12.8s
173
GLM 4.5 Air
12.9s
174
Llama 3.1 Nemotron Ultra 253B v1
12.9s
175
ERNIE 4.5 300B A47B
13.0s
176
GPT-4 Turbo Preview
13.0s
177
Llama 3 8B Instruct
13.1s
178
Qwen2.5 72B Instruct
13.2s
179
Phi 4
13.2s
180
Claude Opus 4.5
13.3s
181
Llama 3 70B Instruct
13.5s
182
Llama 3.3 70B Instruct
13.6s
183
Cogito V2 Preview Llama 405B
13.6s
184
Command R (08-2024)
13.6s
185
Qwen3.5 Plus 2026-02-15
13.6s
186
Qwen3 30B A3B Instruct 2507
13.8s
187
Noromaid 20B
13.9s
188
Grok 3 Mini
13.9s
189
ERNIE 4.5 VL 28B A3B
14.2s
190
Trinity Large Preview
14.2s
191
Grok 3 Mini Beta
14.2s
192
R1 Distill Llama 70B
14.2s
193
Miri
14.2s
194
Llama 3.1 Nemotron 70B Instruct
14.3s
195
Claude 3.5 Sonnet
14.3s
196
GPT-5 Mini
14.5s
197
MiMo-V2-Flash
14.5s
198
GPT-5.2
14.6s
199
GPT-5 Image Mini
14.7s
200
Claude Opus 4.6
15.0s
201
Auto Router
15.1s
202
Qwen2.5 Coder 32B Instruct
15.1s
203
Granite 4.0 Micro
15.1s
204
MythoMax 13B
15.2s
205
GPT-5.1
15.6s
206
Qwen2.5 VL 72B Instruct
15.7s
207
Nano Banana (Gemini 2.5 Flash Image)
15.9s
208
MiniMax M2
16.0s
209
Jamba Large 1.7
16.0s
210
Olmo 3 7B Think
16.3s
211
Qwen3 VL 30B A3B Instruct
16.4s
212
Qwen VL Max
16.6s
213
Qwen3 Max
16.7s
214
Qwen3 VL 32B Instruct
16.7s
215
Step 3.5 Flash
16.8s
216
R1 0528
16.8s
217
DeepSeek V3.1 Terminus (exacto)
16.9s
218
Switchpoint Router
17.1s
219
DeepSeek V3 0324
17.2s
220
Grok 3 Beta
17.3s
221
Qwen3 VL 235B A22B Instruct
17.3s
222
Grok 3
17.3s
223
Qwen3 30B A3B Thinking 2507
17.4s
224
Gemini 3.1 Pro Preview Custom Tools
17.7s
225
Qwen3 Next 80B A3B Thinking
17.9s
226
GLM 4.6
18.2s
227
DeepSeek V3.1 Terminus
18.4s
228
Olmo 3 7B Instruct
18.5s
229
GPT-5
18.7s
230
ERNIE 4.5 VL 424B A47B
18.7s
231
GPT-5 Image
18.8s
232
Qwen3 VL 8B Instruct
19.1s
233
Llama 3.3 Nemotron Super 49B V1.5
19.3s
234
GPT-5 Nano
20.1s
235
MiniMax M1
20.3s
236
Llama 3.1 8B Instruct
20.8s
237
Llama 3.3 Euryale 70B
20.9s
238
Llama 3.1 Euryale 70B v2.2
21.1s
239
Gemini 3.1 Pro Preview
21.4s
240
Qwen3 Max Thinking
21.5s
241
Nano Banana Pro (Gemini 3 Pro Image Preview)
22.1s
242
Free Models Router
22.2s
243
Qwen3 235B A22B Instruct 2507
22.3s
244
Mistral 7B Instruct v0.1
22.4s
245
Hermes 3 405B Instruct
22.9s
246
Gemini 2.5 Pro
23.1s
247
MiniMax M2.1
23.1s
248
Gemini 2.5 Pro Preview 06-05
23.2s
249
Gemini 3 Pro Preview
23.4s
250
Gemini 2.5 Pro Preview 05-06
23.5s
251
Devstral 2 2512
23.6s
252
Qwen3.5-122B-A10B
23.9s
253
Goliath 120B
24.0s
254
Qwen3 32B
24.0s
255
DeepSeek V3.1 Nex N1
24.3s
256
MiMo-V2-Flash
24.7s
257
Qwen3 14B
25.0s
258
Aion-1.0
25.2s
259
GLM 4.5V
25.4s
260
Medgemma
25.5s
261
Qwen3.5-Flash
25.9s
262
Nemotron 3 Nano 30B A3B
26.0s
263
Llama 3.2 3B Instruct
26.1s
264
Qwen3 235B A22B
26.5s
265
Qwen3 VL 30B A3B Thinking
26.9s
266
Claude Opus 4
27.0s
267
GLM 4.5
27.2s
268
Grok 4
28.0s
269
Qwen Plus 0728 (thinking)
28.1s
270
Tongyi DeepResearch 30B A3B
28.3s
271
ERNIE 4.5 21B A3B Thinking
29.0s
272
DeepSeek V3.2
29.7s
273
Claude Opus 4.1
29.8s
274
Claude 3.7 Sonnet (thinking)
29.9s
275
Solar Pro 3
31.0s
276
o1-pro
31.0s
277
CodeLLaMa 7B Instruct Solidity
31.1s
278
MiniMax M2.5
31.3s
279
Llama 3.1 70B Hanami x1
31.4s
280
DeepSeek V3.2 Exp
31.5s
281
Qwen3.5-35B-A3B
31.5s
282
GLM 4.6 (exacto)
32.5s
283
Qwen3.5-27B
33.3s
284
Qwen3 VL 235B A22B Thinking
33.7s
285
Aion-2.0
35.3s
286
GLM 4.6V
35.6s
287
o3 Pro
36.1s
288
R1 Distill Qwen 32B
37.0s
289
Seed 1.6
37.2s
290
GPT-5.2 Pro
38.8s
291
Qwen3 8B
39.3s
292
Qwen2.5 VL 32B Instruct
40.2s
293
DeepSeek V3.1
40.6s
294
Qwen3 VL 8B Thinking
41.3s
295
GLM 4.7
41.6s
296
R1
43.8s
297
Kimi K2.5
44.3s
298
Sonar Deep Research
46.0s
299
Olmo 3 32B Think
47.6s
300
Olmo 3.1 32B Think
47.6s
301
Kimi K2 Thinking
48.2s
302
Qwen3 4B
49.7s
303
Step3
51.5s
304
Kimi Dev 72B
51.9s
305
Llama 3.2 11B Vision Instruct
53.9s
306
QwQ 32B
55.2s
307
Seed-2.0-Mini
59.3s
308
DeepSeek V3.2 Speciale
60.9s
309
Llemma 7b
66.2s
310
Qwen3.5 397B A17B
79.3s
311
Qwen3 235B A22B Thinking 2507
85.5s
312
o4 Mini Deep Research
90.7s
313
ALMA
94.7s
314
GLM 5
100.7s
315
GLM 4.7 Flash
119.3s
316
GPT-5.4 Pro
120.4s
317
o3 Deep Research
127.7s
318
Hermes 3 70B Instruct
177.4s
Average:17.7s
(318 modelos)
Metrics menu
Average cost per question
Average cost in USD per evaluated question
1
LFM2-8B-A1B
$0.0000
2
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
$0.0000
3
Mistral Nemo
$0.0000
4
Ministral 3B
$0.0000
5
Gemma 3n 4B
$0.0000
6
Llama 3 8B Lunaris
$0.0000
7
Gemma 2 9B
$0.0000
8
Llama 3 8B Instruct
$0.0001
9
Gemma 3 4B
$0.0001
10
Granite 4.0 Micro
$0.0001
11
Llama 3.2 3B Instruct
$0.0001
12
MythoMax 13B
$0.0001
13
Command R7B (12-2024)
$0.0001
14
Ministral 8B
$0.0001
15
Qwen2.5 7B Instruct
$0.0001
16
LFM2-24B-A2B
$0.0001
17
GLM 4 32B
$0.0001
18
Llama 3.1 8B Instruct
$0.0001
19
Nova Micro 1.0
$0.0001
20
Mistral Small 3
$0.0001
21
Llama 3.2 1B Instruct
$0.0001
22
Pixtral 12B
$0.0001
23
Phi 4
$0.0001
24
Voxtral Small 24B 2507
$0.0001
25
Hermes 2 Pro - Llama-3 8B
$0.0001
26
Gemma 3 12B
$0.0001
27
Qwen-Turbo
$0.0001
28
Mistral 7B Instruct v0.1
$0.0001
29
Devstral Small 1.1
$0.0001
30
Nova Lite 1.0
$0.0001
31
Ministral 3 3B 2512
$0.0001
32
Mistral Small 3.2 24B
$0.0002
33
Trinity Mini
$0.0002
34
Rnj 1 Instruct
$0.0002
35
Gemini 2.0 Flash Lite
$0.0002
36
gpt-oss-120b (exacto)
$0.0002
37
Gemma 3 27B
$0.0002
38
ERNIE 4.5 21B A3B
$0.0002
39
Mistral 7B Instruct v0.3
$0.0002
40
Mistral 7B Instruct v0.2
$0.0002
41
Mistral 7B Instruct
$0.0002
42
Llama 3.2 11B Vision Instruct
$0.0002
43
Ministral 3 8B 2512
$0.0002
44
Qwen2.5-VL 7B Instruct
$0.0002
45
Molmo2 8B
$0.0002
46
Lumimaid v0.2 8B
$0.0002
47
GPT-4.1 Nano
$0.0002
48
Gemini 2.0 Flash
$0.0002
49
Olmo 3 7B Instruct
$0.0002
50
Hermes 4 70B
$0.0002
51
Qwen3 Coder 30B A3B Instruct
$0.0002
52
Nemotron Nano 9B V2
$0.0003
53
gpt-oss-20b
$0.0003
54
Mistral Tiny
$0.0003
55
Ministral 3 14B 2512
$0.0003
56
Llama 4 Scout
$0.0003
57
Qwen2.5 72B Instruct
$0.0003
58
Saba
$0.0003
59
Command R (08-2024)
$0.0003
60
Jamba Mini 1.7
$0.0003
61
Qwen3 14B
$0.0003
62
Qwen3 30B A3B Instruct 2507
$0.0003
63
gpt-oss-safeguard-20b
$0.0003
64
UnslopNemo 12B
$0.0003
65
Mistral Small 3.1 24B
$0.0003
66
MiMo-V2-Flash
$0.0003
67
Qwen3 4B
$0.0004
68
Rocinante 12B
$0.0004
69
DeepSeek V3.2 Exp
$0.0004
70
Qwen3 8B
$0.0004
71
KAT-Coder-Pro V1
$0.0004
72
Llama 3.1 70B Instruct
$0.0004
73
Hunyuan A13B Instruct
$0.0004
74
DeepSeek V3.2
$0.0004
75
Qwen2.5 Coder 32B Instruct
$0.0004
76
GPT-4o Search Preview
$0.0004
77
Gemini 2.5 Flash Lite
$0.0004
78
Cydonia 24B V4.1
$0.0004
79
Seed 1.6 Flash
$0.0004
80
Gemma 2 27B
$0.0004
81
gpt-oss-120b
$0.0005
82
Gemini 2.5 Flash Lite Preview 09-2025
$0.0005
83
Llama 3.3 70B Instruct
$0.0005
84
Mistral Small Creative
$0.0005
85
Qwen3 235B A22B Instruct 2507
$0.0005
86
Mercury Coder
$0.0005
87
Mercury
$0.0005
88
Llama 3 70B Instruct
$0.0005
89
Gemini 3.1 Pro Preview
$0.0005
90
Codestral 2508
$0.0005
91
ReMM SLERP 13B
$0.0005
92
Olmo 3.1 32B Instruct
$0.0006
93
Mixtral 8x7B Instruct
$0.0006
94
Llama 4 Maverick
$0.0006
95
Qwen2.5 VL 72B Instruct
$0.0006
96
Qwen3 32B
$0.0006
97
DeepSeek V3 0324
$0.0006
98
DeepSeek V3
$0.0006
99
DeepSeek V3.1 Terminus (exacto)
$0.0006
100
Qwen VL Plus
$0.0006
101
Skyfall 36B V2
$0.0006
102
Mercury 2
$0.0006
103
Claude 3 Haiku
$0.0007
104
GPT-4o-mini
$0.0007
105
GPT-4o-mini (2024-07-18)
$0.0007
106
ERNIE 4.5 300B A47B
$0.0007
107
Grok 4 Fast
$0.0007
108
Aion-1.0-Mini
$0.0007
109
Llama 3.3 Nemotron Super 49B V1.5
$0.0007
110
ERNIE 4.5 VL 28B A3B
$0.0007
111
GPT-3.5 Turbo
$0.0007
112
DeepSeek V3.1
$0.0007
113
Grok 4.1 Fast
$0.0007
114
Olmo 3 7B Think
$0.0007
115
Qwen3 30B A3B Thinking 2507
$0.0007
116
Qwen3 VL 30B A3B Instruct
$0.0007
117
Tongyi DeepResearch 30B A3B
$0.0008
118
DeepSeek V3.1 Terminus
$0.0008
119
Nemotron 3 Nano 30B A3B
$0.0008
120
Cogito V2 Preview Llama 70B
$0.0008
121
Qwen2.5 VL 32B Instruct
$0.0008
122
Hermes 3 405B Instruct
$0.0008
123
ERNIE 4.5 21B A3B Thinking
$0.0008
124
GPT-5 Nano
$0.0008
125
Step 3.5 Flash
$0.0008
126
Llama 3.3 Euryale 70B
$0.0009
127
Qwen3 VL 235B A22B Instruct
$0.0009
128
Llama 3.1 Euryale 70B v2.2
$0.0009
129
Grok 3 Mini Beta
$0.0009
130
Grok 3 Mini
$0.0009
131
Seed-2.0-Mini
$0.0009
132
QwQ 32B
$0.0009
133
Qwen3 VL 8B Instruct
$0.0009
134
GLM 4.5 Air
$0.0010
135
Devstral Medium
$0.0010
136
GPT-4.1 Mini
$0.0010
137
Aion-RP 1.0 (8B)
$0.0010
138
DeepSeek V3.1 Nex N1
$0.0010
139
Qwen3 Next 80B A3B Instruct
$0.0010
140
MiniMax M2-her
$0.0010
141
GPT-5.1-Codex-Mini
$0.0010
142
Weaver (alpha)
$0.0011
143
R1 Distill Qwen 32B
$0.0011
144
Qwen3 Coder 480B A35B
$0.0011
145
Mistral Medium 3
$0.0011
146
Cogito v2.1 671B
$0.0011
147
Qwen-Plus
$0.0011
148
Qwen Plus 0728
$0.0012
149
ERNIE 4.5 VL 424B A47B
$0.0012
150
Mistral Large 3 2512
$0.0012
151
Qwen3 235B A22B
$0.0012
152
Qwen3 Coder 480B A35B (exacto)
$0.0012
153
Nemotron Nano 12B 2 VL
$0.0012
154
Qwen3 Coder Flash
$0.0013
155
Llama 3.1 Nemotron Ultra 253B v1
$0.0013
156
Qwen3 Coder Next
$0.0013
157
R1 Distill Llama 70B
$0.0013
158
MiniMax M2.5
$0.0013
159
MiniMax M2.1
$0.0014
160
Llama 3 Euryale 70B v2.1
$0.0014
161
Morph V3 Large
$0.0014
162
Hermes 4 405B
$0.0014
163
GPT-3.5 Turbo (older v0613)
$0.0014
164
Llama 3.1 Nemotron 70B Instruct
$0.0014
165
DeepSeek V3.2 Speciale
$0.0015
166
Noromaid 20B
$0.0015
167
Qwen3.5-Flash
$0.0015
168
Kimi K2 0711
$0.0015
169
GPT-3.5 Turbo Instruct
$0.0015
170
Qwen3 VL 32B Instruct
$0.0015
171
GLM 4.7 Flash
$0.0015
172
MiniMax M2
$0.0015
173
Mistral Medium 3.1
$0.0016
174
Kimi K2 0905
$0.0016
175
Nova Pro 1.0
$0.0016
176
Kimi Dev 72B
$0.0016
177
Aion-2.0
$0.0017
178
Gemini 3 Flash Preview
$0.0017
179
GLM 4.5V
$0.0017
180
CodeLLaMa 7B Instruct Solidity
$0.0017
181
GLM 4.6
$0.0018
182
GLM 4.6V
$0.0018
183
Olmo 3 32B Think
$0.0019
184
Olmo 3.1 32B Think
$0.0019
185
Qwen3 VL 30B A3B Thinking
$0.0020
186
Claude 3.5 Haiku
$0.0020
187
Grok Code Fast 1
$0.0020
188
GPT-5 Mini
$0.0021
189
Gemini 2.5 Flash
$0.0024
190
MiniMax M1
$0.0025
191
Relace Search
$0.0025
192
Gemini 2.5 Flash Preview 09-2025
$0.0026
193
Hermes 3 70B Instruct
$0.0027
194
Nova 2 Lite
$0.0028
195
Seed 1.6
$0.0028
196
Qwen3 235B A22B Thinking 2507
$0.0028
197
GLM 4.5
$0.0029
198
Qwen VL Max
$0.0029
199
Switchpoint Router
$0.0029
200
GLM 4.6 (exacto)
$0.0029
201
Nano Banana (Gemini 2.5 Flash Image)
$0.0030
202
Cogito V2 Preview Llama 405B
$0.0030
203
Qwen3.5 Plus 2026-02-15
$0.0030
204
Step3
$0.0030
205
GPT-5.1-Codex
$0.0030
206
Mixtral 8x22B Instruct
$0.0031
207
Llama 3.1 70B Hanami x1
$0.0031
208
Llemma 7b
$0.0032
209
GPT-5.1 Chat
$0.0034
210
Qwen3 Next 80B A3B Thinking
$0.0037
211
Qwen3 Coder Plus
$0.0038
212
Kimi K2 0905 (exacto)
$0.0038
213
Miri
$0.0039
214
Palmyra X5
$0.0040
215
Mistral Large 2411
$0.0040
216
R1
$0.0040
217
GPT-5 Image Mini
$0.0041
218
Claude Haiku 4.5
$0.0041
219
Command A
$0.0044
220
GPT-4.1
$0.0045
221
Mistral Large
$0.0045
222
Qwen3.5-35B-A3B
$0.0045
223
R1 0528
$0.0045
224
Pixtral Large 2411
$0.0046
225
Qwen3 Max
$0.0046
226
Mistral Large 2407
$0.0046
227
Qwen3 Max Thinking
$0.0047
228
Qwen-Max
$0.0047
229
Command R+ (08-2024)
$0.0047
230
Kimi K2 Thinking
$0.0048
231
GPT-5 Codex
$0.0048
232
Inflection 3 Productivity
$0.0050
233
Inflection 3 Pi
$0.0050
234
GPT-4o
$0.0051
235
Qwen3.5-27B
$0.0052
236
GPT-4o (2024-08-06)
$0.0052
237
GPT-5 Chat
$0.0054
238
Qwen3.5 397B A17B
$0.0055
239
GLM 4.7
$0.0056
240
SorcererLM 8x22B
$0.0056
241
Nova Premier 1.0
$0.0059
242
Qwen3 VL 235B A22B Thinking
$0.0059
243
Sonar
$0.0063
244
o3 Mini High
$0.0064
245
Goliath 120B
$0.0064
246
o3 Mini
$0.0064
247
o4 Mini
$0.0065
248
Kimi K2.5
$0.0065
249
Qwen3.5-122B-A10B
$0.0067
250
Qwen3 VL 8B Thinking
$0.0070
251
Morph V3 Fast
$0.0071
252
GPT-4o (2024-11-20)
$0.0073
253
Jamba Large 1.7
$0.0081
254
GPT-5.2 Chat
$0.0081
255
Qwen Plus 0728 (thinking)
$0.0086
256
GPT-5.2-Codex
$0.0091
257
GPT-4o (2024-05-13)
$0.0095
258
GPT-5.1
$0.0099
259
GLM 5
$0.0102
260
Aion-1.0
$0.0102
261
GPT-5.2
$0.0102
262
o4 Mini High
$0.0107
263
o3
$0.0109
264
GPT-5
$0.0109
265
ChatGPT-4o
$0.0110
266
Claude Sonnet 4
$0.0110
267
GPT-5.1-Codex-Max
$0.0119
268
Claude 3.7 Sonnet
$0.0124
269
Claude Sonnet 4.5
$0.0127
270
Claude Sonnet 4.6
$0.0129
271
Grok 3
$0.0131
272
Grok 3 Beta
$0.0132
273
Sonar Pro
$0.0160
274
Claude 3.5 Sonnet
$0.0168
275
Sonar Reasoning Pro
$0.0173
276
GPT-5 Image
$0.0187
277
Auto Router
$0.0209
278
GPT-4 Turbo
$0.0209
279
Grok 4
$0.0215
280
GPT-4 Turbo Preview
$0.0219
281
Claude Opus 4.5
$0.0231
282
Claude Opus 4.6
$0.0242
283
Sonar Pro Search
$0.0272
284
Nano Banana Pro (Gemini 3 Pro Image Preview)
$0.0276
285
Gemini 2.5 Pro
$0.0287
286
Gemini 2.5 Pro Preview 06-05
$0.0288
287
Gemini 3 Pro Preview
$0.0289
288
Gemini 2.5 Pro Preview 05-06
$0.0293
289
Claude 3.7 Sonnet (thinking)
$0.0360
290
GPT-4 (older v0314)
$0.0381
291
GPT-4
$0.0418
292
ALMA
$0.0499
293
Claude Opus 4
$0.0523
294
Claude Opus 4.1
$0.0556
295
o3 Pro
$0.1048
296
o1
$0.1147
297
GPT-5.2 Pro
$0.1226
298
o4 Mini Deep Research
$0.1792
299
o3 Deep Research
$0.7948
300
Sonar Deep Research
$1.1791
301
o1-pro
$1.1830
Average:$0.0100
(301 modelos)
Metrics menu
Average confidence
Average confidence level reported by the model
1
Gemini 3.1 Pro Preview
100.0%
2
Gemini 3 Flash Preview
100.0%
3
GPT-5 Chat
100.0%
4
Gemini 2.5 Pro Preview 05-06
100.0%
5
o3 Pro
100.0%
6
Gemini 3.1 Pro Preview Custom Tools
100.0%
7
GPT-5.1-Codex-Mini
100.0%
8
GPT-5.1 Chat
100.0%
9
o4 Mini
100.0%
10
GPT-5.2 Chat
100.0%
11
Qwen3.5-122B-A10B
100.0%
12
Aion-1.0
100.0%
13
GPT-5.1-Codex-Max
100.0%
14
Claude Opus 4.5
100.0%
15
Nano Banana Pro (Gemini 3 Pro Image Preview)
100.0%
16
o1-pro
100.0%
17
o4 Mini Deep Research
100.0%
18
gpt-oss-120b
100.0%
19
Grok 4 Fast
100.0%
20
Qwen3 VL 30B A3B Thinking
100.0%
21
Grok 4.1 Fast
100.0%
22
gpt-oss-20b
100.0%
23
Mistral Large 2411
100.0%
24
Gemini 2.5 Pro
100.0%
25
o3 Deep Research
100.0%
26
Gemini 3 Pro Preview
100.0%
27
DeepSeek V3.2 Speciale
100.0%
28
Claude Sonnet 4.5
100.0%
29
Gemini 2.5 Pro Preview 06-05
100.0%
30
o4 Mini High
100.0%
31
GPT-4.1
100.0%
32
Qwen3 VL 235B A22B Instruct
100.0%
33
Qwen Plus 0728 (thinking)
100.0%
34
R1 0528
100.0%
35
Step3
100.0%
36
Qwen3.5 397B A17B
100.0%
37
GPT-5 Mini
100.0%
38
GLM 5
100.0%
39
Auto Router
100.0%
40
Mistral Medium 3.1
100.0%
41
Claude Sonnet 4
100.0%
42
Qwen3 VL 235B A22B Thinking
100.0%
43
Claude Opus 4.1
100.0%
44
o3 Mini
100.0%
45
Qwen3 235B A22B Thinking 2507
100.0%
46
Grok 4
100.0%
47
Gemini 3.1 Flash Lite Preview
100.0%
48
Gemini 2.5 Flash Preview 09-2025
100.0%
49
GPT-5.3 Chat
100.0%
50
Claude Opus 4
99.9%
51
ALMA
99.9%
52
Claude 3.5 Sonnet
99.9%
53
Mistral Large
99.9%
54
Claude 3.7 Sonnet
99.9%
55
Mistral Large 2407
99.9%
56
GLM 4.6V
99.9%
57
Miri
99.9%
58
Mistral Large 3 2512
99.9%
59
GPT-5.4
99.9%
60
ChatGPT-4o
99.9%
61
Qwen Plus 0728
99.9%
62
Tongyi DeepResearch 30B A3B
99.9%
63
GPT-4o (2024-11-20)
99.9%
64
GLM 4.5
99.9%
65
o1
99.9%
66
Gemini 2.0 Flash
99.9%
67
Claude Opus 4.6
99.9%
68
Mercury 2
99.9%
69
gpt-oss-safeguard-20b
99.9%
70
Gemma 3 27B
99.8%
71
Claude Sonnet 4.6
99.8%
72
Gemini 2.5 Flash Lite
99.8%
73
Aion-2.0
99.8%
74
Qwen3.5 Plus 2026-02-15
99.8%
75
GPT-5.1
99.8%
76
Kimi K2.5
99.8%
77
GPT-4 Turbo
99.8%
78
Nemotron 3 Nano 30B A3B
99.8%
79
Mistral Small Creative
99.7%
80
Ministral 3 14B 2512
99.7%
81
Qwen2.5 72B Instruct
99.7%
82
GPT-5.4 Pro
99.7%
83
Switchpoint Router
99.7%
84
Qwen3.5-35B-A3B
99.7%
85
GPT-5.3-Codex
99.7%
86
GPT-5 Codex
99.7%
87
ERNIE 4.5 300B A47B
99.7%
88
Qwen3 30B A3B Instruct 2507
99.6%
89
Mistral Medium 3
99.6%
90
Command A
99.6%
91
Qwen-Max
99.6%
92
Claude Haiku 4.5
99.6%
93
GPT-3.5 Turbo
99.6%
94
GPT-5.2 Pro
99.5%
95
GLM 4.7
99.5%
96
DeepSeek V3.1 Terminus
99.5%
97
gpt-oss-120b (exacto)
99.5%
98
GPT-5.2
99.5%
99
Seed 1.6
99.5%
100
Sonar Deep Research
99.5%
101
GPT-5
99.5%
102
R1
99.5%
103
Claude 3.7 Sonnet (thinking)
99.5%
104
Qwen3 235B A22B
99.5%
105
Qwen3 VL 32B Instruct
99.5%
106
QwQ 32B
99.5%
107
Aurora Alpha
99.5%
108
o3
99.4%
109
Qwen3 Next 80B A3B Instruct
99.4%
110
Devstral Medium
99.4%
111
Mercury Coder
99.4%
112
GPT-5 Image Mini
99.4%
113
GPT-4.1 Mini
99.4%
114
GPT-4o Search Preview
99.4%
115
Qwen3 Coder 480B A35B
99.4%
116
Mistral Small 3.2 24B
99.3%
117
Gemma 3 12B
99.3%
118
GLM 4.6 (exacto)
99.3%
119
DeepSeek V3
99.2%
120
GPT-3.5 Turbo (older v0613)
99.2%
121
Qwen3 30B A3B Thinking 2507
99.2%
122
Grok 3
99.1%
123
Llama 4 Maverick
99.1%
124
GPT-5.2-Codex
99.1%
125
GPT-5 Nano
99.0%
126
Qwen3 Next 80B A3B Thinking
99.0%
127
Mercury
99.0%
128
DeepSeek V3.2
99.0%
129
Qwen3 Coder 480B A35B (exacto)
99.0%
130
Pixtral Large 2411
99.0%
131
Mistral Small 3.1 24B
99.0%
132
Ministral 3 8B 2512
99.0%
133
Grok 3 Beta
99.0%
134
Qwen3 235B A22B Instruct 2507
99.0%
135
DeepSeek V3.2 Exp
99.0%
136
o3 Mini High
99.0%
137
Qwen3 Coder Next
99.0%
138
Palmyra X5
99.0%
139
DeepSeek V3.1 Terminus (exacto)
98.9%
140
Jamba Large 1.7
98.9%
141
GPT-4o (2024-05-13)
98.9%
142
GPT-5 Image
98.9%
143
Devstral 2 2512
98.9%
144
Qwen3 VL 30B A3B Instruct
98.9%
145
R1 Distill Qwen 32B
98.9%
146
Grok 3 Mini
98.8%
147
MiMo-V2-Flash
98.8%
148
GPT-5.1-Codex
98.8%
149
Gemma 3 4B
98.8%
150
Llama 3.1 Nemotron Ultra 253B v1
98.8%
151
Devstral Small 1.1
98.8%
152
Gemini 2.5 Flash Lite Preview 09-2025
98.7%
153
Hermes 3 405B Instruct
98.7%
154
Qwen3 4B
98.7%
155
MiMo-V2-Flash
98.7%
156
Medgemma
98.7%
157
GPT-3.5 Turbo 16k
98.7%
158
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
98.7%
159
GPT-4o-mini
98.7%
160
ERNIE 4.5 VL 424B A47B
98.7%
161
Step 3.5 Flash
98.6%
162
Llama 3 70B Instruct
98.6%
163
Qwen3 32B
98.5%
164
R1 Distill Llama 70B
98.5%
165
Gemini 2.5 Flash
98.5%
166
DeepSeek V3 0324
98.5%
167
Qwen VL Max
98.5%
168
Qwen-Plus
98.5%
169
Saba
98.5%
170
Nova Pro 1.0
98.5%
171
GLM 4.5V
98.5%
172
Llama 3.3 Nemotron Super 49B V1.5
98.5%
173
Relace Search
98.5%
174
Sonar Pro
98.4%
175
Mixtral 8x22B Instruct
98.4%
176
Voxtral Small 24B 2507
98.4%
177
Solar Pro 3
98.4%
178
Kimi K2 Thinking
98.4%
179
Qwen VL Plus
98.4%
180
ERNIE 4.5 21B A3B Thinking
98.4%
181
Sonar Pro Search
98.3%
182
GPT-4o-mini (2024-07-18)
98.3%
183
GLM 4.6
98.3%
184
Claude 3.5 Haiku
98.3%
185
Llama 4 Scout
98.3%
186
Qwen3 Max Thinking
98.2%
187
GPT-4.1 Nano
98.1%
188
Nova Premier 1.0
98.1%
189
Command R+ (08-2024)
98.1%
190
Qwen2.5 VL 72B Instruct
98.1%
191
DeepSeek V3.1
98.1%
192
Qwen3 Max
98.0%
193
Grok 3 Mini Beta
98.0%
194
Qwen2.5 VL 32B Instruct
98.0%
195
Qwen3 Coder Plus
98.0%
196
Qwen3 Coder 30B A3B Instruct
98.0%
197
Llama 3.1 70B Instruct
98.0%
198
ERNIE 4.5 VL 28B A3B
98.0%
199
Mistral Small 3
98.0%
200
GPT-4o-mini Search Preview
97.9%
201
MiniMax M2.5
97.9%
202
Nova 2 Lite
97.9%
203
MiniMax M2
97.8%
204
Qwen3 VL 8B Thinking
97.8%
205
GPT-3.5 Turbo Instruct
97.8%
206
Step 3.5 Flash
97.7%
207
Claude 3 Haiku
97.7%
208
GPT-4 Turbo Preview
97.7%
209
Gemini 2.0 Flash Lite
97.6%
210
Kimi K2 0711
97.6%
211
Inflection 3 Productivity
97.6%
212
Llama 3.3 70B Instruct
97.6%
213
Qwen3 Coder Flash
97.6%
214
Free Models Router
97.5%
215
GPT-4o (2024-08-06)
97.5%
216
Kimi Dev 72B
97.5%
217
Qwen3.5-27B
97.4%
218
Olmo 3 7B Think
97.4%
219
GPT-4o
97.4%
220
Inflection 3 Pi
97.4%
221
Sonar
97.2%
222
Qwen3.5-Flash
97.2%
223
KAT-Coder-Pro V1
97.2%
224
Trinity Large Preview
97.2%
225
Command R (08-2024)
97.1%
226
Qwen3 14B
97.0%
227
Phi 4
97.0%
228
Qwen-Turbo
97.0%
229
GLM 4.7 Flash
96.9%
230
Cogito V2 Preview Llama 405B
96.9%
231
DeepSeek V3.1 Nex N1
96.9%
232
Seed 1.6 Flash
96.8%
233
Hermes 4 70B
96.7%
234
LFM2-24B-A2B
96.6%
235
Granite 4.0 Micro
96.6%
236
GPT-4 (older v0314)
96.5%
237
Nano Banana (Gemini 2.5 Flash Image)
96.5%
238
Cogito v2.1 671B
96.4%
239
MiniMax M1
96.4%
240
Cogito V2 Preview Llama 70B
96.3%
241
Grok Code Fast 1
96.3%
242
Llama 3.1 Nemotron 70B Instruct
96.2%
243
Ministral 3 3B 2512
96.2%
244
Nemotron Nano 12B 2 VL
96.2%
245
Qwen3 8B
96.2%
246
Cydonia 24B V4.1
96.1%
247
GPT-4
96.0%
248
ERNIE 4.5 21B A3B
96.0%
249
LFM2-8B-A1B
95.9%
250
Qwen3 VL 8B Instruct
95.6%
251
GLM 4 32B
95.6%
252
GLM 4.5 Air
95.6%
253
Mistral Nemo
95.5%
254
Ministral 8B
95.4%
255
Pixtral 12B
95.3%
256
MiniMax M2.1
95.2%
257
Jamba Mini 1.7
95.2%
258
Skyfall 36B V2
95.0%
259
Kimi K2 0905
95.0%
260
Seed-2.0-Mini
95.0%
261
Aion-1.0-Mini
94.9%
262
MiniMax M2-her
94.8%
263
Olmo 3.1 32B Instruct
94.7%
264
Trinity Mini
94.6%
265
Hermes 4 405B
94.3%
266
Nova Lite 1.0
94.3%
267
Llama 3.3 Euryale 70B
94.2%
268
Mixtral 8x7B Instruct
94.1%
269
Gemma 3n 4B
94.1%
270
Molmo2 8B
93.9%
271
GPT-4 Turbo (older v1106)
93.9%
272
Llama 3 Euryale 70B v2.1
93.3%
273
Kimi K2 0905 (exacto)
93.3%
274
Llama 3.1 70B Hanami x1
93.3%
275
Mistral 7B Instruct
93.2%
276
Command R7B (12-2024)
93.2%
277
Gemma 2 27B
92.8%
278
Llama 3 8B Lunaris
92.8%
279
Mistral Tiny
92.8%
280
Llama 3.1 Euryale 70B v2.2
92.7%
281
Mistral 7B Instruct v0.3
92.3%
282
Lumimaid v0.2 8B
92.1%
283
Sonar Reasoning Pro
92.1%
284
Mistral 7B Instruct v0.2
92.0%
285
SorcererLM 8x22B
91.8%
286
Nova Micro 1.0
91.5%
287
Olmo 3 32B Think
90.4%
288
Codestral 2508
90.4%
289
Qwen2.5 7B Instruct
90.2%
290
Nemotron Nano 9B V2
90.0%
291
Gemma 2 9B
89.1%
292
Olmo 3.1 32B Think
89.0%
293
Olmo 3 7B Instruct
88.7%
294
Goliath 120B
87.7%
295
Qwen2.5-VL 7B Instruct
87.0%
296
Qwen2.5 Coder 32B Instruct
85.8%
297
Rnj 1 Instruct
85.2%
298
Llama 3 8B Instruct
84.2%
299
Hermes 2 Pro - Llama-3 8B
84.1%
300
Mistral 7B Instruct v0.1
84.0%
301
Llama 3.1 8B Instruct
81.6%
302
Llama 3.2 3B Instruct
81.0%
303
ReMM SLERP 13B
79.1%
304
Weaver (alpha)
79.0%
305
Hunyuan A13B Instruct
78.5%
306
Noromaid 20B
75.6%
307
Ministral 3B
74.6%
308
MythoMax 13B
72.1%
309
Rocinante 12B
72.0%
310
UnslopNemo 12B
68.3%
311
Hermes 3 70B Instruct
64.7%
312
Aion-RP 1.0 (8B)
58.0%
313
Llama 3.2 11B Vision Instruct
57.2%
314
Llama 3.2 1B Instruct
47.8%
315
Morph V3 Large
41.1%
316
Morph V3 Fast
32.9%
317
CodeLLaMa 7B Instruct Solidity
24.0%
318
Llemma 7b
22.9%
Average:95.7%
(318 modelos)
Metrics menu
Total Cost
Total cost in USD to evaluate all questions
1
LFM2-8B-A1B
$0.00
2
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
$0.00
3
Mistral Nemo
$0.01
4
Ministral 3B
$0.01
5
Gemma 3n 4B
$0.01
6
Llama 3 8B Lunaris
$0.01
7
Gemma 2 9B
$0.01
8
Llama 3 8B Instruct
$0.01
9
Gemma 3 4B
$0.01
10
Granite 4.0 Micro
$0.01
11
Llama 3.2 3B Instruct
$0.01
12
MythoMax 13B
$0.01
13
Command R7B (12-2024)
$0.02
14
Ministral 8B
$0.02
15
Qwen2.5 7B Instruct
$0.02
16
LFM2-24B-A2B
$0.02
17
GLM 4 32B
$0.02
18
Llama 3.1 8B Instruct
$0.02
19
Nova Micro 1.0
$0.02
20
Mistral Small 3
$0.02
21
Llama 3.2 1B Instruct
$0.02
22
Pixtral 12B
$0.02
23
Phi 4
$0.02
24
Voxtral Small 24B 2507
$0.02
25
Hermes 2 Pro - Llama-3 8B
$0.03
26
Gemma 3 12B
$0.03
27
Qwen-Turbo
$0.03
28
Mistral 7B Instruct v0.1
$0.03
29
Devstral Small 1.1
$0.03
30
Nova Lite 1.0
$0.03
31
Ministral 3 3B 2512
$0.03
32
Mistral Small 3.2 24B
$0.03
33
Trinity Mini
$0.03
34
Rnj 1 Instruct
$0.04
35
Gemini 2.0 Flash Lite
$0.04
36
gpt-oss-120b (exacto)
$0.04
37
Gemma 3 27B
$0.04
38
ERNIE 4.5 21B A3B
$0.04
39
Mistral 7B Instruct v0.3
$0.04
40
Mistral 7B Instruct v0.2
$0.04
41
Mistral 7B Instruct
$0.04
42
Llama 3.2 11B Vision Instruct
$0.04
43
Ministral 3 8B 2512
$0.04
44
Qwen2.5-VL 7B Instruct
$0.04
45
Molmo2 8B
$0.04
46
Lumimaid v0.2 8B
$0.04
47
GPT-4.1 Nano
$0.04
48
Gemini 2.0 Flash
$0.05
49
Olmo 3 7B Instruct
$0.05
50
Hermes 4 70B
$0.05
51
Qwen3 Coder 30B A3B Instruct
$0.05
52
Nemotron Nano 9B V2
$0.05
53
gpt-oss-20b
$0.05
54
Mistral Tiny
$0.05
55
Ministral 3 14B 2512
$0.06
56
Llama 4 Scout
$0.06
57
Qwen2.5 72B Instruct
$0.06
58
Saba
$0.06
59
Command R (08-2024)
$0.06
60
Jamba Mini 1.7
$0.06
61
Qwen3 14B
$0.06
62
Qwen3 30B A3B Instruct 2507
$0.07
63
gpt-oss-safeguard-20b
$0.07
64
UnslopNemo 12B
$0.07
65
Mistral Small 3.1 24B
$0.07
66
MiMo-V2-Flash
$0.07
67
Qwen3 4B
$0.07
68
Rocinante 12B
$0.08
69
DeepSeek V3.2 Exp
$0.08
70
Qwen3 8B
$0.08
71
KAT-Coder-Pro V1
$0.08
72
Llama 3.1 70B Instruct
$0.08
73
Hunyuan A13B Instruct
$0.08
74
DeepSeek V3.2
$0.08
75
Qwen2.5 Coder 32B Instruct
$0.08
76
GPT-4o Search Preview
$0.08
77
Gemini 2.5 Flash Lite
$0.09
78
Cydonia 24B V4.1
$0.09
79
Seed 1.6 Flash
$0.09
80
Gemma 2 27B
$0.09
81
gpt-oss-120b
$0.09
82
Gemini 2.5 Flash Lite Preview 09-2025
$0.09
83
Llama 3.3 70B Instruct
$0.09
84
Mistral Small Creative
$0.09
85
Qwen3 235B A22B Instruct 2507
$0.10
86
Mercury Coder
$0.10
87
Mercury
$0.10
88
Llama 3 70B Instruct
$0.10
89
Gemini 3.1 Pro Preview
$0.11
90
Codestral 2508
$0.11
91
ReMM SLERP 13B
$0.11
92
Olmo 3.1 32B Instruct
$0.11
93
Mixtral 8x7B Instruct
$0.11
94
Llama 4 Maverick
$0.12
95
Qwen2.5 VL 72B Instruct
$0.12
96
Qwen3 32B
$0.12
97
DeepSeek V3 0324
$0.12
98
DeepSeek V3
$0.12
99
DeepSeek V3.1 Terminus (exacto)
$0.13
100
Qwen VL Plus
$0.13
101
Skyfall 36B V2
$0.13
102
Mercury 2
$0.13
103
Claude 3 Haiku
$0.13
104
GPT-4o-mini
$0.13
105
GPT-4o-mini (2024-07-18)
$0.13
106
ERNIE 4.5 300B A47B
$0.13
107
Grok 4 Fast
$0.13
108
Aion-1.0-Mini
$0.13
109
Llama 3.3 Nemotron Super 49B V1.5
$0.13
110
ERNIE 4.5 VL 28B A3B
$0.14
111
GPT-3.5 Turbo
$0.14
112
DeepSeek V3.1
$0.14
113
Grok 4.1 Fast
$0.14
114
Olmo 3 7B Think
$0.14
115
Qwen3 30B A3B Thinking 2507
$0.14
116
Qwen3 VL 30B A3B Instruct
$0.15
117
Tongyi DeepResearch 30B A3B
$0.15
118
DeepSeek V3.1 Terminus
$0.15
119
Nemotron 3 Nano 30B A3B
$0.16
120
Cogito V2 Preview Llama 70B
$0.16
121
Qwen2.5 VL 32B Instruct
$0.16
122
Hermes 3 405B Instruct
$0.16
123
ERNIE 4.5 21B A3B Thinking
$0.16
124
GPT-5 Nano
$0.17
125
Step 3.5 Flash
$0.17
126
Llama 3.3 Euryale 70B
$0.17
127
Qwen3 VL 235B A22B Instruct
$0.18
128
Llama 3.1 Euryale 70B v2.2
$0.18
129
Grok 3 Mini Beta
$0.18
130
Grok 3 Mini
$0.18
131
Seed-2.0-Mini
$0.18
132
QwQ 32B
$0.18
133
Qwen3 VL 8B Instruct
$0.19
134
GLM 4.5 Air
$0.19
135
Devstral Medium
$0.19
136
GPT-4.1 Mini
$0.19
137
Aion-RP 1.0 (8B)
$0.19
138
DeepSeek V3.1 Nex N1
$0.20
139
Qwen3 Next 80B A3B Instruct
$0.20
140
MiniMax M2-her
$0.20
141
GPT-5.1-Codex-Mini
$0.20
142
Weaver (alpha)
$0.21
143
R1 Distill Qwen 32B
$0.22
144
Qwen3 Coder 480B A35B
$0.22
145
Mistral Medium 3
$0.22
146
Cogito v2.1 671B
$0.22
147
Qwen-Plus
$0.23
148
Qwen Plus 0728
$0.23
149
ERNIE 4.5 VL 424B A47B
$0.23
150
Mistral Large 3 2512
$0.23
151
Qwen3 235B A22B
$0.23
152
Qwen3 Coder 480B A35B (exacto)
$0.24
153
Nemotron Nano 12B 2 VL
$0.25
154
Qwen3 Coder Flash
$0.25
155
Llama 3.1 Nemotron Ultra 253B v1
$0.25
156
Qwen3 Coder Next
$0.26
157
R1 Distill Llama 70B
$0.26
158
MiniMax M2.5
$0.27
159
MiniMax M2.1
$0.27
160
Llama 3 Euryale 70B v2.1
$0.28
161
Morph V3 Large
$0.28
162
Hermes 4 405B
$0.29
163
GPT-3.5 Turbo (older v0613)
$0.29
164
Llama 3.1 Nemotron 70B Instruct
$0.29
165
DeepSeek V3.2 Speciale
$0.29
166
Noromaid 20B
$0.30
167
Qwen3.5-Flash
$0.30
168
Kimi K2 0711
$0.30
169
GPT-3.5 Turbo Instruct
$0.30
170
Qwen3 VL 32B Instruct
$0.30
171
GLM 4.7 Flash
$0.30
172
MiniMax M2
$0.31
173
Mistral Medium 3.1
$0.31
174
Kimi K2 0905
$0.32
175
Nova Pro 1.0
$0.32
176
Kimi Dev 72B
$0.32
177
Aion-2.0
$0.33
178
Gemini 3 Flash Preview
$0.33
179
GLM 4.5V
$0.34
180
CodeLLaMa 7B Instruct Solidity
$0.35
181
GLM 4.6
$0.36
182
GLM 4.6V
$0.37
183
Olmo 3 32B Think
$0.38
184
Olmo 3.1 32B Think
$0.38
185
Qwen3 VL 30B A3B Thinking
$0.40
186
Claude 3.5 Haiku
$0.41
187
Grok Code Fast 1
$0.41
188
GPT-5 Mini
$0.41
189
Gemini 2.5 Flash
$0.48
190
MiniMax M1
$0.51
191
Relace Search
$0.51
192
Gemini 2.5 Flash Preview 09-2025
$0.52
193
Hermes 3 70B Instruct
$0.53
194
Nova 2 Lite
$0.55
195
Seed 1.6
$0.55
196
Qwen3 235B A22B Thinking 2507
$0.57
197
GLM 4.5
$0.58
198
Qwen VL Max
$0.58
199
Switchpoint Router
$0.59
200
GLM 4.6 (exacto)
$0.59
201
Nano Banana (Gemini 2.5 Flash Image)
$0.59
202
Cogito V2 Preview Llama 405B
$0.60
203
Qwen3.5 Plus 2026-02-15
$0.60
204
Step3
$0.60
205
GPT-5.1-Codex
$0.60
206
Mixtral 8x22B Instruct
$0.62
207
Llama 3.1 70B Hanami x1
$0.63
208
Llemma 7b
$0.65
209
GPT-5.1 Chat
$0.69
210
Qwen3 Next 80B A3B Thinking
$0.73
211
Qwen3 Coder Plus
$0.76
212
Kimi K2 0905 (exacto)
$0.77
213
Miri
$0.78
214
Palmyra X5
$0.79
215
Mistral Large 2411
$0.80
216
R1
$0.81
217
GPT-5 Image Mini
$0.82
218
Claude Haiku 4.5
$0.83
219
Command A
$0.87
220
GPT-4.1
$0.89
221
Mistral Large
$0.90
222
Qwen3.5-35B-A3B
$0.91
223
R1 0528
$0.91
224
Pixtral Large 2411
$0.91
225
Qwen3 Max
$0.92
226
Mistral Large 2407
$0.92
227
Qwen3 Max Thinking
$0.94
228
Qwen-Max
$0.95
229
Command R+ (08-2024)
$0.95
230
Kimi K2 Thinking
$0.96
231
GPT-5 Codex
$0.96
232
Inflection 3 Productivity
$1.00
233
Inflection 3 Pi
$1.01
234
GPT-4o
$1.01
235
Qwen3.5-27B
$1.03
236
GPT-4o (2024-08-06)
$1.05
237
GPT-5 Chat
$1.08
238
Qwen3.5 397B A17B
$1.11
239
GLM 4.7
$1.13
240
SorcererLM 8x22B
$1.13
241
Nova Premier 1.0
$1.18
242
Qwen3 VL 235B A22B Thinking
$1.19
243
Sonar
$1.27
244
o3 Mini High
$1.28
245
Goliath 120B
$1.28
246
o3 Mini
$1.29
247
o4 Mini
$1.30
248
Kimi K2.5
$1.31
249
Qwen3.5-122B-A10B
$1.35
250
Qwen3 VL 8B Thinking
$1.39
251
Morph V3 Fast
$1.42
252
GPT-4o (2024-11-20)
$1.46
253
Jamba Large 1.7
$1.62
254
GPT-5.2 Chat
$1.63
255
Qwen Plus 0728 (thinking)
$1.72
256
GPT-5.2-Codex
$1.81
257
GPT-4o (2024-05-13)
$1.90
258
GPT-5.1
$1.98
259
GLM 5
$2.03
260
Aion-1.0
$2.03
261
GPT-5.2
$2.03
262
o4 Mini High
$2.14
263
o3
$2.17
264
GPT-5
$2.19
265
ChatGPT-4o
$2.20
266
Claude Sonnet 4
$2.21
267
GPT-5.1-Codex-Max
$2.37
268
Claude 3.7 Sonnet
$2.47
269
Claude Sonnet 4.5
$2.54
270
Claude Sonnet 4.6
$2.57
271
Grok 3
$2.62
272
Grok 3 Beta
$2.65
273
Sonar Pro
$3.20
274
Claude 3.5 Sonnet
$3.37
275
Sonar Reasoning Pro
$3.45
276
GPT-5 Image
$3.74
277
Auto Router
$4.17
278
GPT-4 Turbo
$4.17
279
Grok 4
$4.31
280
GPT-4 Turbo Preview
$4.38
281
Claude Opus 4.5
$4.62
282
Claude Opus 4.6
$4.85
283
Sonar Pro Search
$5.43
284
Nano Banana Pro (Gemini 3 Pro Image Preview)
$5.51
285
Gemini 2.5 Pro
$5.74
286
Gemini 2.5 Pro Preview 06-05
$5.77
287
Gemini 3 Pro Preview
$5.78
288
Gemini 2.5 Pro Preview 05-06
$5.87
289
Claude 3.7 Sonnet (thinking)
$7.19
290
GPT-4 (older v0314)
$7.63
291
GPT-4
$8.36
292
ALMA
$9.99
293
Claude Opus 4
$10.46
294
Claude Opus 4.1
$11.12
295
o3 Pro
$20.97
296
o1
$22.95
297
GPT-5.2 Pro
$24.52
298
o4 Mini Deep Research
$35.85
299
o3 Deep Research
$158.95
300
Sonar Deep Research
$235.83
301
o1-pro
$236.61
Total:$990.18
Average:$3.28
(301 modelos)
Metrics menu
Reasoning Tokens
Tokens used in the reasoning process
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
GPT-5.3 Chat
23K
7
DeepSeek V3.1 Terminus
24K
8
GPT-5.2 Pro
39K
9
GPT-5.2
40K
10
GPT-5.3-Codex
41K
11
DeepSeek V3.2 Exp
45K
12
GPT-5.1-Codex-Mini
48K
13
GPT-5 Codex
53K
14
GLM 4.5
57K
15
Qwen3.5 Plus 2026-02-15
58K
16
GLM 4.5V
61K
17
GLM 4.6
66K
18
ALMA
71K
19
gpt-oss-120b
71K
20
Mercury 2
74K
21
GPT-5.1
75K
22
gpt-oss-120b (exacto)
76K
23
o3 Pro
78K
24
GPT-5.2-Codex
78K
25
o3
86K
26
o4 Mini
105K
27
o3 Mini High
107K
28
o3 Mini
109K
29
gpt-oss-20b
110K
30
Nemotron Nano 9B V2
111K
31
Grok 4 Fast
118K
32
gpt-oss-safeguard-20b
120K
33
GPT-5 Mini
120K
34
Trinity Mini
122K
35
MiniMax M2.5
123K
36
GPT-5 Image Mini
125K
37
Free Models Router
129K
38
GPT-5.4 Pro
129K
39
MiniMax M1
131K
40
MiniMax M2.1
141K
41
R1 Distill Llama 70B
143K
42
GPT-5 Image
146K
43
GPT-5
147K
44
GLM 4.6 (exacto)
149K
45
Grok Code Fast 1
149K
46
o1
152K
47
Grok 4.1 Fast
153K
48
o1-pro
157K
49
R1 Distill Qwen 32B
160K
50
Grok 4
161K
51
Seed 1.6
166K
52
Qwen3 4B
168K
53
Seed 1.6 Flash
171K
54
Aion-2.0
172K
55
Qwen3 32B
173K
56
Grok 3 Mini
173K
57
R1
174K
58
Grok 3 Mini Beta
175K
59
Qwen3 14B
178K
60
MiniMax M2
185K
61
Kimi Dev 72B
186K
62
GPT-5.1-Codex-Max
187K
63
Qwen3 VL 235B A22B Thinking
188K
64
o4 Mini High
199K
65
R1 0528
208K
66
Qwen3 8B
210K
67
Step3
222K
68
Qwen3 235B A22B
224K
69
Gemini 3.1 Pro Preview
238K
70
Kimi K2 Thinking
243K
71
Llama 3.3 Nemotron Super 49B V1.5
252K
72
Tongyi DeepResearch 30B A3B
256K
73
Gemini 3.1 Pro Preview Custom Tools
257K
74
GLM 4.6V
258K
75
Qwen3 VL 30B A3B Thinking
260K
76
Qwen3 30B A3B Thinking 2507
270K
77
Claude 3.7 Sonnet (thinking)
281K
78
Nano Banana Pro (Gemini 3 Pro Image Preview)
282K
79
Kimi K2.5
287K
80
Qwen3 235B A22B Thinking 2507
287K
81
QwQ 32B
291K
82
Qwen Plus 0728 (thinking)
296K
83
Solar Pro 3
307K
84
Nemotron Nano 12B 2 VL
313K
85
Gemini 3 Pro Preview
322K
86
GPT-5 Nano
336K
87
Seed-2.0-Mini
343K
88
DeepSeek V3.2 Speciale
363K
89
Qwen3.5 397B A17B
364K
90
Gemini 2.5 Pro Preview 06-05
386K
91
Gemini 2.5 Pro
386K
92
Step 3.5 Flash
393K
93
Gemini 2.5 Pro Preview 05-06
394K
94
Step 3.5 Flash
408K
95
GLM 4.7
410K
96
ERNIE 4.5 21B A3B Thinking
417K
97
Qwen3.5-122B-A10B
419K
98
Qwen3.5-35B-A3B
430K
99
Qwen3.5-27B
434K
100
GLM 5
467K
101
Qwen3 Next 80B A3B Thinking
476K
102
Qwen3 VL 8B Thinking
561K
103
Qwen3.5-Flash
579K
104
Olmo 3 7B Think
583K
105
Nemotron 3 Nano 30B A3B
620K
106
GLM 4.7 Flash
625K
107
Olmo 3.1 32B Think
661K
108
Olmo 3 32B Think
663K
109
o4 Mini Deep Research
1.5M
110
o3 Deep Research
1.6M
111
Sonar Deep Research
68.4M
Total:94.9M
Average:855K
(111 modelos)
Metrics menu
Output Tokens
Tokens generated in responses
1
Unknown
0
2
Solar Pro 3
0
3
Gemma 2 27B
45K
4
Aion-1.0-Mini
47K
5
GPT-5.1-Codex
48K
6
Voxtral Small 24B 2507
52K
7
Mistral Nemo
52K
8
Lumimaid v0.2 8B
56K
9
GPT-5.1 Chat
56K
10
Ministral 3B
57K
11
Gemma 2 9B
59K
12
GPT-3.5 Turbo
59K
13
GPT-3.5 Turbo 16k
60K
14
Devstral Small 1.1
61K
15
Hermes 4 405B
62K
16
Hermes 3 405B Instruct
64K
17
Mistral Small 3.1 24B
64K
18
Ministral 8B
64K
19
Command A
65K
20
Nova Premier 1.0
66K
21
Nova Pro 1.0
69K
22
MythoMax 13B
69K
23
Llama 3 8B Lunaris
69K
24
Mistral Small 3
70K
25
Mistral 7B Instruct v0.3
71K
26
GPT-4o-mini
71K
27
Skyfall 36B V2
71K
28
Llama 3 70B Instruct
72K
29
GPT-4o-mini (2024-07-18)
72K
30
Command R+ (08-2024)
72K
31
Mistral 7B Instruct v0.2
72K
32
Mistral 7B Instruct v0.1
72K
33
Mistral Small 3.2 24B
72K
34
Saba
73K
35
Cogito V2 Preview Llama 405B
73K
36
Aion-RP 1.0 (8B)
73K
37
Mixtral 8x22B Instruct
73K
38
ReMM SLERP 13B
74K
39
Mistral 7B Instruct
75K
40
GPT-4o
76K
41
UnslopNemo 12B
76K
42
Inflection 3 Productivity
77K
43
Claude 3.5 Haiku
77K
44
Inflection 3 Pi
77K
45
Devstral Medium
78K
46
GPT-3.5 Turbo Instruct
78K
47
Command R7B (12-2024)
78K
48
Cogito v2.1 671B
78K
49
Mercury Coder
79K
50
GPT-4 (older v0314)
79K
51
Claude 3 Haiku
79K
52
GPT-4o (2024-08-06)
79K
53
Mercury
80K
54
KAT-Coder-Pro V1
80K
55
Kimi K2 0905
81K
56
Gemini 2.0 Flash
81K
57
Command R (08-2024)
81K
58
Aurora Alpha
82K
59
GPT-4.1 Nano
83K
60
DeepSeek V3
83K
61
Cogito V2 Preview Llama 70B
83K
62
Nova Lite 1.0
83K
63
Hermes 4 70B
84K
64
DeepSeek V3 0324
84K
65
GPT-5 Codex
84K
66
Mixtral 8x7B Instruct
84K
67
Pixtral 12B
86K
68
Gemini 2.0 Flash Lite
86K
69
GPT-4.1
86K
70
Llama 3.1 70B Instruct
86K
71
Hermes 2 Pro - Llama-3 8B
86K
72
Codestral 2508
87K
73
Claude 3.5 Sonnet
87K
74
Llama 3 Euryale 70B v2.1
88K
75
Gemma 3 12B
89K
76
Mistral Medium 3
90K
77
GPT-5.1-Codex-Mini
90K
78
Devstral 2 2512
91K
79
GPT-4
91K
80
Sonar Pro Search
91K
81
Molmo2 8B
91K
82
Morph V3 Large
92K
83
Mistral Tiny
92K
84
Gemini 3 Flash Preview
92K
85
GPT-4o (2024-05-13)
92K
86
Noromaid 20B
92K
87
Gemma 3 4B
92K
88
Kimi K2 0905 (exacto)
93K
89
GPT-4o Search Preview
93K
90
Mistral Large 2411
93K
91
ERNIE 4.5 300B A47B
93K
92
GPT-4o-mini Search Preview
94K
93
Cydonia 24B V4.1
94K
94
Gemma 3 27B
95K
95
GPT-4.1 Mini
95K
96
GPT-5 Chat
96K
97
GLM 4 32B
96K
98
Gemini 3.1 Flash Lite Preview
98K
99
GPT-4 Turbo (older v1106)
98K
100
Pixtral Large 2411
100K
101
Trinity Large Preview
100K
102
GPT-3.5 Turbo (older v0613)
100K
103
Llama 3 8B Instruct
100K
104
Granite 4.0 Micro
100K
105
Llama 3.2 1B Instruct
101K
106
GPT-5.4
101K
107
GPT-4 Turbo
102K
108
GPT-5.3-Codex
102K
109
Goliath 120B
103K
110
Kimi K2 0711
103K
111
Llama 4 Scout
104K
112
LFM2-8B-A1B
104K
113
GPT-5.2 Chat
104K
114
Qwen2.5-VL 7B Instruct
104K
115
Jamba Mini 1.7
105K
116
Llama 3.3 70B Instruct
105K
117
ERNIE 4.5 21B A3B
106K
118
Llama 3.1 70B Hanami x1
107K
119
Sonar Pro
108K
120
Qwen2.5 VL 72B Instruct
108K
121
Llama 3.1 Nemotron Ultra 253B v1
108K
122
Llama 4 Maverick
110K
123
Sonar
110K
124
Qwen3 VL 235B A22B Instruct
111K
125
Qwen-Turbo
111K
126
GPT-5.3 Chat
111K
127
Weaver (alpha)
111K
128
ChatGPT-4o
112K
129
GPT-4 Turbo Preview
114K
130
Hunyuan A13B Instruct
114K
131
Claude Opus 4
115K
132
Nova Micro 1.0
115K
133
Qwen2.5 72B Instruct
115K
134
Llama 3.1 Euryale 70B v2.2
117K
135
Palmyra X5
117K
136
GPT-5.2-Codex
118K
137
Gemma 3n 4B
119K
138
Mistral Large
119K
139
Qwen2.5 Coder 32B Instruct
121K
140
GPT-4o (2024-11-20)
121K
141
Qwen2.5 7B Instruct
121K
142
Mistral Large 3 2512
121K
143
SorcererLM 8x22B
121K
144
Claude Sonnet 4
122K
145
DeepSeek V3.2
123K
146
Mistral Large 2407
123K
147
LFM2-24B-A2B
123K
148
Claude Opus 4.1
123K
149
Qwen3 Coder 480B A35B (exacto)
123K
150
Qwen-Max
124K
151
Rocinante 12B
125K
152
Qwen3 Coder 480B A35B
127K
153
Llama 3.3 Euryale 70B
128K
154
DeepSeek V3.1
128K
155
Phi 4
130K
156
Rnj 1 Instruct
131K
157
DeepSeek V3.1 Terminus (exacto)
132K
158
Qwen3 Coder Plus
133K
159
GPT-5.2
133K
160
Qwen3 Max
133K
161
GPT-5.2 Pro
134K
162
Mistral Medium 3.1
136K
163
Relace Search
137K
164
Qwen3 Max Thinking
137K
165
MiniMax M2-her
138K
166
Miri
139K
167
DeepSeek V3.1 Nex N1
139K
168
Claude 3.7 Sonnet
140K
169
DeepSeek V3.2 Exp
141K
170
Claude Haiku 4.5
141K
171
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
142K
172
ERNIE 4.5 VL 424B A47B
142K
173
Qwen3 Coder 30B A3B Instruct
144K
174
Llama 3.1 Nemotron 70B Instruct
144K
175
Claude Sonnet 4.5
144K
176
DeepSeek V3.1 Terminus
146K
177
Claude Sonnet 4.6
147K
178
Olmo 3.1 32B Instruct
147K
179
Qwen3 Coder Flash
148K
180
Qwen VL Max
149K
181
Qwen3 Next 80B A3B Instruct
150K
182
gpt-oss-120b
151K
183
Switchpoint Router
152K
184
GLM 4.6
152K
185
Ministral 3 14B 2512
153K
186
gpt-oss-120b (exacto)
153K
187
Nano Banana (Gemini 2.5 Flash Image)
153K
188
Qwen3 235B A22B Instruct 2507
154K
189
Mercury 2
155K
190
GLM 4.5V
155K
191
Qwen VL Plus
157K
192
Qwen-Plus
158K
193
o3 Pro
158K
194
Aion-2.0
160K
195
Claude Opus 4.5
160K
196
o3
161K
197
Qwen Plus 0728
161K
198
o3 Mini High
161K
199
o3 Mini
161K
200
Auto Router
164K
201
Qwen3 VL 32B Instruct
164K
202
Grok 3 Beta
164K
203
Grok 3
165K
204
o4 Mini
165K
205
Ministral 3 8B 2512
168K
206
R1 Distill Llama 70B
169K
207
Claude Opus 4.6
169K
208
Qwen3 30B A3B Instruct 2507
172K
209
Ministral 3 3B 2512
173K
210
Jamba Large 1.7
176K
211
Olmo 3 7B Instruct
177K
212
Trinity Mini
177K
213
Gemini 2.5 Flash
178K
214
Llama 3.2 3B Instruct
179K
215
Gemini 2.5 Flash Lite
181K
216
GPT-5.1
185K
217
MiniMax M2.5
187K
218
MiMo-V2-Flash
187K
219
gpt-oss-20b
189K
220
GPT-5 Mini
194K
221
Gemini 2.5 Flash Preview 09-2025
196K
222
Qwen3 VL 30B A3B Instruct
197K
223
R1 Distill Qwen 32B
198K
224
GPT-5 Image Mini
199K
225
Gemini 2.5 Flash Lite Preview 09-2025
201K
226
Free Models Router
201K
227
gpt-oss-safeguard-20b
202K
228
GPT-5 Image
202K
229
MiMo-V2-Flash
204K
230
Aion-1.0
206K
231
GPT-5
206K
232
Llama 3.2 11B Vision Instruct
207K
233
o1
208K
234
Nova 2 Lite
208K
235
CodeLLaMa 7B Instruct Solidity
209K
236
MiniMax M1
211K
237
MiniMax M2.1
212K
238
Qwen2.5 VL 32B Instruct
213K
239
ERNIE 4.5 VL 28B A3B
213K
240
o1-pro
215K
241
GLM 4.5 Air
216K
242
GPT-5.4 Pro
222K
243
GPT-5.1-Codex-Max
225K
244
Medgemma
225K
245
Grok 4 Fast
228K
246
Qwen3.5 Plus 2026-02-15
233K
247
Qwen3 4B
236K
248
Qwen3 14B
238K
249
Qwen3 Coder Next
240K
250
Nemotron Nano 9B V2
240K
251
Grok 4.1 Fast
242K
252
Sonar Reasoning Pro
247K
253
GLM 4.5
248K
254
Seed 1.6 Flash
255K
255
GLM 4.6 (exacto)
256K
256
MiniMax M2
256K
257
Kimi Dev 72B
256K
258
Qwen3 32B
258K
259
Llama 3.1 8B Instruct
258K
260
Seed 1.6
261K
261
o4 Mini High
262K
262
Grok Code Fast 1
264K
263
Grok 4
265K
264
Qwen3 VL 235B A22B Thinking
280K
265
Mistral Small Creative
282K
266
Qwen3 235B A22B
287K
267
Qwen3 8B
290K
268
R1
296K
269
Qwen3 VL 8B Instruct
296K
270
Llama 3.3 Nemotron Super 49B V1.5
311K
271
ALMA
317K
272
Grok 3 Mini
329K
273
Grok 3 Mini Beta
333K
274
Gemini 3.1 Pro Preview
336K
275
Tongyi DeepResearch 30B A3B
336K
276
R1 0528
338K
277
Qwen3 30B A3B Thinking 2507
343K
278
Gemini 3.1 Pro Preview Custom Tools
352K
279
Nemotron Nano 12B 2 VL
360K
280
Kimi K2 Thinking
366K
281
QwQ 32B
371K
282
Qwen3 VL 30B A3B Thinking
371K
283
GLM 4.6V
374K
284
Step3
379K
285
Qwen3 235B A22B Thinking 2507
400K
286
GPT-5 Nano
407K
287
Qwen Plus 0728 (thinking)
420K
288
Seed-2.0-Mini
424K
289
DeepSeek V3.2 Speciale
438K
290
Kimi K2.5
442K
291
Nano Banana Pro (Gemini 3 Pro Image Preview)
443K
292
Claude 3.7 Sonnet (thinking)
453K
293
Llemma 7b
455K
294
Gemini 3 Pro Preview
463K
295
Qwen3.5 397B A17B
482K
296
Solar Pro 3
485K
297
Step 3.5 Flash
515K
298
Step 3.5 Flash
529K
299
GLM 4.7
534K
300
Qwen3.5-122B-A10B
555K
301
Qwen3 Next 80B A3B Thinking
555K
302
Qwen3.5-27B
556K
303
ERNIE 4.5 21B A3B Thinking
559K
304
Gemini 2.5 Pro
562K
305
Gemini 2.5 Pro Preview 06-05
562K
306
Gemini 2.5 Pro Preview 05-06
572K
307
GLM 5
610K
308
Nemotron 3 Nano 30B A3B
634K
309
Olmo 3 7B Think
647K
310
Qwen3 VL 8B Thinking
653K
311
Qwen3.5-35B-A3B
672K
312
Qwen3.5-Flash
719K
313
Olmo 3 32B Think
728K
314
GLM 4.7 Flash
729K
315
Olmo 3.1 32B Think
729K
316
Morph V3 Fast
1.1M
317
o4 Mini Deep Research
1.6M
318
Hermes 3 70B Instruct
1.7M
319
o3 Deep Research
1.7M
320
Sonar Deep Research
68.8M
Total:132.6M
Average:414K
(320 modelos)