Ranking for MIR 2025
25 January 2025
210questions
6invalidated
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
Gemini 3 Flash Preview
194.66 pts
4
GPT-5.2-Codex
193.66 pts
5
GPT-5.2 Pro
193.33 pts
6
GPT-5.2 Chat
192.33 pts
7
GPT-5 Codex
192.00 pts
8
GPT-5.2
192.00 pts
9
GPT-5 Image
192.00 pts
10
o3 Pro
192.00 pts
11
GPT-5.3-Codex
191.33 pts
12
GPT-5.3 Chat
190.66 pts
13
GPT-5 Mini
190.66 pts
14
GPT-5.1 Chat
190.66 pts
15
GPT-5.1
190.66 pts
16
GPT-5.1-Codex-Max
190.66 pts
17
Gemini 3.1 Pro Preview
190.66 pts
18
Gemini 3 Pro Preview
190.66 pts
19
GPT-5.4
190.33 pts
20
Gemini 3.1 Pro Preview Custom Tools
189.33 pts
21
GPT-5.1-Codex
189.33 pts
22
GPT-5
189.33 pts
23
Nano Banana Pro (Gemini 3 Pro Image Preview)
189.33 pts
24
Gemini 2.5 Pro
189.33 pts
25
GPT-5.4 Pro
188.33 pts
26
o3
188.00 pts
27
GLM 5
188.00 pts
28
Claude Opus 4.6
188.00 pts
29
Gemini 2.5 Pro Preview 05-06
188.00 pts
30
GPT-5 Image Mini
187.00 pts
31
Qwen3.5-35B-A3B
187.00 pts
32
Qwen3.5 397B A17B
186.66 pts
33
o4 Mini Deep Research
186.66 pts
34
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
186.33 pts
35
o4 Mini High
185.33 pts
36
Gemini 2.5 Pro Preview 06-05
185.33 pts
37
o3 Deep Research
185.33 pts
38
Sonar Deep Research
185.33 pts
39
Grok 4.1 Fast
184.00 pts
40
GPT-5.1-Codex-Mini
184.00 pts
41
Qwen3.5 Plus 2026-02-15
184.00 pts
42
Qwen3 235B A22B Thinking 2507
184.00 pts
43
o4 Mini
184.00 pts
44
Claude Sonnet 4.6
184.00 pts
45
o1-pro
184.00 pts
46
Qwen3.5-Flash
183.33 pts
47
Gemini 2.5 Flash
183.33 pts
48
Kimi K2.5
183.00 pts
49
Grok 4
183.00 pts
50
Qwen3 235B A22B
182.66 pts
51
Qwen3.5-122B-A10B
182.66 pts
52
Qwen Plus 0728 (thinking)
182.66 pts
53
Auto Router
182.66 pts
54
Claude Opus 4.5
182.66 pts
55
DeepSeek V3.2 Speciale
181.66 pts
56
GLM 4.7
181.66 pts
57
gpt-oss-120b
181.33 pts
58
Grok 4 Fast
181.33 pts
59
Aion-1.0
181.33 pts
60
Claude Sonnet 4
181.33 pts
61
Claude 3.7 Sonnet
181.33 pts
62
Claude 3.7 Sonnet (thinking)
181.33 pts
63
o1
181.33 pts
64
Llama 4 Maverick
180.66 pts
65
Qwen3.5-27B
180.66 pts
66
Claude Sonnet 4.5
180.00 pts
67
GLM 4.5
179.33 pts
68
Aion-2.0
179.00 pts
69
Gemini 2.5 Flash Preview 09-2025
179.00 pts
70
GPT-5 Chat
179.00 pts
71
Step 3.5 Flash
178.33 pts
72
Gemini 3.1 Flash Lite Preview
178.00 pts
73
Grok 3 Beta
177.66 pts
74
Qwen3 Next 80B A3B Thinking
177.33 pts
75
R1 0528
177.33 pts
76
Claude Opus 4
177.33 pts
77
Nano Banana (Gemini 2.5 Flash Image)
176.33 pts
78
Claude 3.5 Sonnet
176.33 pts
79
Seed-2.0-Mini
176.00 pts
80
Qwen3 VL 235B A22B Thinking
176.00 pts
81
Step 3.5 Flash
175.66 pts
82
DeepSeek V3.2 Exp
175.66 pts
83
Switchpoint Router
175.33 pts
84
Seed 1.6
175.33 pts
85
Kimi K2 Thinking
175.33 pts
86
GLM 4.6
175.33 pts
87
Grok 3
175.33 pts
88
Llama 3.3 Nemotron Super 49B V1.5
175.00 pts
89
Claude Opus 4.1
175.00 pts
90
Qwen-Plus
174.66 pts
91
Qwen3 VL 30B A3B Thinking
174.66 pts
92
Qwen3 Max
174.66 pts
93
DeepSeek V3.1 Terminus (exacto)
174.33 pts
94
Mercury 2
174.33 pts
95
Qwen Plus 0728
173.66 pts
96
GPT-4.1
173.66 pts
97
MiniMax M2.5
173.33 pts
98
ChatGPT-4o
173.33 pts
99
Mistral Medium 3
173.00 pts
100
R1
173.00 pts
101
Aurora Alpha
172.66 pts
102
GLM 4.6 (exacto)
172.66 pts
103
Qwen3 Max Thinking
172.66 pts
104
Sonar Pro Search
172.66 pts
105
GPT-4.1 Mini
172.33 pts
106
Mistral Large
172.33 pts
107
Mistral Large 3 2512
172.00 pts
108
gpt-oss-120b (exacto)
171.33 pts
109
Qwen3 32B
171.00 pts
110
Grok 3 Mini
171.00 pts
111
Qwen3 Coder Plus
171.00 pts
112
Nova Premier 1.0
170.66 pts
113
o3 Mini High
170.66 pts
114
Qwen3 Coder Next
170.33 pts
115
GPT-4o (2024-11-20)
170.33 pts
116
GPT-5 Nano
169.66 pts
117
DeepSeek V3 0324
169.66 pts
118
Mistral Large 2407
169.66 pts
119
DeepSeek V3.1
169.33 pts
120
Grok Code Fast 1
169.33 pts
121
Qwen VL Max
169.33 pts
122
o3 Mini
169.33 pts
123
DeepSeek V3.1 Terminus
168.66 pts
124
Mistral Medium 3.1
168.33 pts
125
GPT-4o (2024-05-13)
168.33 pts
126
Qwen3 Next 80B A3B Instruct
168.00 pts
127
GPT-4
168.00 pts
128
Pixtral Large 2411
167.66 pts
129
Solar Pro 3
167.33 pts
130
MiniMax M2
167.33 pts
131
Qwen3 VL 235B A22B Instruct
167.00 pts
132
Qwen3 235B A22B Instruct 2507
167.00 pts
133
Grok 3 Mini Beta
167.00 pts
134
Kimi K2 0711
167.00 pts
135
Palmyra X5
167.00 pts
136
Gemini 2.0 Flash
166.33 pts
137
DeepSeek V3.2
166.33 pts
138
Jamba Large 1.7
166.33 pts
139
DeepSeek V3.1 Nex N1
166.00 pts
140
Tongyi DeepResearch 30B A3B
165.66 pts
Best human
165.66 pts
141
Gemini 2.5 Flash Lite Preview 09-2025
165.33 pts
142
GPT-3.5 Turbo (older v0613)
165.00 pts
143
Kimi K2 0905
165.00 pts
144
GPT-4o (2024-08-06)
165.00 pts
145
Devstral 2 2512
164.66 pts
146
Cogito v2.1 671B
164.66 pts
147
GPT-4 Turbo Preview
164.66 pts
148
Qwen3 Coder 480B A35B (exacto)
164.33 pts
149
Claude Haiku 4.5
164.33 pts
150
GPT-4o
164.00 pts
151
Qwen3 VL 32B Instruct
163.66 pts
152
gpt-oss-safeguard-20b
162.66 pts
153
KAT-Coder-Pro V1
162.66 pts
154
Qwen3 30B A3B Thinking 2507
162.66 pts
155
GPT-4 Turbo (older v1106)
162.00 pts
156
Mistral Small Creative
162.00 pts
157
DeepSeek V3
162.00 pts
158
gpt-oss-20b
161.66 pts
159
Gemini 2.5 Flash Lite
161.66 pts
160
Nemotron 3 Nano 30B A3B
161.66 pts
161
GLM 4.6V
161.66 pts
162
GPT-4o Search Preview
161.33 pts
163
Step3
160.33 pts
164
Aion-1.0-Mini
160.00 pts
165
GPT-4 Turbo
159.33 pts
166
Trinity Large Preview
159.00 pts
167
Qwen3 Coder 480B A35B
159.00 pts
168
Sonar
159.00 pts
169
QwQ 32B
158.66 pts
170
Nova Pro 1.0
158.33 pts
171
Kimi K2 0905 (exacto)
158.00 pts
172
Qwen3 30B A3B Instruct 2507
157.66 pts
173
Qwen3 VL 30B A3B Instruct
157.66 pts
174
Mistral Large 2411
157.66 pts
175
ERNIE 4.5 VL 424B A47B
157.33 pts
176
MiniMax M2.1
157.33 pts
177
Qwen3 VL 8B Thinking
157.33 pts
178
Qwen3 14B
157.00 pts
179
Cogito V2 Preview Llama 405B
156.33 pts
180
Qwen2.5 72B Instruct
156.00 pts
181
GLM 4.5V
156.00 pts
182
Llama 4 Scout
155.66 pts
183
Devstral Medium
155.66 pts
184
R1 Distill Llama 70B
155.66 pts
185
Sonar Pro
155.66 pts
186
Llama 3.1 Nemotron Ultra 253B v1
155.33 pts
187
Cogito V2 Preview Llama 70B
155.00 pts
188
Command A
155.00 pts
189
Sonar Reasoning Pro
154.00 pts
190
MiMo-V2-Flash
153.66 pts
191
Seed 1.6 Flash
153.66 pts
192
Mistral Small 3.2 24B
153.00 pts
193
Hermes 3 405B Instruct
152.66 pts
194
Hermes 4 405B
152.66 pts
195
Mistral Small 3.1 24B
152.33 pts
196
Qwen2.5 VL 72B Instruct
152.33 pts
197
Qwen-Max
151.33 pts
198
MiMo-V2-Flash
151.00 pts
199
Mercury Coder
151.00 pts
200
ERNIE 4.5 300B A47B
151.00 pts
201
GPT-4 (older v0314)
150.66 pts
202
Gemini 2.0 Flash Lite
150.33 pts
203
Llama 3.3 70B Instruct
150.33 pts
204
Llama 3.1 70B Instruct
150.00 pts
205
Mercury
149.66 pts
206
Llama 3.1 Nemotron 70B Instruct
149.00 pts
207
GLM 4 32B
148.66 pts
208
Voxtral Small 24B 2507
148.66 pts
209
Ministral 3 8B 2512
148.00 pts
210
Saba
146.33 pts
211
GLM 4.5 Air
146.00 pts
212
Mixtral 8x22B Instruct
145.66 pts
213
GPT-4o-mini (2024-07-18)
144.66 pts
214
MiniMax M1
144.66 pts
215
Nova 2 Lite
144.33 pts
216
GPT-4o-mini Search Preview
143.66 pts
217
Llama 3.3 Euryale 70B
143.00 pts
218
GPT-4o-mini
142.66 pts
219
Cydonia 24B V4.1
142.33 pts
220
Medgemma
142.00 pts
221
Ministral 3 14B 2512
142.00 pts
222
Inflection 3 Pi
141.66 pts
223
Mistral Small 3
139.66 pts
224
Devstral Small 1.1
139.66 pts
225
Qwen-Turbo
139.33 pts
226
Qwen VL Plus
139.00 pts
227
MiniMax M2-her
139.00 pts
228
Qwen3 Coder Flash
138.66 pts
229
Nemotron Nano 12B 2 VL
138.66 pts
230
Kimi Dev 72B
138.66 pts
231
Hermes 4 70B
137.66 pts
232
Nemotron Nano 9B V2
137.00 pts
233
Inflection 3 Productivity
136.66 pts
234
Relace Search
136.00 pts
235
Qwen3 8B
135.66 pts
236
Qwen2.5 VL 32B Instruct
134.66 pts
237
Free Models Router
134.00 pts
238
Qwen3 Coder 30B A3B Instruct
134.00 pts
239
Skyfall 36B V2
134.00 pts
240
Claude 3.5 Haiku
131.66 pts
241
Llama 3.1 70B Hanami x1
131.66 pts
242
GPT-4.1 Nano
131.00 pts
243
Llama 3 70B Instruct
130.00 pts
244
GLM 4.7 Flash
128.66 pts
245
Qwen3 VL 8B Instruct
128.33 pts
246
Olmo 3.1 32B Think
127.66 pts
247
Olmo 3 32B Think
126.00 pts
248
Gemma 3 27B
124.00 pts
249
R1 Distill Qwen 32B
123.33 pts
250
Gemma 3 12B
121.66 pts
251
Llama 3.1 Euryale 70B v2.2
120.66 pts
252
SorcererLM 8x22B
119.33 pts
253
Claude 3 Haiku
114.00 pts
254
Trinity Mini
113.33 pts
255
Nova Lite 1.0
112.66 pts
256
ERNIE 4.5 21B A3B Thinking
112.00 pts
257
Gemma 2 27B
110.66 pts
258
Nova Micro 1.0
109.00 pts
259
Solar Pro 3
108.33 pts
260
ERNIE 4.5 VL 28B A3B
108.33 pts
261
ERNIE 4.5 21B A3B
102.66 pts
262
Llama 3 Euryale 70B v2.1
102.66 pts
263
LFM2-24B-A2B
101.66 pts
264
Command R+ (08-2024)
100.66 pts
265
Phi 4
99.66 pts
266
Mixtral 8x7B Instruct
99.00 pts
267
GPT-3.5 Turbo 16k
96.00 pts
268
Command R (08-2024)
93.66 pts
269
Jamba Mini 1.7
92.00 pts
270
Qwen2.5 Coder 32B Instruct
90.66 pts
271
Ministral 3 3B 2512
87.66 pts
272
Gemma 2 9B
84.33 pts
273
Pixtral 12B
83.33 pts
274
GPT-3.5 Turbo
83.00 pts
275
Gemma 3n 4B
82.66 pts
276
Olmo 3.1 32B Instruct
79.33 pts
277
Mistral Nemo
77.33 pts
278
GPT-3.5 Turbo Instruct
76.66 pts
279
Molmo2 8B
76.00 pts
280
Hunyuan A13B Instruct
75.00 pts
281
Ministral 8B
74.66 pts
282
LFM2-8B-A1B
71.00 pts
283
Hermes 3 70B Instruct
71.00 pts
284
Goliath 120B
71.00 pts
285
Qwen2.5 7B Instruct
68.66 pts
286
Codestral 2508
68.33 pts
287
Olmo 3 7B Think
66.33 pts
288
Qwen2.5-VL 7B Instruct
58.66 pts
289
Llama 3 8B Lunaris
55.33 pts
290
Llama 3.1 8B Instruct
53.00 pts
291
Gemma 3 4B
52.33 pts
292
Mistral 7B Instruct v0.2
50.66 pts
293
Granite 4.0 Micro
50.33 pts
294
Mistral 7B Instruct
49.66 pts
295
Mistral 7B Instruct v0.3
49.33 pts
296
Mistral Tiny
49.00 pts
297
Rocinante 12B
45.66 pts
298
Hermes 2 Pro - Llama-3 8B
44.33 pts
299
Command R7B (12-2024)
40.00 pts
300
Llama 3 8B Instruct
38.33 pts
301
Ministral 3B
34.33 pts
302
Mistral 7B Instruct v0.1
34.33 pts
303
UnslopNemo 12B
33.00 pts
304
Llama 3.2 11B Vision Instruct
30.33 pts
305
Llama 3.2 3B Instruct
28.66 pts
306
Lumimaid v0.2 8B
27.33 pts
307
Aion-RP 1.0 (8B)
24.66 pts
308
Olmo 3 7B Instruct
23.66 pts
309
MythoMax 13B
23.33 pts
310
Rnj 1 Instruct
20.66 pts
311
ReMM SLERP 13B
19.00 pts
312
Noromaid 20B
19.00 pts
313
Weaver (alpha)
12.00 pts
314
Morph V3 Large
7.66 pts
315
Llama 3.2 1B Instruct
6.66 pts
316
Llemma 7b
3.33 pts
317
Morph V3 Fast
1.66 pts
318
Qwen3 4B
0.00 pts
319
CodeLLaMa 7B Instruct Solidity
0.00 pts
Average:143.96 pts
(319 modelos)
Metrics menu
Correct Answers
Total number of correct answers
1
ALMA
200
2
Miri
198
3
Gemini 3 Flash Preview
196
4
GPT-5.2-Codex
195
5
GPT-5.2 Pro
195
6
GPT-5.2 Chat
194
7
GPT-5 Codex
194
8
GPT-5.2
194
9
GPT-5 Image
194
10
o3 Pro
194
11
GPT-5.3-Codex
193
12
GPT-5.3 Chat
193
13
GPT-5 Mini
193
14
GPT-5.1 Chat
193
15
GPT-5.1
193
16
GPT-5.1-Codex-Max
193
17
Gemini 3.1 Pro Preview
193
18
Gemini 3 Pro Preview
193
19
GPT-5.4
192
20
GPT-5.1-Codex
192
21
GPT-5
192
22
Nano Banana Pro (Gemini 3 Pro Image Preview)
192
23
Gemini 2.5 Pro
192
24
Gemini 3.1 Pro Preview Custom Tools
191
25
o3
191
26
GLM 5
191
27
Claude Opus 4.6
191
28
Gemini 2.5 Pro Preview 05-06
191
29
GPT-5.4 Pro
190
30
GPT-5 Image Mini
190
31
Qwen3.5-35B-A3B
190
32
Qwen3.5 397B A17B
190
33
o4 Mini Deep Research
190
34
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
189
35
o4 Mini High
189
36
Gemini 2.5 Pro Preview 06-05
189
37
o3 Deep Research
189
38
Sonar Deep Research
189
39
Grok 4.1 Fast
188
40
GPT-5.1-Codex-Mini
188
41
Qwen3.5 Plus 2026-02-15
188
42
Qwen3 235B A22B Thinking 2507
188
43
o4 Mini
188
44
Claude Sonnet 4.6
188
45
o1-pro
188
46
Qwen3.5-Flash
187
47
Gemini 2.5 Flash
187
48
Kimi K2.5
187
49
Grok 4
187
50
Qwen3 235B A22B
187
51
Qwen Plus 0728 (thinking)
187
52
Auto Router
187
53
Claude Opus 4.5
187
54
Qwen3.5-122B-A10B
186
55
GLM 4.7
186
56
gpt-oss-120b
186
57
Grok 4 Fast
186
58
Aion-1.0
186
59
Claude Sonnet 4
186
60
Claude 3.7 Sonnet (thinking)
186
61
o1
186
62
DeepSeek V3.2 Speciale
185
63
Claude 3.7 Sonnet
185
64
Llama 4 Maverick
185
65
Qwen3.5-27B
185
66
Claude Sonnet 4.5
185
67
GLM 4.5
184
68
Gemini 2.5 Flash Preview 09-2025
184
69
GPT-5 Chat
184
70
Aion-2.0
183
71
Step 3.5 Flash
183
72
Gemini 3.1 Flash Lite Preview
183
73
Grok 3 Beta
183
74
Qwen3 Next 80B A3B Thinking
183
75
R1 0528
183
76
Claude Opus 4
183
77
Claude 3.5 Sonnet
182
78
Qwen3 VL 235B A22B Thinking
182
79
Nano Banana (Gemini 2.5 Flash Image)
181
80
Step 3.5 Flash
181
81
DeepSeek V3.2 Exp
181
82
Switchpoint Router
181
83
Seed 1.6
181
84
GLM 4.6
181
85
Grok 3
181
86
Llama 3.3 Nemotron Super 49B V1.5
181
87
Claude Opus 4.1
181
88
Qwen-Plus
181
89
Qwen3 VL 30B A3B Thinking
181
90
Seed-2.0-Mini
180
91
Kimi K2 Thinking
180
92
Qwen3 Max
180
93
DeepSeek V3.1 Terminus (exacto)
180
94
Mercury 2
180
95
Qwen Plus 0728
180
96
GPT-4.1
180
97
ChatGPT-4o
180
98
MiniMax M2.5
179
99
Mistral Medium 3
179
100
R1
179
101
Aurora Alpha
179
102
GLM 4.6 (exacto)
179
103
Qwen3 Max Thinking
179
104
GPT-4.1 Mini
179
105
Mistral Large
179
106
Mistral Large 3 2512
179
107
Sonar Pro Search
178
108
gpt-oss-120b (exacto)
178
109
Qwen3 32B
178
110
Nova Premier 1.0
178
111
o3 Mini High
178
112
Grok 3 Mini
177
113
Qwen3 Coder Plus
177
114
Qwen3 Coder Next
177
115
GPT-4o (2024-11-20)
177
116
GPT-5 Nano
177
117
DeepSeek V3 0324
177
118
Mistral Large 2407
177
119
o3 Mini
177
120
DeepSeek V3.1
176
121
Grok Code Fast 1
176
122
Qwen VL Max
176
123
DeepSeek V3.1 Terminus
176
124
Mistral Medium 3.1
176
125
GPT-4o (2024-05-13)
176
126
Qwen3 Next 80B A3B Instruct
176
127
GPT-4
175
128
Pixtral Large 2411
175
129
Solar Pro 3
175
130
MiniMax M2
175
131
Qwen3 VL 235B A22B Instruct
175
132
Qwen3 235B A22B Instruct 2507
175
133
Palmyra X5
175
134
Grok 3 Mini Beta
174
135
Kimi K2 0711
174
136
Gemini 2.0 Flash
174
137
DeepSeek V3.2
174
138
Jamba Large 1.7
174
139
Tongyi DeepResearch 30B A3B
174
140
Gemini 2.5 Flash Lite Preview 09-2025
174
Best human
174
141
DeepSeek V3.1 Nex N1
173
142
GPT-3.5 Turbo (older v0613)
173
143
Devstral 2 2512
173
144
GPT-4 Turbo Preview
173
145
Qwen3 Coder 480B A35B (exacto)
173
146
Claude Haiku 4.5
173
147
GPT-4o (2024-08-06)
172
148
Qwen3 VL 32B Instruct
172
149
gpt-oss-safeguard-20b
172
150
KAT-Coder-Pro V1
172
151
Cogito v2.1 671B
171
152
GPT-4o
171
153
Qwen3 30B A3B Thinking 2507
171
154
Mistral Small Creative
171
155
DeepSeek V3
171
156
gpt-oss-20b
171
157
Gemini 2.5 Flash Lite
171
158
Nemotron 3 Nano 30B A3B
171
159
GLM 4.6V
171
160
Kimi K2 0905
170
161
Step3
170
162
GPT-4 Turbo (older v1106)
169
163
GPT-4o Search Preview
169
164
Aion-1.0-Mini
169
165
GPT-4 Turbo
169
166
Qwen3 Coder 480B A35B
169
167
Sonar
169
168
QwQ 32B
169
169
Trinity Large Preview
168
170
Nova Pro 1.0
168
171
Qwen3 30B A3B Instruct 2507
168
172
Qwen3 VL 30B A3B Instruct
168
173
Mistral Large 2411
168
174
ERNIE 4.5 VL 424B A47B
168
175
Qwen3 VL 8B Thinking
168
176
Qwen3 14B
167
177
Qwen2.5 72B Instruct
167
178
GLM 4.5V
167
179
Llama 4 Scout
166
180
Devstral Medium
166
181
R1 Distill Llama 70B
166
182
Sonar Pro
166
183
Llama 3.1 Nemotron Ultra 253B v1
166
184
Command A
166
185
MiniMax M2.1
165
186
Cogito V2 Preview Llama 405B
165
187
Cogito V2 Preview Llama 70B
165
188
MiMo-V2-Flash
165
189
Seed 1.6 Flash
165
190
Kimi K2 0905 (exacto)
164
191
Mistral Small 3.2 24B
164
192
Mistral Small 3.1 24B
164
193
Qwen2.5 VL 72B Instruct
164
194
Sonar Reasoning Pro
163
195
Hermes 4 405B
163
196
Qwen-Max
163
197
Mercury Coder
163
198
ERNIE 4.5 300B A47B
163
199
Hermes 3 405B Instruct
162
200
MiMo-V2-Flash
162
201
GPT-4 (older v0314)
162
202
Gemini 2.0 Flash Lite
162
203
Llama 3.3 70B Instruct
161
204
Llama 3.1 70B Instruct
161
205
Mercury
161
206
GLM 4 32B
161
207
Voxtral Small 24B 2507
161
208
Ministral 3 8B 2512
161
209
Llama 3.1 Nemotron 70B Instruct
160
210
Saba
159
211
Mixtral 8x22B Instruct
158
212
GPT-4o-mini (2024-07-18)
158
213
MiniMax M1
157
214
Nova 2 Lite
157
215
GPT-4o-mini Search Preview
157
216
GPT-4o-mini
157
217
GLM 4.5 Air
156
218
Medgemma
156
219
Ministral 3 14B 2512
156
220
Cydonia 24B V4.1
155
221
Inflection 3 Pi
155
222
Llama 3.3 Euryale 70B
154
223
Qwen VL Plus
154
224
Qwen3 Coder Flash
154
225
Mistral Small 3
153
226
Devstral Small 1.1
153
227
Qwen-Turbo
153
228
Nemotron Nano 12B 2 VL
153
229
MiniMax M2-her
152
230
Nemotron Nano 9B V2
152
231
Relace Search
152
232
Inflection 3 Productivity
151
233
Qwen3 8B
151
234
Qwen2.5 VL 32B Instruct
151
235
Hermes 4 70B
150
236
Qwen3 Coder 30B A3B Instruct
150
237
Free Models Router
149
238
Skyfall 36B V2
148
239
Claude 3.5 Haiku
148
240
GPT-4.1 Nano
148
241
Kimi Dev 72B
147
242
Llama 3.1 70B Hanami x1
147
243
Llama 3 70B Instruct
147
244
GLM 4.7 Flash
146
245
Qwen3 VL 8B Instruct
144
246
Gemma 3 27B
143
247
R1 Distill Qwen 32B
142
248
Olmo 3.1 32B Think
141
249
Gemma 3 12B
141
250
Olmo 3 32B Think
140
251
Llama 3.1 Euryale 70B v2.2
137
252
SorcererLM 8x22B
136
253
Claude 3 Haiku
134
254
Nova Lite 1.0
134
255
ERNIE 4.5 21B A3B Thinking
134
256
Trinity Mini
133
257
Gemma 2 27B
130
258
Solar Pro 3
130
259
ERNIE 4.5 VL 28B A3B
130
260
Nova Micro 1.0
129
261
ERNIE 4.5 21B A3B
126
262
LFM2-24B-A2B
126
263
Llama 3 Euryale 70B v2.1
124
264
Phi 4
124
265
Mixtral 8x7B Instruct
122
266
Command R+ (08-2024)
121
267
GPT-3.5 Turbo 16k
121
268
Command R (08-2024)
120
269
Jamba Mini 1.7
117
270
Ministral 3 3B 2512
115
271
Qwen2.5 Coder 32B Instruct
114
272
GPT-3.5 Turbo
112
273
Pixtral 12B
110
274
Gemma 3n 4B
110
275
Gemma 2 9B
107
276
Olmo 3.1 32B Instruct
107
277
GPT-3.5 Turbo Instruct
106
278
Mistral Nemo
105
279
Ministral 8B
103
280
Molmo2 8B
102
281
LFM2-8B-A1B
102
282
Codestral 2508
100
283
Goliath 120B
99
284
Olmo 3 7B Think
99
285
Hunyuan A13B Instruct
97
286
Qwen2.5 7B Instruct
93
287
Gemma 3 4B
89
288
Hermes 3 70B Instruct
88
289
Llama 3 8B Lunaris
86
290
Granite 4.0 Micro
85
291
Mistral 7B Instruct v0.2
84
292
Qwen2.5-VL 7B Instruct
83
293
Mistral 7B Instruct
83
294
Mistral 7B Instruct v0.3
83
295
Mistral Tiny
82
296
Llama 3.1 8B Instruct
79
297
Hermes 2 Pro - Llama-3 8B
78
298
Command R7B (12-2024)
78
299
Llama 3 8B Instruct
72
300
Ministral 3B
71
301
Lumimaid v0.2 8B
69
302
Rocinante 12B
68
303
Mistral 7B Instruct v0.1
65
304
Olmo 3 7B Instruct
65
305
Llama 3.2 3B Instruct
64
306
Rnj 1 Instruct
60
307
UnslopNemo 12B
55
308
Noromaid 20B
54
309
MythoMax 13B
52
310
ReMM SLERP 13B
52
311
Weaver (alpha)
49
312
Llama 3.2 11B Vision Instruct
46
313
Aion-RP 1.0 (8B)
45
314
Llama 3.2 1B Instruct
29
315
Morph V3 Large
23
316
Morph V3 Fast
21
317
Llemma 7b
17
318
CodeLLaMa 7B Instruct Solidity
7
319
Qwen3 4B
0
Total:49670
Average:155.7
(319 modelos)
Metrics menu
Incorrect Answers
Total number of incorrect answers
1
ALMA
0
2
Qwen3 4B
0
3
Miri
2
4
Gemini 3 Flash Preview
4
5
GPT-5.2-Codex
4
6
GPT-5.2 Pro
5
7
GPT-5.2 Chat
5
8
GPT-5.3-Codex
5
9
GPT-5.4
5
10
Gemini 3.1 Pro Preview Custom Tools
5
11
GPT-5.4 Pro
5
12
GPT-5 Codex
6
13
GPT-5.2
6
14
GPT-5 Image
6
15
o3 Pro
6
16
GPT-5.3 Chat
7
17
GPT-5 Mini
7
18
GPT-5.1 Chat
7
19
GPT-5.1
7
20
GPT-5.1-Codex-Max
7
21
Gemini 3.1 Pro Preview
7
22
Gemini 3 Pro Preview
7
23
GPT-5.1-Codex
8
24
GPT-5
8
25
Nano Banana Pro (Gemini 3 Pro Image Preview)
8
26
Gemini 2.5 Pro
8
27
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
8
28
o3
9
29
GLM 5
9
30
Claude Opus 4.6
9
31
Gemini 2.5 Pro Preview 05-06
9
32
GPT-5 Image Mini
9
33
Qwen3.5-35B-A3B
9
34
Qwen3.5 397B A17B
10
35
o4 Mini Deep Research
10
36
Qwen3.5-122B-A10B
10
37
DeepSeek V3.2 Speciale
10
38
o4 Mini High
11
39
Gemini 2.5 Pro Preview 06-05
11
40
o3 Deep Research
11
41
Sonar Deep Research
11
42
Qwen3.5-Flash
11
43
Gemini 2.5 Flash
11
44
Claude 3.7 Sonnet
11
45
Grok 4.1 Fast
12
46
GPT-5.1-Codex-Mini
12
47
Qwen3.5 Plus 2026-02-15
12
48
Qwen3 235B A22B Thinking 2507
12
49
o4 Mini
12
50
Claude Sonnet 4.6
12
51
o1-pro
12
52
Kimi K2.5
12
53
Grok 4
12
54
Aion-2.0
12
55
Seed-2.0-Mini
12
56
Qwen3 235B A22B
13
57
Qwen Plus 0728 (thinking)
13
58
Auto Router
13
59
Claude Opus 4.5
13
60
GLM 4.7
13
61
Llama 4 Maverick
13
62
Qwen3.5-27B
13
63
gpt-oss-120b
14
64
Grok 4 Fast
14
65
Aion-1.0
14
66
Claude Sonnet 4
14
67
Claude 3.7 Sonnet (thinking)
14
68
o1
14
69
GLM 4.5
14
70
Step 3.5 Flash
14
71
Nano Banana (Gemini 2.5 Flash Image)
14
72
Kimi K2 Thinking
14
73
Claude Sonnet 4.5
15
74
Gemini 2.5 Flash Preview 09-2025
15
75
GPT-5 Chat
15
76
Gemini 3.1 Flash Lite Preview
15
77
Kimi K2 0905
15
78
Grok 3 Beta
16
79
Step 3.5 Flash
16
80
DeepSeek V3.2 Exp
16
81
Qwen3 Max
16
82
Sonar Pro Search
16
83
Qwen3 Next 80B A3B Thinking
17
84
R1 0528
17
85
Claude Opus 4
17
86
Claude 3.5 Sonnet
17
87
Switchpoint Router
17
88
Seed 1.6
17
89
GLM 4.6
17
90
Grok 3
17
91
DeepSeek V3.1 Terminus (exacto)
17
92
Mercury 2
17
93
MiniMax M2.5
17
94
Qwen3 VL 235B A22B Thinking
18
95
Llama 3.3 Nemotron Super 49B V1.5
18
96
Claude Opus 4.1
18
97
Mistral Medium 3
18
98
R1
18
99
Grok 3 Mini
18
100
Qwen3 Coder Plus
18
101
Kimi K2 0905 (exacto)
18
102
Qwen-Plus
19
103
Qwen3 VL 30B A3B Thinking
19
104
Qwen Plus 0728
19
105
GPT-4.1
19
106
Aurora Alpha
19
107
GLM 4.6 (exacto)
19
108
Qwen3 Max Thinking
19
109
Cogito v2.1 671B
19
110
ChatGPT-4o
20
111
GPT-4.1 Mini
20
112
Mistral Large
20
113
gpt-oss-120b (exacto)
20
114
Qwen3 Coder Next
20
115
GPT-4o (2024-11-20)
20
116
DeepSeek V3.1
20
117
Grok Code Fast 1
20
118
Qwen VL Max
20
119
Mistral Large 3 2512
21
120
Qwen3 32B
21
121
GPT-4
21
122
Grok 3 Mini Beta
21
123
Kimi K2 0711
21
124
DeepSeek V3.1 Nex N1
21
125
GPT-4o (2024-08-06)
21
126
GPT-4o
21
127
GPT-4 Turbo (older v1106)
21
128
Nova Premier 1.0
22
129
o3 Mini High
22
130
GPT-5 Nano
22
131
DeepSeek V3 0324
22
132
Mistral Large 2407
22
133
DeepSeek V3.1 Terminus
22
134
Pixtral Large 2411
22
135
CodeLLaMa 7B Instruct Solidity
22
136
o3 Mini
23
137
Mistral Medium 3.1
23
138
GPT-4o (2024-05-13)
23
139
Solar Pro 3
23
140
MiniMax M2
23
141
Gemini 2.0 Flash
23
142
DeepSeek V3.2
23
143
Jamba Large 1.7
23
144
GPT-4o Search Preview
23
145
MiniMax M2.1
23
146
Qwen3 Next 80B A3B Instruct
24
147
Qwen3 VL 235B A22B Instruct
24
148
Qwen3 235B A22B Instruct 2507
24
149
Palmyra X5
24
150
GPT-3.5 Turbo (older v0613)
24
151
Tongyi DeepResearch 30B A3B
25
152
Devstral 2 2512
25
153
GPT-4 Turbo Preview
25
154
Qwen3 VL 32B Instruct
25
155
Qwen3 30B A3B Thinking 2507
25
156
Kimi Dev 72B
25
Best human
25
157
Gemini 2.5 Flash Lite Preview 09-2025
26
158
Qwen3 Coder 480B A35B (exacto)
26
159
Claude Haiku 4.5
26
160
Cogito V2 Preview Llama 405B
26
161
Mistral Small Creative
27
162
DeepSeek V3
27
163
Aion-1.0-Mini
27
164
Trinity Large Preview
27
165
Sonar Reasoning Pro
27
166
gpt-oss-safeguard-20b
28
167
KAT-Coder-Pro V1
28
168
gpt-oss-20b
28
169
Gemini 2.5 Flash Lite
28
170
Nemotron 3 Nano 30B A3B
28
171
GLM 4.6V
28
172
Hermes 3 405B Instruct
28
173
Step3
29
174
GPT-4 Turbo
29
175
Nova Pro 1.0
29
176
Qwen3 Coder 480B A35B
30
177
Sonar
30
178
Qwen3 14B
30
179
Cogito V2 Preview Llama 70B
30
180
GLM 4.5 Air
30
181
QwQ 32B
31
182
Qwen3 30B A3B Instruct 2507
31
183
Qwen3 VL 30B A3B Instruct
31
184
Mistral Large 2411
31
185
Llama 4 Scout
31
186
Devstral Medium
31
187
R1 Distill Llama 70B
31
188
Sonar Pro
31
189
Hermes 4 405B
31
190
ERNIE 4.5 VL 424B A47B
32
191
Qwen3 VL 8B Thinking
32
192
Llama 3.1 Nemotron Ultra 253B v1
32
193
Llama 3.3 70B Instruct
32
194
Qwen2.5 72B Instruct
33
195
GLM 4.5V
33
196
Command A
33
197
Mistral Small 3.2 24B
33
198
MiMo-V2-Flash
33
199
Llama 3.1 70B Instruct
33
200
Llama 3.1 Nemotron 70B Instruct
33
201
Llama 3.3 Euryale 70B
33
202
MiMo-V2-Flash
34
203
Seed 1.6 Flash
34
204
GPT-4 (older v0314)
34
205
Mercury
34
206
Mistral Small 3.1 24B
35
207
Qwen2.5 VL 72B Instruct
35
208
Qwen-Max
35
209
Gemini 2.0 Flash Lite
35
210
Mercury Coder
36
211
ERNIE 4.5 300B A47B
36
212
GLM 4 32B
37
213
Voxtral Small 24B 2507
37
214
Mixtral 8x22B Instruct
37
215
MiniMax M1
37
216
Hermes 4 70B
37
217
Saba
38
218
Nova 2 Lite
38
219
Cydonia 24B V4.1
38
220
Ministral 3 8B 2512
39
221
MiniMax M2-her
39
222
GPT-4o-mini (2024-07-18)
40
223
GPT-4o-mini Search Preview
40
224
Inflection 3 Pi
40
225
Mistral Small 3
40
226
Devstral Small 1.1
40
227
Olmo 3.1 32B Think
40
228
Qwen-Turbo
41
229
Llemma 7b
41
230
Medgemma
42
231
Ministral 3 14B 2512
42
232
Skyfall 36B V2
42
233
Olmo 3 32B Think
42
234
GPT-4o-mini
43
235
Nemotron Nano 12B 2 VL
43
236
Inflection 3 Productivity
43
237
Qwen VL Plus
45
238
Nemotron Nano 9B V2
45
239
Free Models Router
45
240
Qwen3 Coder Flash
46
241
Qwen3 8B
46
242
Llama 3.1 70B Hanami x1
46
243
Morph V3 Large
46
244
Qwen3 VL 8B Instruct
47
245
Llama 3.2 11B Vision Instruct
47
246
Relace Search
48
247
Qwen3 Coder 30B A3B Instruct
48
248
Qwen2.5 VL 32B Instruct
49
249
Claude 3.5 Haiku
49
250
Llama 3.1 Euryale 70B v2.2
49
251
SorcererLM 8x22B
50
252
GPT-4.1 Nano
51
253
Llama 3 70B Instruct
51
254
Hermes 3 70B Instruct
51
255
GLM 4.7 Flash
52
256
R1 Distill Qwen 32B
56
257
Gemma 3 27B
57
258
Gemma 3 12B
58
259
Gemma 2 27B
58
260
Morph V3 Fast
58
261
Trinity Mini
59
262
Claude 3 Haiku
60
263
Nova Micro 1.0
60
264
Command R+ (08-2024)
61
265
Aion-RP 1.0 (8B)
61
266
Nova Lite 1.0
64
267
Llama 3 Euryale 70B v2.1
64
268
Solar Pro 3
65
269
ERNIE 4.5 VL 28B A3B
65
270
ERNIE 4.5 21B A3B Thinking
66
271
Hunyuan A13B Instruct
66
272
UnslopNemo 12B
66
273
Rocinante 12B
67
274
Llama 3.2 1B Instruct
67
275
Gemma 2 9B
68
276
Mixtral 8x7B Instruct
69
277
ERNIE 4.5 21B A3B
70
278
Qwen2.5 Coder 32B Instruct
70
279
LFM2-24B-A2B
73
280
Phi 4
73
281
Qwen2.5 7B Instruct
73
282
Qwen2.5-VL 7B Instruct
73
283
GPT-3.5 Turbo 16k
75
284
Jamba Mini 1.7
75
285
Molmo2 8B
78
286
Llama 3.1 8B Instruct
78
287
Command R (08-2024)
79
288
Pixtral 12B
80
289
Ministral 3 3B 2512
82
290
Gemma 3n 4B
82
291
Olmo 3.1 32B Instruct
83
292
Mistral Nemo
83
293
Goliath 120B
84
294
Ministral 8B
85
295
MythoMax 13B
86
296
GPT-3.5 Turbo
87
297
GPT-3.5 Turbo Instruct
88
298
Llama 3 8B Lunaris
92
299
Mistral 7B Instruct v0.1
92
300
LFM2-8B-A1B
93
301
Codestral 2508
95
302
Olmo 3 7B Think
98
303
Mistral Tiny
99
304
ReMM SLERP 13B
99
305
Mistral 7B Instruct v0.2
100
306
Mistral 7B Instruct
100
307
Mistral 7B Instruct v0.3
101
308
Hermes 2 Pro - Llama-3 8B
101
309
Llama 3 8B Instruct
101
310
Granite 4.0 Micro
104
311
Noromaid 20B
105
312
Llama 3.2 3B Instruct
106
313
Gemma 3 4B
110
314
Ministral 3B
110
315
Weaver (alpha)
111
316
Command R7B (12-2024)
114
317
Rnj 1 Instruct
118
318
Olmo 3 7B Instruct
124
319
Lumimaid v0.2 8B
125
Total:11238
Average:35.22
(319 modelos)
Metrics menu
Accuracy Percentage
Proportion of correct answers over total
1
ALMA
100.0%
2
Miri
99.0%
3
Gemini 3 Flash Preview
98.0%
4
GPT-5.2-Codex
97.5%
5
GPT-5.2 Pro
97.5%
6
GPT-5.2 Chat
97.0%
7
GPT-5 Codex
97.0%
8
GPT-5.2
97.0%
9
GPT-5 Image
97.0%
10
o3 Pro
97.0%
11
GPT-5.3-Codex
96.5%
12
GPT-5.3 Chat
96.5%
13
GPT-5 Mini
96.5%
14
GPT-5.1 Chat
96.5%
15
GPT-5.1
96.5%
16
GPT-5.1-Codex-Max
96.5%
17
Gemini 3.1 Pro Preview
96.5%
18
Gemini 3 Pro Preview
96.5%
19
GPT-5.4
96.0%
20
GPT-5.1-Codex
96.0%
21
GPT-5
96.0%
22
Nano Banana Pro (Gemini 3 Pro Image Preview)
96.0%
23
Gemini 2.5 Pro
96.0%
24
Gemini 3.1 Pro Preview Custom Tools
95.5%
25
o3
95.5%
26
GLM 5
95.5%
27
Claude Opus 4.6
95.5%
28
Gemini 2.5 Pro Preview 05-06
95.5%
29
GPT-5.4 Pro
95.0%
30
GPT-5 Image Mini
95.0%
31
Qwen3.5-35B-A3B
95.0%
32
Qwen3.5 397B A17B
95.0%
33
o4 Mini Deep Research
95.0%
34
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
94.5%
35
o4 Mini High
94.5%
36
Gemini 2.5 Pro Preview 06-05
94.5%
37
o3 Deep Research
94.5%
38
Sonar Deep Research
94.5%
39
Grok 4.1 Fast
94.0%
40
GPT-5.1-Codex-Mini
94.0%
41
Qwen3.5 Plus 2026-02-15
94.0%
42
Qwen3 235B A22B Thinking 2507
94.0%
43
o4 Mini
94.0%
44
Claude Sonnet 4.6
94.0%
45
o1-pro
94.0%
46
Qwen3.5-Flash
93.5%
47
Gemini 2.5 Flash
93.5%
48
Kimi K2.5
93.5%
49
Grok 4
93.5%
50
Qwen3 235B A22B
93.5%
51
Qwen Plus 0728 (thinking)
93.5%
52
Auto Router
93.5%
53
Claude Opus 4.5
93.5%
54
Qwen3.5-122B-A10B
93.0%
55
GLM 4.7
93.0%
56
gpt-oss-120b
93.0%
57
Grok 4 Fast
93.0%
58
Aion-1.0
93.0%
59
Claude Sonnet 4
93.0%
60
Claude 3.7 Sonnet (thinking)
93.0%
61
o1
93.0%
62
DeepSeek V3.2 Speciale
92.5%
63
Claude 3.7 Sonnet
92.5%
64
Llama 4 Maverick
92.5%
65
Qwen3.5-27B
92.5%
66
Claude Sonnet 4.5
92.5%
67
GLM 4.5
92.0%
68
Gemini 2.5 Flash Preview 09-2025
92.0%
69
GPT-5 Chat
92.0%
70
Aion-2.0
91.5%
71
Step 3.5 Flash
91.5%
72
Gemini 3.1 Flash Lite Preview
91.5%
73
Grok 3 Beta
91.5%
74
Qwen3 Next 80B A3B Thinking
91.5%
75
R1 0528
91.5%
76
Claude Opus 4
91.5%
77
Claude 3.5 Sonnet
91.0%
78
Qwen3 VL 235B A22B Thinking
91.0%
79
Nano Banana (Gemini 2.5 Flash Image)
90.5%
80
Step 3.5 Flash
90.5%
81
DeepSeek V3.2 Exp
90.5%
82
Switchpoint Router
90.5%
83
Seed 1.6
90.5%
84
GLM 4.6
90.5%
85
Grok 3
90.5%
86
Llama 3.3 Nemotron Super 49B V1.5
90.5%
87
Claude Opus 4.1
90.5%
88
Qwen-Plus
90.5%
89
Qwen3 VL 30B A3B Thinking
90.5%
90
Seed-2.0-Mini
90.0%
91
Kimi K2 Thinking
90.0%
92
Qwen3 Max
90.0%
93
DeepSeek V3.1 Terminus (exacto)
90.0%
94
Mercury 2
90.0%
95
Qwen Plus 0728
90.0%
96
GPT-4.1
90.0%
97
ChatGPT-4o
90.0%
98
MiniMax M2.5
89.5%
99
Mistral Medium 3
89.5%
100
R1
89.5%
101
Aurora Alpha
89.5%
102
GLM 4.6 (exacto)
89.5%
103
Qwen3 Max Thinking
89.5%
104
GPT-4.1 Mini
89.5%
105
Mistral Large
89.5%
106
Mistral Large 3 2512
89.5%
107
Sonar Pro Search
89.0%
108
gpt-oss-120b (exacto)
89.0%
109
Qwen3 32B
89.0%
110
Nova Premier 1.0
89.0%
111
o3 Mini High
89.0%
112
Grok 3 Mini
88.5%
113
Qwen3 Coder Plus
88.5%
114
Qwen3 Coder Next
88.5%
115
GPT-4o (2024-11-20)
88.5%
116
GPT-5 Nano
88.5%
117
DeepSeek V3 0324
88.5%
118
Mistral Large 2407
88.5%
119
o3 Mini
88.5%
120
DeepSeek V3.1
88.0%
121
Grok Code Fast 1
88.0%
122
Qwen VL Max
88.0%
123
DeepSeek V3.1 Terminus
88.0%
124
Mistral Medium 3.1
88.0%
125
GPT-4o (2024-05-13)
88.0%
126
Qwen3 Next 80B A3B Instruct
88.0%
127
GPT-4
87.5%
128
Pixtral Large 2411
87.5%
129
Solar Pro 3
87.5%
130
MiniMax M2
87.5%
131
Qwen3 VL 235B A22B Instruct
87.5%
132
Qwen3 235B A22B Instruct 2507
87.5%
133
Palmyra X5
87.5%
134
Grok 3 Mini Beta
87.0%
135
Kimi K2 0711
87.0%
136
Gemini 2.0 Flash
87.0%
137
DeepSeek V3.2
87.0%
138
Jamba Large 1.7
87.0%
139
Tongyi DeepResearch 30B A3B
87.0%
140
Gemini 2.5 Flash Lite Preview 09-2025
87.0%
Best human
87.0%
141
DeepSeek V3.1 Nex N1
86.5%
142
GPT-3.5 Turbo (older v0613)
86.5%
143
Devstral 2 2512
86.5%
144
GPT-4 Turbo Preview
86.5%
145
Qwen3 Coder 480B A35B (exacto)
86.5%
146
Claude Haiku 4.5
86.5%
147
GPT-4o (2024-08-06)
86.0%
148
Qwen3 VL 32B Instruct
86.0%
149
gpt-oss-safeguard-20b
86.0%
150
KAT-Coder-Pro V1
86.0%
151
Cogito v2.1 671B
85.5%
152
GPT-4o
85.5%
153
Qwen3 30B A3B Thinking 2507
85.5%
154
Mistral Small Creative
85.5%
155
DeepSeek V3
85.5%
156
gpt-oss-20b
85.5%
157
Gemini 2.5 Flash Lite
85.5%
158
Nemotron 3 Nano 30B A3B
85.5%
159
GLM 4.6V
85.5%
160
Kimi K2 0905
85.0%
161
Step3
85.0%
162
GPT-4 Turbo (older v1106)
84.5%
163
GPT-4o Search Preview
84.5%
164
Aion-1.0-Mini
84.5%
165
GPT-4 Turbo
84.5%
166
Qwen3 Coder 480B A35B
84.5%
167
Sonar
84.5%
168
QwQ 32B
84.5%
169
Trinity Large Preview
84.0%
170
Nova Pro 1.0
84.0%
171
Qwen3 30B A3B Instruct 2507
84.0%
172
Qwen3 VL 30B A3B Instruct
84.0%
173
Mistral Large 2411
84.0%
174
ERNIE 4.5 VL 424B A47B
84.0%
175
Qwen3 VL 8B Thinking
84.0%
176
Qwen3 14B
83.5%
177
Qwen2.5 72B Instruct
83.5%
178
GLM 4.5V
83.5%
179
Llama 4 Scout
83.0%
180
Devstral Medium
83.0%
181
R1 Distill Llama 70B
83.0%
182
Sonar Pro
83.0%
183
Llama 3.1 Nemotron Ultra 253B v1
83.0%
184
Command A
83.0%
185
MiniMax M2.1
82.5%
186
Cogito V2 Preview Llama 405B
82.5%
187
Cogito V2 Preview Llama 70B
82.5%
188
MiMo-V2-Flash
82.5%
189
Seed 1.6 Flash
82.5%
190
Kimi K2 0905 (exacto)
82.0%
191
Mistral Small 3.2 24B
82.0%
192
Mistral Small 3.1 24B
82.0%
193
Qwen2.5 VL 72B Instruct
82.0%
194
Sonar Reasoning Pro
81.5%
195
Hermes 4 405B
81.5%
196
Qwen-Max
81.5%
197
Mercury Coder
81.5%
198
ERNIE 4.5 300B A47B
81.5%
199
Hermes 3 405B Instruct
81.0%
200
MiMo-V2-Flash
81.0%
201
GPT-4 (older v0314)
81.0%
202
Gemini 2.0 Flash Lite
81.0%
203
Llama 3.3 70B Instruct
80.5%
204
Llama 3.1 70B Instruct
80.5%
205
Mercury
80.5%
206
GLM 4 32B
80.5%
207
Voxtral Small 24B 2507
80.5%
208
Ministral 3 8B 2512
80.5%
209
Llama 3.1 Nemotron 70B Instruct
80.0%
210
Saba
79.5%
211
Mixtral 8x22B Instruct
79.0%
212
GPT-4o-mini (2024-07-18)
79.0%
213
MiniMax M1
78.5%
214
Nova 2 Lite
78.5%
215
GPT-4o-mini Search Preview
78.5%
216
GPT-4o-mini
78.5%
217
GLM 4.5 Air
78.0%
218
Medgemma
78.0%
219
Ministral 3 14B 2512
78.0%
220
Cydonia 24B V4.1
77.5%
221
Inflection 3 Pi
77.5%
222
Llama 3.3 Euryale 70B
77.0%
223
Qwen VL Plus
77.0%
224
Qwen3 Coder Flash
77.0%
225
Mistral Small 3
76.5%
226
Devstral Small 1.1
76.5%
227
Qwen-Turbo
76.5%
228
Nemotron Nano 12B 2 VL
76.5%
229
MiniMax M2-her
76.0%
230
Nemotron Nano 9B V2
76.0%
231
Relace Search
76.0%
232
Inflection 3 Productivity
75.5%
233
Qwen3 8B
75.5%
234
Qwen2.5 VL 32B Instruct
75.5%
235
Hermes 4 70B
75.0%
236
Qwen3 Coder 30B A3B Instruct
75.0%
237
Free Models Router
74.5%
238
Skyfall 36B V2
74.0%
239
Claude 3.5 Haiku
74.0%
240
GPT-4.1 Nano
74.0%
241
Kimi Dev 72B
73.5%
242
Llama 3.1 70B Hanami x1
73.5%
243
Llama 3 70B Instruct
73.5%
244
GLM 4.7 Flash
73.0%
245
Qwen3 VL 8B Instruct
72.0%
246
Gemma 3 27B
71.5%
247
R1 Distill Qwen 32B
71.0%
248
Olmo 3.1 32B Think
70.5%
249
Gemma 3 12B
70.5%
250
Olmo 3 32B Think
70.0%
251
Llama 3.1 Euryale 70B v2.2
68.5%
252
SorcererLM 8x22B
68.0%
253
Claude 3 Haiku
67.0%
254
Nova Lite 1.0
67.0%
255
ERNIE 4.5 21B A3B Thinking
67.0%
256
Trinity Mini
66.5%
257
Gemma 2 27B
65.0%
258
Solar Pro 3
65.0%
259
ERNIE 4.5 VL 28B A3B
65.0%
260
Nova Micro 1.0
64.5%
261
ERNIE 4.5 21B A3B
63.0%
262
LFM2-24B-A2B
63.0%
263
Llama 3 Euryale 70B v2.1
62.0%
264
Phi 4
62.0%
265
Mixtral 8x7B Instruct
61.0%
266
Command R+ (08-2024)
60.5%
267
GPT-3.5 Turbo 16k
60.5%
268
Command R (08-2024)
60.0%
269
Jamba Mini 1.7
58.5%
270
Ministral 3 3B 2512
57.5%
271
Qwen2.5 Coder 32B Instruct
57.0%
272
GPT-3.5 Turbo
56.0%
273
Pixtral 12B
55.0%
274
Gemma 3n 4B
55.0%
275
Gemma 2 9B
53.5%
276
Olmo 3.1 32B Instruct
53.5%
277
GPT-3.5 Turbo Instruct
53.0%
278
Mistral Nemo
52.5%
279
Ministral 8B
51.5%
280
Molmo2 8B
51.0%
281
LFM2-8B-A1B
51.0%
282
Codestral 2508
50.0%
283
Goliath 120B
49.5%
284
Olmo 3 7B Think
49.5%
285
Hunyuan A13B Instruct
48.5%
286
Qwen2.5 7B Instruct
46.5%
287
Gemma 3 4B
44.5%
288
Hermes 3 70B Instruct
44.0%
289
Llama 3 8B Lunaris
43.0%
290
Granite 4.0 Micro
42.5%
291
Mistral 7B Instruct v0.2
42.0%
292
Qwen2.5-VL 7B Instruct
41.5%
293
Mistral 7B Instruct
41.5%
294
Mistral 7B Instruct v0.3
41.5%
295
Mistral Tiny
41.0%
296
Llama 3.1 8B Instruct
39.5%
297
Hermes 2 Pro - Llama-3 8B
39.0%
298
Command R7B (12-2024)
39.0%
299
Llama 3 8B Instruct
36.0%
300
Ministral 3B
35.5%
301
Lumimaid v0.2 8B
34.5%
302
Rocinante 12B
34.0%
303
Mistral 7B Instruct v0.1
32.5%
304
Olmo 3 7B Instruct
32.5%
305
Llama 3.2 3B Instruct
32.0%
306
Rnj 1 Instruct
30.0%
307
UnslopNemo 12B
27.5%
308
Noromaid 20B
27.0%
309
MythoMax 13B
26.0%
310
ReMM SLERP 13B
26.0%
311
Weaver (alpha)
24.5%
312
Llama 3.2 11B Vision Instruct
23.0%
313
Aion-RP 1.0 (8B)
22.5%
314
Llama 3.2 1B Instruct
14.5%
315
Morph V3 Large
11.5%
316
Morph V3 Fast
10.5%
317
Llemma 7b
8.5%
318
CodeLLaMa 7B Instruct Solidity
3.5%
319
Qwen3 4B
0.0%
Average:77.8%
(319 modelos)
Metrics menu
Average response time
Average time for the model to respond to each question
1
Ministral 3B
1.5s
2
gpt-oss-safeguard-20b
1.5s
3
Devstral Small 1.1
1.5s
4
Mercury 2
1.6s
5
Ministral 8B
1.8s
6
Mistral 7B Instruct v0.3
1.9s
7
Mistral 7B Instruct
1.9s
8
Morph V3 Large
1.9s
9
Voxtral Small 24B 2507
2.0s
10
LFM2-8B-A1B
2.1s
11
Mercury Coder
2.2s
12
Mercury
2.3s
13
Codestral 2508
2.4s
14
Mistral Tiny
2.5s
15
Nova Micro 1.0
2.6s
16
Gemma 2 9B
2.6s
17
Mistral 7B Instruct v0.2
2.6s
18
Gemini 3.1 Flash Lite Preview
2.8s
19
GPT-3.5 Turbo 16k
3.0s
20
GPT-3.5 Turbo
3.1s
21
Morph V3 Fast
3.1s
22
Command R7B (12-2024)
3.2s
23
GPT-4o (2024-05-13)
3.4s
24
Ministral 3 3B 2512
3.5s
25
Jamba Mini 1.7
3.5s
26
Claude 3 Haiku
3.5s
27
Gemini 2.0 Flash
3.5s
28
Gemini 2.5 Flash Lite Preview 09-2025
3.6s
29
Devstral Medium
3.6s
30
GPT-3.5 Turbo Instruct
3.7s
31
GPT-4.1 Nano
3.8s
32
Nova Lite 1.0
3.9s
33
Gemini 2.0 Flash Lite
3.9s
34
GPT-5.1-Codex-Mini
4.0s
35
LFM2-24B-A2B
4.1s
36
Hermes 2 Pro - Llama-3 8B
4.1s
37
Gemini 2.5 Flash Lite
4.2s
38
Qwen3 Coder 480B A35B (exacto)
4.2s
39
gpt-oss-20b
4.3s
40
Lumimaid v0.2 8B
4.3s
41
Pixtral 12B
4.3s
42
Mixtral 8x22B Instruct
4.3s
43
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
4.4s
44
GPT-4o-mini Search Preview
4.4s
45
Nova Pro 1.0
4.5s
46
Relace Search
4.6s
47
Saba
4.7s
48
ChatGPT-4o
4.7s
49
GPT-5.1-Codex
4.8s
50
Hermes 4 70B
4.9s
51
Llama 3.2 1B Instruct
4.9s
52
Aion-1.0-Mini
4.9s
53
Solar Pro 3
5.0s
54
GPT-5 Chat
5.1s
55
GPT-5.1 Chat
5.1s
56
Rnj 1 Instruct
5.2s
57
Cogito v2.1 671B
5.3s
58
Skyfall 36B V2
5.4s
59
Gemini 2.5 Flash Preview 09-2025
5.4s
60
Gemini 2.5 Flash
5.5s
61
Gemma 2 27B
5.5s
62
Ministral 3 8B 2512
5.6s
63
Qwen3 Coder 480B A35B
5.7s
64
Llama 3 8B Lunaris
5.7s
65
GPT-5 Codex
5.8s
66
Mistral Medium 3
6.2s
67
Qwen2.5-VL 7B Instruct
6.2s
68
Claude Haiku 4.5
6.2s
69
Mixtral 8x7B Instruct
6.3s
70
Kimi K2 0905 (exacto)
6.4s
71
Molmo2 8B
6.5s
72
Sonar
6.5s
73
Gemini 3 Flash Preview
6.5s
74
GPT-4o (2024-11-20)
6.6s
75
Sonar Pro
6.6s
76
o3 Mini High
6.7s
77
GPT-5.3 Chat
6.9s
78
Mistral Nemo
7.0s
79
GPT-4.1 Mini
7.1s
80
o3 Mini
7.1s
81
Aurora Alpha
7.2s
82
Claude 3.5 Haiku
7.2s
83
Kimi K2 0905
7.2s
84
Qwen-Turbo
7.2s
85
Mistral Small 3
7.3s
86
GPT-4o Search Preview
7.4s
87
Qwen3 Coder Flash
7.5s
88
Nova 2 Lite
7.5s
89
GLM 4 32B
7.6s
90
GPT-4o-mini (2024-07-18)
7.6s
91
GPT-4o-mini
7.6s
92
Mistral Small Creative
7.6s
93
Llama 4 Scout
7.8s
94
ERNIE 4.5 21B A3B
7.8s
95
GPT-5.4
7.9s
96
Hunyuan A13B Instruct
7.9s
97
Seed 1.6 Flash
8.0s
98
Cogito V2 Preview Llama 70B
8.0s
99
Palmyra X5
8.1s
100
Ministral 3 14B 2512
8.2s
101
Trinity Mini
8.2s
102
UnslopNemo 12B
8.3s
103
Command R (08-2024)
8.5s
104
Mistral Medium 3.1
8.5s
105
Cydonia 24B V4.1
8.6s
106
o4 Mini
8.7s
107
Mistral Small 3.1 24B
8.9s
108
Hermes 4 405B
8.9s
109
MiniMax M2-her
8.9s
110
Mistral Small 3.2 24B
8.9s
111
Llama 3 Euryale 70B v2.1
9.0s
112
GPT-3.5 Turbo (older v0613)
9.1s
113
GPT-5.2 Chat
9.1s
114
Qwen VL Plus
9.1s
115
Inflection 3 Productivity
9.2s
116
Inflection 3 Pi
9.2s
117
DeepSeek V3 0324
9.2s
118
KAT-Coder-Pro V1
9.2s
119
GPT-4o
9.3s
120
Grok 4 Fast
9.3s
121
Pixtral Large 2411
9.4s
122
Mistral Large 2411
9.5s
123
Rocinante 12B
9.5s
124
GPT-4o (2024-08-06)
9.6s
125
Llama 3.1 70B Instruct
9.6s
126
Qwen3 Next 80B A3B Instruct
9.6s
127
Command A
10.0s
128
Sonar Pro Search
10.2s
129
Command R+ (08-2024)
10.3s
130
MiMo-V2-Flash
10.4s
131
GPT-4 Turbo (older v1106)
10.5s
132
Claude 3.7 Sonnet
10.6s
133
Llama 3 8B Instruct
10.7s
134
o3
10.7s
135
Claude Sonnet 4
10.7s
136
Step 3.5 Flash
10.7s
137
Qwen2.5 7B Instruct
10.8s
138
Claude 3.5 Sonnet
10.8s
139
MythoMax 13B
10.8s
140
GPT-5.3-Codex
10.8s
141
GPT-4.1
11.0s
142
Qwen-Max
11.1s
143
SorcererLM 8x22B
11.1s
144
Llama 4 Maverick
11.2s
145
o1
11.2s
146
Nemotron Nano 9B V2
11.3s
147
Qwen2.5 72B Instruct
11.3s
148
MiniMax M2
11.5s
149
o4 Mini High
11.9s
150
Aion-RP 1.0 (8B)
12.0s
151
Mistral Large
12.1s
152
Mistral Large 2407
12.1s
153
Grok Code Fast 1
12.1s
154
Gemma 3n 4B
12.2s
155
Qwen3 VL 8B Instruct
12.2s
156
Mistral Large 3 2512
12.2s
157
Gemma 3 4B
12.3s
158
Sonar Reasoning Pro
12.4s
159
gpt-oss-120b (exacto)
12.4s
160
Gemma 3 12B
12.5s
161
Qwen Plus 0728
12.5s
162
Trinity Large Preview
12.6s
163
Grok 4.1 Fast
12.7s
164
ReMM SLERP 13B
12.8s
165
Claude Sonnet 4.6
12.9s
166
Weaver (alpha)
13.0s
167
GPT-4 (older v0314)
13.1s
168
Qwen3 VL 30B A3B Instruct
13.1s
169
GPT-4 Turbo
13.1s
170
Claude Sonnet 4.5
13.2s
171
GPT-4
13.4s
172
Gemma 3 27B
13.4s
173
Noromaid 20B
13.5s
174
Cogito V2 Preview Llama 405B
13.6s
175
Llama 3.3 70B Instruct
13.7s
176
GPT-4 Turbo Preview
13.7s
177
Olmo 3.1 32B Instruct
13.7s
178
Qwen-Plus
13.8s
179
GPT-5.2-Codex
13.8s
180
Claude Opus 4.5
13.9s
181
DeepSeek V3
14.0s
182
GPT-5.2
14.1s
183
Llama 3 70B Instruct
14.2s
184
Nemotron Nano 12B 2 VL
14.2s
185
Llama 3.1 Nemotron Ultra 253B v1
14.3s
186
Granite 4.0 Micro
14.3s
187
Phi 4
14.4s
188
Qwen3 Coder 30B A3B Instruct
14.5s
189
Tongyi DeepResearch 30B A3B
14.6s
190
Llama 3.1 Nemotron 70B Instruct
14.6s
191
GPT-5.1-Codex-Max
14.9s
192
R1 Distill Llama 70B
15.1s
193
Auto Router
15.2s
194
Miri
15.3s
195
Olmo 3 7B Think
15.3s
196
Qwen2.5 Coder 32B Instruct
15.4s
197
Nova Premier 1.0
15.5s
198
DeepSeek V3.1 Terminus
15.5s
199
DeepSeek V3.1 Terminus (exacto)
15.6s
200
Qwen3 Coder Plus
15.7s
201
Kimi K2 0711
15.8s
202
Hermes 3 405B Instruct
15.9s
203
Qwen3.5 Plus 2026-02-15
16.0s
204
ERNIE 4.5 VL 28B A3B
16.1s
205
Claude Opus 4.6
16.3s
206
Grok 3 Beta
16.4s
207
Grok 3 Mini
16.5s
208
Grok 3 Mini Beta
16.5s
209
Jamba Large 1.7
16.6s
210
Grok 3
16.6s
211
GPT-5 Mini
16.7s
212
Qwen2.5 VL 32B Instruct
16.8s
213
ERNIE 4.5 300B A47B
16.8s
214
Qwen3 30B A3B Instruct 2507
16.9s
215
GPT-5 Image Mini
17.1s
216
Qwen3 30B A3B Thinking 2507
17.3s
217
Qwen3 VL 235B A22B Instruct
17.7s
218
Nano Banana (Gemini 2.5 Flash Image)
17.8s
219
GPT-5.1
17.8s
220
Llama 3.1 Euryale 70B v2.2
18.2s
221
Qwen3 VL 32B Instruct
18.5s
222
Qwen3 Max
18.9s
223
Gemini 3.1 Pro Preview Custom Tools
19.0s
224
Llama 3.3 Nemotron Super 49B V1.5
19.0s
225
Switchpoint Router
19.2s
226
Olmo 3 7B Instruct
19.3s
227
Llama 3.2 3B Instruct
19.5s
228
Qwen3 8B
19.6s
229
Llama 3.3 Euryale 70B
19.6s
230
gpt-oss-120b
19.7s
231
Step 3.5 Flash
19.9s
232
Qwen3 235B A22B Instruct 2507
20.2s
233
ERNIE 4.5 VL 424B A47B
20.4s
234
Llama 3.1 8B Instruct
20.8s
235
Qwen3 Next 80B A3B Thinking
21.0s
236
Gemini 3.1 Pro Preview
21.3s
237
Qwen VL Max
21.6s
238
GPT-5 Nano
21.7s
239
GPT-5 Image
21.9s
240
MiMo-V2-Flash
22.4s
241
Qwen2.5 VL 72B Instruct
22.7s
242
Qwen3 Coder Next
22.9s
243
Qwen3 Max Thinking
23.8s
244
GPT-5
23.8s
245
Goliath 120B
24.3s
246
Mistral 7B Instruct v0.1
24.5s
247
Qwen3.5-122B-A10B
24.8s
248
Qwen3 14B
25.0s
249
MiniMax M1
25.6s
250
Qwen3 235B A22B
25.7s
251
Gemini 2.5 Pro Preview 06-05
25.8s
252
Gemini 2.5 Pro
26.1s
253
GLM 4.5 Air
26.1s
254
Gemini 2.5 Pro Preview 05-06
26.2s
255
Medgemma
26.4s
256
Qwen3 32B
26.8s
257
Free Models Router
28.4s
258
Claude Opus 4
28.5s
259
Qwen3.5-Flash
28.7s
260
MiniMax M2.1
28.8s
261
DeepSeek V3.1 Nex N1
30.6s
262
ERNIE 4.5 21B A3B Thinking
30.9s
263
Claude Opus 4.1
31.0s
264
Qwen Plus 0728 (thinking)
31.2s
265
Aion-1.0
31.4s
266
Llama 3.1 70B Hanami x1
31.8s
267
Gemini 3 Pro Preview
31.9s
268
Nano Banana Pro (Gemini 3 Pro Image Preview)
32.1s
269
Qwen3.5-35B-A3B
32.1s
270
Solar Pro 3
32.1s
271
o1-pro
33.2s
272
CodeLLaMa 7B Instruct Solidity
33.4s
273
R1 0528
33.7s
274
GLM 4.5V
33.8s
275
DeepSeek V3.2 Exp
33.9s
276
Claude 3.7 Sonnet (thinking)
34.7s
277
Nemotron 3 Nano 30B A3B
35.5s
278
DeepSeek V3.2
36.2s
279
Aion-2.0
36.3s
280
GLM 4.5
36.8s
281
GLM 4.6V
37.6s
282
MiniMax M2.5
38.2s
283
R1 Distill Qwen 32B
38.5s
284
Qwen3 VL 30B A3B Thinking
38.8s
285
Qwen3 VL 8B Thinking
38.9s
286
Seed 1.6
39.7s
287
GLM 4.6
40.9s
288
GPT-5.2 Pro
42.3s
289
Devstral 2 2512
43.8s
290
Grok 4
44.7s
291
Sonar Deep Research
45.0s
292
R1
46.3s
293
Qwen3 VL 235B A22B Thinking
46.7s
294
Kimi Dev 72B
46.9s
295
DeepSeek V3.1
47.5s
296
Qwen3.5-27B
47.5s
297
ALMA
50.8s
298
Llama 3.2 11B Vision Instruct
50.8s
299
Olmo 3 32B Think
51.1s
300
Step3
52.1s
301
Kimi K2 Thinking
52.8s
302
o3 Pro
52.9s
303
Olmo 3.1 32B Think
54.7s
304
Kimi K2.5
60.4s
305
Qwen3.5 397B A17B
60.8s
306
Seed-2.0-Mini
62.8s
307
QwQ 32B
64.2s
308
Llemma 7b
65.0s
309
GLM 4.6 (exacto)
72.3s
310
GLM 4.7
74.6s
311
DeepSeek V3.2 Speciale
94.0s
312
GLM 4.7 Flash
101.0s
313
Qwen3 235B A22B Thinking 2507
107.9s
314
GPT-5.4 Pro
110.7s
315
o4 Mini Deep Research
124.5s
316
o3 Deep Research
125.1s
317
GLM 5
126.0s
318
Hermes 3 70B Instruct
163.5s
Average:19.0s
(318 modelos)
Metrics menu
Average cost per question
Average cost in USD per evaluated question
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
LFM2-24B-A2B
$0.0001
17
GLM 4 32B
$0.0001
18
Nova Micro 1.0
$0.0001
19
Pixtral 12B
$0.0001
20
Mistral Small 3
$0.0001
21
Phi 4
$0.0001
22
Voxtral Small 24B 2507
$0.0001
23
Gemma 3 12B
$0.0001
24
Hermes 2 Pro - Llama-3 8B
$0.0001
25
Llama 3.2 1B Instruct
$0.0001
26
Ministral 3 3B 2512
$0.0001
27
Qwen-Turbo
$0.0001
28
Devstral Small 1.1
$0.0001
29
Nova Lite 1.0
$0.0001
30
Mistral 7B Instruct v0.1
$0.0001
31
Rnj 1 Instruct
$0.0002
32
Mistral Small 3.2 24B
$0.0002
33
Gemma 3 27B
$0.0002
34
Gemini 2.0 Flash Lite
$0.0002
35
Mistral 7B Instruct v0.3
$0.0002
36
Mistral 7B Instruct
$0.0002
37
gpt-oss-120b (exacto)
$0.0002
38
ERNIE 4.5 21B A3B
$0.0002
39
Qwen2.5-VL 7B Instruct
$0.0002
40
Ministral 3 8B 2512
$0.0002
41
Llama 3.2 11B Vision Instruct
$0.0002
42
Mistral 7B Instruct v0.2
$0.0002
43
GPT-4.1 Nano
$0.0002
44
Molmo2 8B
$0.0002
45
gpt-oss-20b
$0.0002
46
Lumimaid v0.2 8B
$0.0002
47
Gemini 2.0 Flash
$0.0002
48
Mistral Tiny
$0.0002
49
Olmo 3 7B Instruct
$0.0002
50
Qwen3 Coder 30B A3B Instruct
$0.0002
51
Hermes 4 70B
$0.0002
52
Trinity Mini
$0.0003
53
Nemotron Nano 9B V2
$0.0003
54
Llama 4 Scout
$0.0003
55
Ministral 3 14B 2512
$0.0003
56
Qwen2.5 72B Instruct
$0.0003
57
Jamba Mini 1.7
$0.0003
58
Qwen2.5 Coder 32B Instruct
$0.0003
59
Qwen3 14B
$0.0003
60
Saba
$0.0003
61
Command R (08-2024)
$0.0003
62
gpt-oss-safeguard-20b
$0.0003
63
Mistral Small 3.1 24B
$0.0004
64
Qwen3 30B A3B Instruct 2507
$0.0004
65
UnslopNemo 12B
$0.0004
66
Rocinante 12B
$0.0004
67
Hunyuan A13B Instruct
$0.0004
68
MiMo-V2-Flash
$0.0004
69
Qwen3 8B
$0.0004
70
KAT-Coder-Pro V1
$0.0004
71
Solar Pro 3
$0.0004
72
DeepSeek V3.2 Exp
$0.0004
73
Llama 3.1 70B Instruct
$0.0004
74
Cydonia 24B V4.1
$0.0004
75
Gemma 2 27B
$0.0004
76
Seed 1.6 Flash
$0.0005
77
DeepSeek V3.2
$0.0005
78
Gemini 2.5 Flash Lite
$0.0005
79
Gemini 2.5 Flash Lite Preview 09-2025
$0.0005
80
Llama 3.3 70B Instruct
$0.0005
81
GPT-4o-mini (2024-07-18)
$0.0005
82
Mistral Small Creative
$0.0005
83
GPT-4o-mini
$0.0005
84
gpt-oss-120b
$0.0005
85
Llama 3 70B Instruct
$0.0005
86
Codestral 2508
$0.0005
87
Mercury Coder
$0.0005
88
Mercury
$0.0005
89
ReMM SLERP 13B
$0.0006
90
Qwen2.5 VL 72B Instruct
$0.0006
91
Llama 4 Maverick
$0.0006
92
Qwen3 VL 8B Instruct
$0.0006
93
Olmo 3.1 32B Instruct
$0.0006
94
DeepSeek V3.1 Terminus (exacto)
$0.0006
95
DeepSeek V3
$0.0006
96
Mixtral 8x7B Instruct
$0.0006
97
Qwen VL Plus
$0.0006
98
Skyfall 36B V2
$0.0006
99
Mercury 2
$0.0007
100
ERNIE 4.5 300B A47B
$0.0007
101
Olmo 3 7B Think
$0.0007
102
DeepSeek V3.1
$0.0007
103
Qwen3 30B A3B Thinking 2507
$0.0007
104
Claude 3 Haiku
$0.0007
105
Qwen3 VL 235B A22B Instruct
$0.0007
106
Qwen3 32B
$0.0007
107
Llama 3.3 Nemotron Super 49B V1.5
$0.0007
108
ERNIE 4.5 VL 28B A3B
$0.0007
109
Grok 4 Fast
$0.0007
110
Qwen3 235B A22B Instruct 2507
$0.0007
111
Aion-1.0-Mini
$0.0007
112
GPT-3.5 Turbo
$0.0007
113
Qwen3 VL 30B A3B Instruct
$0.0007
114
Tongyi DeepResearch 30B A3B
$0.0008
115
DeepSeek V3.1 Terminus
$0.0008
116
Grok 4.1 Fast
$0.0008
117
Cogito V2 Preview Llama 70B
$0.0008
118
Llama 3.3 Euryale 70B
$0.0008
119
Hermes 3 405B Instruct
$0.0008
120
ERNIE 4.5 21B A3B Thinking
$0.0009
121
Step 3.5 Flash
$0.0009
122
Llama 3.1 Euryale 70B v2.2
$0.0009
123
GPT-5 Nano
$0.0009
124
Nemotron 3 Nano 30B A3B
$0.0009
125
Grok 3 Mini Beta
$0.0009
126
QwQ 32B
$0.0009
127
Grok 3 Mini
$0.0010
128
GPT-4.1 Mini
$0.0010
129
DeepSeek V3 0324
$0.0010
130
Qwen3 Next 80B A3B Instruct
$0.0010
131
Devstral Medium
$0.0010
132
Seed-2.0-Mini
$0.0010
133
Aion-RP 1.0 (8B)
$0.0011
134
GLM 4.5 Air
$0.0011
135
Weaver (alpha)
$0.0011
136
MiniMax M2-her
$0.0011
137
GPT-5.1-Codex-Mini
$0.0011
138
Mistral Medium 3
$0.0012
139
Cogito v2.1 671B
$0.0012
140
DeepSeek V3.1 Nex N1
$0.0012
141
Mistral Large 3 2512
$0.0012
142
ERNIE 4.5 VL 424B A47B
$0.0012
143
R1 Distill Qwen 32B
$0.0013
144
Qwen3 Coder 480B A35B
$0.0013
145
Qwen Plus 0728
$0.0013
146
Qwen3 Coder Flash
$0.0013
147
Qwen-Plus
$0.0013
148
Qwen3 Coder 480B A35B (exacto)
$0.0013
149
Nemotron Nano 12B 2 VL
$0.0013
150
Qwen3 235B A22B
$0.0013
151
Llama 3.1 Nemotron Ultra 253B v1
$0.0014
152
R1 Distill Llama 70B
$0.0014
153
Llama 3 Euryale 70B v2.1
$0.0014
154
MiniMax M2.5
$0.0014
155
Qwen2.5 VL 32B Instruct
$0.0014
156
Morph V3 Large
$0.0014
157
Qwen3 Coder Next
$0.0014
158
MiniMax M2.1
$0.0015
159
Noromaid 20B
$0.0015
160
Llama 3.1 Nemotron 70B Instruct
$0.0015
161
Kimi Dev 72B
$0.0015
162
GPT-3.5 Turbo (older v0613)
$0.0015
163
Hermes 4 405B
$0.0015
164
Qwen3 VL 32B Instruct
$0.0016
165
GPT-3.5 Turbo Instruct
$0.0016
166
Nova Pro 1.0
$0.0016
167
Kimi K2 0711
$0.0016
168
GLM 4.7 Flash
$0.0016
169
Qwen3.5-Flash
$0.0017
170
GLM 4.5V
$0.0017
171
Mistral Medium 3.1
$0.0017
172
Aion-2.0
$0.0018
173
Gemini 3 Flash Preview
$0.0018
174
GLM 4.6V
$0.0018
175
CodeLLaMa 7B Instruct Solidity
$0.0019
176
Olmo 3 32B Think
$0.0019
177
Claude 3.5 Haiku
$0.0020
178
MiniMax M2
$0.0020
179
Olmo 3.1 32B Think
$0.0020
180
Grok Code Fast 1
$0.0022
181
Qwen3 VL 30B A3B Thinking
$0.0022
182
GPT-5 Mini
$0.0023
183
Gemini 2.5 Flash
$0.0025
184
GLM 4.6 (exacto)
$0.0026
185
Relace Search
$0.0026
186
DeepSeek V3.2 Speciale
$0.0027
187
Hermes 3 70B Instruct
$0.0027
188
Nova 2 Lite
$0.0028
189
Gemini 2.5 Flash Preview 09-2025
$0.0028
190
MiniMax M1
$0.0029
191
Switchpoint Router
$0.0030
192
Cogito V2 Preview Llama 405B
$0.0030
193
Seed 1.6
$0.0030
194
Qwen3.5 Plus 2026-02-15
$0.0031
195
Qwen VL Max
$0.0031
196
Nano Banana (Gemini 2.5 Flash Image)
$0.0031
197
Llama 3.1 70B Hanami x1
$0.0032
198
Llemma 7b
$0.0032
199
Qwen3 235B A22B Thinking 2507
$0.0032
200
Step3
$0.0032
201
Kimi K2 0905
$0.0033
202
Mixtral 8x22B Instruct
$0.0033
203
GPT-5.1 Chat
$0.0037
204
GPT-5.1-Codex
$0.0037
205
GLM 4.5
$0.0037
206
Kimi K2 0905 (exacto)
$0.0039
207
Qwen3 Coder Plus
$0.0040
208
Miri
$0.0041
209
Mistral Large 2411
$0.0042
210
R1
$0.0042
211
GPT-5 Image Mini
$0.0043
212
Claude Haiku 4.5
$0.0043
213
Palmyra X5
$0.0046
214
Command A
$0.0046
215
Mistral Large
$0.0047
216
Mistral Large 2407
$0.0047
217
Pixtral Large 2411
$0.0048
218
GPT-4.1
$0.0048
219
Command R+ (08-2024)
$0.0050
220
Qwen3 Next 80B A3B Thinking
$0.0050
221
Qwen-Max
$0.0050
222
Qwen3.5-35B-A3B
$0.0050
223
Inflection 3 Productivity
$0.0051
224
Qwen3 Max
$0.0051
225
Inflection 3 Pi
$0.0051
226
Qwen3 Max Thinking
$0.0052
227
GPT-4o
$0.0053
228
GPT-4o (2024-08-06)
$0.0053
229
Kimi K2 Thinking
$0.0053
230
Qwen3.5 397B A17B
$0.0054
231
SorcererLM 8x22B
$0.0056
232
GPT-5 Chat
$0.0056
233
Nova Premier 1.0
$0.0057
234
GPT-5 Codex
$0.0057
235
R1 0528
$0.0057
236
GLM 4.6
$0.0058
237
Qwen3 VL 235B A22B Thinking
$0.0061
238
Goliath 120B
$0.0063
239
GLM 4.7
$0.0063
240
Sonar
$0.0063
241
Qwen3 VL 8B Thinking
$0.0066
242
o3 Mini High
$0.0068
243
o3 Mini
$0.0072
244
Kimi K2.5
$0.0073
245
Qwen3.5-27B
$0.0074
246
o4 Mini
$0.0075
247
GPT-4o (2024-11-20)
$0.0075
248
Qwen3.5-122B-A10B
$0.0076
249
Morph V3 Fast
$0.0079
250
Jamba Large 1.7
$0.0085
251
GPT-5.2 Chat
$0.0087
252
Qwen Plus 0728 (thinking)
$0.0091
253
GPT-4o (2024-05-13)
$0.0095
254
GPT-5.2-Codex
$0.0103
255
GPT-5.2
$0.0107
256
Aion-1.0
$0.0109
257
ChatGPT-4o
$0.0112
258
Claude Sonnet 4
$0.0112
259
GPT-5.1
$0.0115
260
o3
$0.0115
261
GLM 5
$0.0116
262
o4 Mini High
$0.0117
263
Claude 3.7 Sonnet
$0.0126
264
GPT-5
$0.0128
265
Claude Sonnet 4.5
$0.0132
266
Grok 3 Beta
$0.0133
267
Claude Sonnet 4.6
$0.0135
268
Grok 3
$0.0139
269
GPT-5.1-Codex-Max
$0.0155
270
Sonar Pro
$0.0166
271
Claude 3.5 Sonnet
$0.0167
272
Sonar Reasoning Pro
$0.0174
273
GPT-5 Image
$0.0197
274
Gemini 3.1 Pro Preview
$0.0205
275
GPT-4 Turbo
$0.0210
276
GPT-4 Turbo Preview
$0.0221
277
Auto Router
$0.0239
278
Claude Opus 4.5
$0.0239
279
Grok 4
$0.0252
280
Claude Opus 4.6
$0.0254
281
Sonar Pro Search
$0.0280
282
Nano Banana Pro (Gemini 3 Pro Image Preview)
$0.0297
283
Gemini 2.5 Pro Preview 06-05
$0.0303
284
Gemini 2.5 Pro
$0.0305
285
Gemini 2.5 Pro Preview 05-06
$0.0305
286
Gemini 3 Pro Preview
$0.0319
287
GPT-4 (older v0314)
$0.0398
288
Claude 3.7 Sonnet (thinking)
$0.0417
289
GPT-4
$0.0427
290
Claude Opus 4
$0.0535
291
ALMA
$0.0551
292
Claude Opus 4.1
$0.0566
293
o3 Pro
$0.1142
294
GPT-5.2 Pro
$0.1303
295
o1
$0.1363
296
o4 Mini Deep Research
$0.1823
297
o3 Deep Research
$0.8452
298
Sonar Deep Research
$1.1711
299
o1-pro
$1.3937
Average:$0.0100
(299 modelos)
Metrics menu
Average confidence
Average confidence level reported by the model
1
o3 Pro
100.0%
2
Gemini 3.1 Pro Preview
100.0%
3
Gemini 2.5 Pro Preview 06-05
100.0%
4
Claude Opus 4.5
100.0%
5
gpt-oss-120b
100.0%
6
R1 0528
100.0%
7
o3 Deep Research
100.0%
8
GPT-5.2
100.0%
9
GPT-5.3 Chat
100.0%
10
Gemini 3 Pro Preview
100.0%
11
Auto Router
100.0%
12
GLM 4.7
100.0%
13
Gemini 3.1 Flash Lite Preview
100.0%
14
GPT-5.4 Pro
100.0%
15
o4 Mini Deep Research
99.9%
16
GPT-5.1
99.9%
17
Claude Opus 4
99.9%
18
GPT-5 Codex
99.9%
19
GPT-5.1-Codex-Max
99.9%
20
Gemini 2.5 Pro
99.9%
21
Claude Opus 4.6
99.9%
22
Gemini 2.5 Pro Preview 05-06
99.9%
23
o4 Mini
99.9%
24
o1-pro
99.9%
25
Claude Sonnet 4.5
99.9%
26
GLM 4.5V
99.9%
27
GPT-5.1-Codex-Mini
99.9%
28
Aion-2.0
99.9%
29
o1
99.9%
30
Qwen3.5 397B A17B
99.9%
31
KAT-Coder-Pro V1
99.9%
32
GPT-5.3-Codex
99.9%
33
GPT-5.4
99.9%
34
Gemini 3.1 Pro Preview Custom Tools
99.9%
35
Qwen3 235B A22B
99.8%
36
Grok 4 Fast
99.8%
37
GPT-5.2-Codex
99.8%
38
Qwen3.5-35B-A3B
99.8%
39
ALMA
99.8%
40
Miri
99.8%
41
GPT-5 Mini
99.8%
42
GLM 5
99.8%
43
Qwen3 VL 30B A3B Thinking
99.8%
44
Sonar Deep Research
99.8%
45
Claude Sonnet 4
99.8%
46
o3 Mini
99.8%
47
Qwen3 VL 8B Thinking
99.8%
48
Mistral Large 3 2512
99.8%
49
ChatGPT-4o
99.8%
50
Qwen3 Next 80B A3B Instruct
99.8%
51
Qwen3.5 Plus 2026-02-15
99.8%
52
gpt-oss-20b
99.8%
53
Qwen3 Coder Flash
99.8%
54
Claude Sonnet 4.6
99.7%
55
Gemini 3 Flash Preview
99.7%
56
Nano Banana Pro (Gemini 3 Pro Image Preview)
99.7%
57
Aion-1.0
99.7%
58
QwQ 32B
99.7%
59
o3
99.5%
60
o4 Mini High
99.5%
61
Nemotron 3 Nano 30B A3B
99.5%
62
Qwen2.5 72B Instruct
99.5%
63
GPT-5.2 Pro
99.5%
64
Gemini 2.5 Flash Lite Preview 09-2025
99.5%
65
GPT-5 Image
99.5%
66
Grok 4
99.5%
67
GPT-4.1 Mini
99.5%
68
Mercury 2
99.5%
69
GPT-4.1
99.5%
70
GLM 4.6V
99.5%
71
Qwen-Plus
99.5%
72
Palmyra X5
99.4%
73
Relace Search
99.4%
74
GPT-5.1 Chat
99.4%
75
Kimi K2.5
99.4%
76
Qwen Plus 0728 (thinking)
99.4%
77
Claude 3.7 Sonnet (thinking)
99.4%
78
Step3
99.4%
79
Qwen3 VL 30B A3B Instruct
99.4%
80
Qwen3 VL 235B A22B Thinking
99.4%
81
Qwen Plus 0728
99.4%
82
Qwen3 VL 235B A22B Instruct
99.4%
83
Mistral Large 2411
99.4%
84
Gemini 2.5 Flash Preview 09-2025
99.4%
85
o3 Mini High
99.4%
86
Grok 4.1 Fast
99.4%
87
Claude Opus 4.1
99.4%
88
GPT-5.1-Codex
99.3%
89
GPT-4o (2024-05-13)
99.3%
90
ERNIE 4.5 300B A47B
99.3%
91
GPT-5
99.3%
92
Qwen3.5-Flash
99.3%
93
Qwen3 Coder 480B A35B (exacto)
99.3%
94
Seed 1.6
99.3%
95
gpt-oss-safeguard-20b
99.3%
96
Qwen3 Coder 480B A35B
99.3%
97
Ministral 3 8B 2512
99.3%
98
Qwen3 235B A22B Thinking 2507
99.3%
99
Mistral Large 2407
99.2%
100
Qwen3 Next 80B A3B Thinking
99.2%
101
Seed 1.6 Flash
99.1%
102
Tongyi DeepResearch 30B A3B
99.1%
103
MiMo-V2-Flash
99.1%
104
GPT-4.1 Nano
99.1%
105
Qwen3 30B A3B Instruct 2507
99.1%
106
Qwen2.5 VL 32B Instruct
99.1%
107
GPT-5.2 Chat
99.0%
108
GPT-5 Chat
99.0%
109
GLM 4.6
99.0%
110
gpt-oss-120b (exacto)
99.0%
111
Claude 3.5 Sonnet
99.0%
112
Qwen3 Coder 30B A3B Instruct
99.0%
113
DeepSeek V3.1 Terminus
99.0%
114
ERNIE 4.5 VL 424B A47B
99.0%
115
Mistral Large
99.0%
116
MiniMax M2
99.0%
117
Gemma 3 27B
99.0%
118
Gemma 3 12B
99.0%
119
GPT-5 Image Mini
99.0%
120
Switchpoint Router
99.0%
121
Nova Premier 1.0
99.0%
122
Mercury Coder
98.9%
123
Devstral 2 2512
98.9%
124
R1 Distill Qwen 32B
98.9%
125
ERNIE 4.5 21B A3B Thinking
98.9%
126
Qwen3 32B
98.9%
127
Mistral Medium 3.1
98.9%
128
Gemma 3 4B
98.9%
129
Qwen3.5-27B
98.9%
130
Gemini 2.5 Flash Lite
98.8%
131
GPT-3.5 Turbo
98.8%
132
Sonar
98.8%
133
Qwen3 VL 32B Instruct
98.8%
134
Command R (08-2024)
98.8%
135
Qwen3 235B A22B Instruct 2507
98.8%
136
Qwen2.5 VL 72B Instruct
98.8%
137
Llama 3.3 Nemotron Super 49B V1.5
98.7%
138
GLM 4.7 Flash
98.7%
139
Aurora Alpha
98.7%
140
DeepSeek V3
98.7%
141
Solar Pro 3
98.6%
142
GPT-4o-mini
98.6%
143
Claude Haiku 4.5
98.6%
144
GPT-5 Nano
98.6%
145
Llama 3.1 Nemotron Ultra 253B v1
98.5%
146
GLM 4.5
98.5%
147
Command A
98.5%
148
Mistral Medium 3
98.5%
149
GPT-3.5 Turbo (older v0613)
98.5%
150
DeepSeek V3.1 Terminus (exacto)
98.5%
151
DeepSeek V3.2 Exp
98.5%
152
Voxtral Small 24B 2507
98.5%
153
Gemini 2.5 Flash
98.5%
154
Qwen-Max
98.4%
155
GLM 4.6 (exacto)
98.4%
156
R1
98.4%
157
DeepSeek V3 0324
98.4%
158
GPT-4 Turbo
98.3%
159
R1 Distill Llama 70B
98.3%
160
Qwen3.5-122B-A10B
98.3%
161
DeepSeek V3.2
98.3%
162
Pixtral Large 2411
98.2%
163
Jamba Large 1.7
98.2%
164
Mistral Small 3.1 24B
98.2%
165
Claude 3.5 Haiku
98.2%
166
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
98.1%
167
LFM2-24B-A2B
98.1%
168
Grok 3
98.1%
169
Qwen3 Max Thinking
98.1%
170
Llama 4 Maverick
98.1%
171
Qwen VL Plus
98.1%
172
GPT-4o (2024-11-20)
98.1%
173
Qwen3 14B
98.0%
174
GLM 4 32B
98.0%
175
GPT-4o-mini (2024-07-18)
98.0%
176
Gemini 2.0 Flash Lite
98.0%
177
Mistral Small Creative
98.0%
178
Qwen VL Max
98.0%
179
Qwen3 Coder Next
97.9%
180
Llama 4 Scout
97.9%
181
Nova Lite 1.0
97.9%
182
Grok 3 Beta
97.9%
183
GPT-3.5 Turbo 16k
97.9%
184
Devstral Medium
97.7%
185
Nova Pro 1.0
97.7%
186
GPT-4o-mini Search Preview
97.7%
187
Step 3.5 Flash
97.7%
188
Ministral 3 14B 2512
97.7%
189
DeepSeek V3.1
97.6%
190
Sonar Pro
97.6%
191
Claude 3.7 Sonnet
97.6%
192
DeepSeek V3.2 Speciale
97.6%
193
Qwen3 30B A3B Thinking 2507
97.6%
194
GPT-4 Turbo Preview
97.5%
195
Llama 3 70B Instruct
97.5%
196
Gemini 2.0 Flash
97.5%
197
Qwen3 8B
97.5%
198
Step 3.5 Flash
97.5%
199
MiniMax M2.5
97.5%
200
Medgemma
97.5%
201
Kimi K2 0711
97.4%
202
Grok Code Fast 1
97.4%
203
Qwen3 Max
97.4%
204
GPT-4o (2024-08-06)
97.4%
205
Olmo 3 7B Think
97.3%
206
Nano Banana (Gemini 2.5 Flash Image)
97.3%
207
ERNIE 4.5 21B A3B
97.2%
208
Mistral Small 3.2 24B
97.2%
209
Qwen3 Coder Plus
97.2%
210
Trinity Large Preview
97.1%
211
Nova 2 Lite
97.1%
212
GPT-4o
97.1%
213
Grok 3 Mini
97.0%
214
Solar Pro 3
97.0%
215
Mercury
97.0%
216
Nemotron Nano 12B 2 VL
97.0%
217
Saba
97.0%
218
MiMo-V2-Flash
96.9%
219
GPT-4
96.9%
220
MiniMax M1
96.9%
221
Kimi K2 Thinking
96.8%
222
Grok 3 Mini Beta
96.8%
223
Hermes 4 405B
96.8%
224
Llama 3.1 70B Instruct
96.7%
225
Phi 4
96.7%
226
ERNIE 4.5 VL 28B A3B
96.6%
227
Kimi Dev 72B
96.6%
228
Seed-2.0-Mini
96.6%
229
Mixtral 8x22B Instruct
96.5%
230
GPT-4 (older v0314)
96.5%
231
Cogito V2 Preview Llama 70B
96.4%
232
Claude 3 Haiku
96.4%
233
Ministral 3 3B 2512
96.3%
234
Qwen-Turbo
96.1%
235
DeepSeek V3.1 Nex N1
96.0%
236
Nemotron Nano 9B V2
95.8%
237
Aion-1.0-Mini
95.8%
238
Devstral Small 1.1
95.7%
239
GPT-4o Search Preview
95.6%
240
Jamba Mini 1.7
95.6%
241
Sonar Pro Search
95.6%
242
LFM2-8B-A1B
95.5%
243
Inflection 3 Productivity
95.5%
244
Codestral 2508
95.5%
245
Trinity Mini
95.4%
246
GPT-3.5 Turbo Instruct
95.4%
247
Inflection 3 Pi
95.4%
248
Lumimaid v0.2 8B
95.2%
249
Llama 3.1 Nemotron 70B Instruct
95.1%
250
Cydonia 24B V4.1
95.0%
251
Mixtral 8x7B Instruct
94.9%
252
Qwen3 VL 8B Instruct
94.8%
253
Mistral Small 3
94.8%
254
Cogito v2.1 671B
94.7%
255
Granite 4.0 Micro
94.6%
256
Llama 3.3 70B Instruct
94.5%
257
Cogito V2 Preview Llama 405B
94.4%
258
Free Models Router
94.3%
259
Skyfall 36B V2
94.3%
260
GPT-4 Turbo (older v1106)
94.3%
261
Sonar Reasoning Pro
94.2%
262
MiniMax M2-her
94.2%
263
Llama 3.1 70B Hanami x1
94.1%
264
Gemma 3n 4B
94.1%
265
Olmo 3.1 32B Instruct
94.0%
266
MiniMax M2.1
93.7%
267
Hermes 3 405B Instruct
93.3%
268
GLM 4.5 Air
93.2%
269
Ministral 8B
93.2%
270
Kimi K2 0905
93.2%
271
Llama 3 Euryale 70B v2.1
93.1%
272
Gemma 2 27B
92.9%
273
Nova Micro 1.0
92.5%
274
Mistral 7B Instruct v0.2
92.0%
275
Mistral Nemo
91.9%
276
SorcererLM 8x22B
91.9%
277
Llama 3.3 Euryale 70B
91.8%
278
Qwen2.5 Coder 32B Instruct
91.8%
279
Command R7B (12-2024)
91.5%
280
Llama 3.1 Euryale 70B v2.2
91.4%
281
Hermes 4 70B
91.3%
282
Kimi K2 0905 (exacto)
91.3%
283
Mistral 7B Instruct v0.3
90.8%
284
Mistral Tiny
90.6%
285
Command R+ (08-2024)
90.1%
286
Mistral 7B Instruct
90.0%
287
Olmo 3 32B Think
89.5%
288
Pixtral 12B
89.4%
289
Molmo2 8B
89.0%
290
Goliath 120B
88.6%
291
Olmo 3.1 32B Think
88.3%
292
Llama 3 8B Lunaris
87.9%
293
Rnj 1 Instruct
87.7%
294
Ministral 3B
87.0%
295
Gemma 2 9B
86.8%
296
Llama 3 8B Instruct
86.7%
297
Hermes 2 Pro - Llama-3 8B
86.5%
298
Olmo 3 7B Instruct
84.0%
299
Qwen2.5 7B Instruct
82.8%
300
Llama 3.2 3B Instruct
82.5%
301
Hunyuan A13B Instruct
81.7%
302
Weaver (alpha)
79.0%
303
Noromaid 20B
78.7%
304
Mistral 7B Instruct v0.1
78.2%
305
Llama 3.1 8B Instruct
77.5%
306
Qwen2.5-VL 7B Instruct
76.8%
307
ReMM SLERP 13B
76.0%
308
MythoMax 13B
70.3%
309
Rocinante 12B
66.5%
310
Hermes 3 70B Instruct
65.0%
311
UnslopNemo 12B
59.6%
312
Aion-RP 1.0 (8B)
55.5%
313
Llama 3.2 1B Instruct
47.1%
314
Llama 3.2 11B Vision Instruct
45.4%
315
Morph V3 Fast
37.4%
316
Morph V3 Large
34.7%
317
Llemma 7b
29.0%
318
CodeLLaMa 7B Instruct Solidity
16.4%
Average:95.2%
(318 modelos)
Metrics menu
Total Cost
Total cost in USD to evaluate all questions
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
LFM2-24B-A2B
$0.02
17
GLM 4 32B
$0.02
18
Nova Micro 1.0
$0.02
19
Pixtral 12B
$0.02
20
Mistral Small 3
$0.02
21
Phi 4
$0.02
22
Voxtral Small 24B 2507
$0.03
23
Gemma 3 12B
$0.03
24
Hermes 2 Pro - Llama-3 8B
$0.03
25
Llama 3.2 1B Instruct
$0.03
26
Ministral 3 3B 2512
$0.03
27
Qwen-Turbo
$0.03
28
Devstral Small 1.1
$0.03
29
Nova Lite 1.0
$0.03
30
Mistral 7B Instruct v0.1
$0.03
31
Rnj 1 Instruct
$0.04
32
Mistral Small 3.2 24B
$0.04
33
Gemma 3 27B
$0.04
34
Gemini 2.0 Flash Lite
$0.04
35
Mistral 7B Instruct v0.3
$0.04
36
Mistral 7B Instruct
$0.04
37
gpt-oss-120b (exacto)
$0.04
38
ERNIE 4.5 21B A3B
$0.04
39
Qwen2.5-VL 7B Instruct
$0.04
40
Ministral 3 8B 2512
$0.04
41
Llama 3.2 11B Vision Instruct
$0.04
42
Mistral 7B Instruct v0.2
$0.04
43
GPT-4.1 Nano
$0.05
44
Molmo2 8B
$0.05
45
gpt-oss-20b
$0.05
46
Lumimaid v0.2 8B
$0.05
47
Gemini 2.0 Flash
$0.05
48
Mistral Tiny
$0.05
49
Olmo 3 7B Instruct
$0.05
50
Qwen3 Coder 30B A3B Instruct
$0.05
51
Hermes 4 70B
$0.05
52
Trinity Mini
$0.05
53
Nemotron Nano 9B V2
$0.06
54
Llama 4 Scout
$0.06
55
Ministral 3 14B 2512
$0.06
56
Qwen2.5 72B Instruct
$0.06
57
Jamba Mini 1.7
$0.06
58
Qwen2.5 Coder 32B Instruct
$0.06
59
Qwen3 14B
$0.06
60
Saba
$0.07
61
Command R (08-2024)
$0.07
62
gpt-oss-safeguard-20b
$0.07
63
Mistral Small 3.1 24B
$0.07
64
Qwen3 30B A3B Instruct 2507
$0.07
65
UnslopNemo 12B
$0.07
66
Rocinante 12B
$0.08
67
Hunyuan A13B Instruct
$0.08
68
MiMo-V2-Flash
$0.08
69
Qwen3 8B
$0.08
70
KAT-Coder-Pro V1
$0.08
71
Solar Pro 3
$0.08
72
DeepSeek V3.2 Exp
$0.09
73
Llama 3.1 70B Instruct
$0.09
74
Cydonia 24B V4.1
$0.09
75
Gemma 2 27B
$0.09
76
Seed 1.6 Flash
$0.09
77
DeepSeek V3.2
$0.09
78
Gemini 2.5 Flash Lite
$0.10
79
Gemini 2.5 Flash Lite Preview 09-2025
$0.10
80
Llama 3.3 70B Instruct
$0.10
81
GPT-4o-mini (2024-07-18)
$0.10
82
Mistral Small Creative
$0.10
83
GPT-4o-mini
$0.10
84
gpt-oss-120b
$0.10
85
Llama 3 70B Instruct
$0.10
86
Codestral 2508
$0.11
87
Mercury Coder
$0.11
88
Mercury
$0.11
89
ReMM SLERP 13B
$0.11
90
Qwen2.5 VL 72B Instruct
$0.12
91
Llama 4 Maverick
$0.12
92
Qwen3 VL 8B Instruct
$0.12
93
Olmo 3.1 32B Instruct
$0.12
94
DeepSeek V3.1 Terminus (exacto)
$0.12
95
DeepSeek V3
$0.12
96
Mixtral 8x7B Instruct
$0.12
97
Qwen VL Plus
$0.13
98
Skyfall 36B V2
$0.13
99
Mercury 2
$0.13
100
ERNIE 4.5 300B A47B
$0.14
101
Olmo 3 7B Think
$0.14
102
DeepSeek V3.1
$0.14
103
Qwen3 30B A3B Thinking 2507
$0.14
104
Claude 3 Haiku
$0.14
105
Qwen3 VL 235B A22B Instruct
$0.14
106
Qwen3 32B
$0.14
107
Llama 3.3 Nemotron Super 49B V1.5
$0.14
108
ERNIE 4.5 VL 28B A3B
$0.14
109
Grok 4 Fast
$0.15
110
Qwen3 235B A22B Instruct 2507
$0.15
111
Aion-1.0-Mini
$0.15
112
GPT-3.5 Turbo
$0.15
113
Qwen3 VL 30B A3B Instruct
$0.15
114
Tongyi DeepResearch 30B A3B
$0.16
115
DeepSeek V3.1 Terminus
$0.16
116
Grok 4.1 Fast
$0.16
117
Cogito V2 Preview Llama 70B
$0.16
118
Llama 3.3 Euryale 70B
$0.16
119
Hermes 3 405B Instruct
$0.17
120
ERNIE 4.5 21B A3B Thinking
$0.17
121
Step 3.5 Flash
$0.18
122
Llama 3.1 Euryale 70B v2.2
$0.18
123
GPT-5 Nano
$0.18
124
Nemotron 3 Nano 30B A3B
$0.18
125
Grok 3 Mini Beta
$0.19
126
QwQ 32B
$0.19
127
Grok 3 Mini
$0.19
128
GPT-4.1 Mini
$0.20
129
DeepSeek V3 0324
$0.20
130
Qwen3 Next 80B A3B Instruct
$0.20
131
Devstral Medium
$0.21
132
Seed-2.0-Mini
$0.21
133
Aion-RP 1.0 (8B)
$0.21
134
GLM 4.5 Air
$0.22
135
Weaver (alpha)
$0.22
136
MiniMax M2-her
$0.22
137
GPT-5.1-Codex-Mini
$0.22
138
Mistral Medium 3
$0.23
139
Cogito v2.1 671B
$0.23
140
DeepSeek V3.1 Nex N1
$0.24
141
Mistral Large 3 2512
$0.24
142
ERNIE 4.5 VL 424B A47B
$0.24
143
R1 Distill Qwen 32B
$0.25
144
Qwen3 Coder 480B A35B
$0.26
145
Qwen Plus 0728
$0.26
146
Qwen3 Coder Flash
$0.26
147
Qwen-Plus
$0.26
148
Qwen3 Coder 480B A35B (exacto)
$0.26
149
Nemotron Nano 12B 2 VL
$0.27
150
Qwen3 235B A22B
$0.27
151
Llama 3.1 Nemotron Ultra 253B v1
$0.28
152
R1 Distill Llama 70B
$0.28
153
Llama 3 Euryale 70B v2.1
$0.28
154
MiniMax M2.5
$0.28
155
Qwen2.5 VL 32B Instruct
$0.28
156
Morph V3 Large
$0.28
157
Qwen3 Coder Next
$0.28
158
MiniMax M2.1
$0.29
159
Noromaid 20B
$0.29
160
Llama 3.1 Nemotron 70B Instruct
$0.30
161
Kimi Dev 72B
$0.30
162
GPT-3.5 Turbo (older v0613)
$0.31
163
Hermes 4 405B
$0.31
164
Qwen3 VL 32B Instruct
$0.31
165
GPT-3.5 Turbo Instruct
$0.31
166
Nova Pro 1.0
$0.32
167
Kimi K2 0711
$0.32
168
GLM 4.7 Flash
$0.33
169
Qwen3.5-Flash
$0.33
170
GLM 4.5V
$0.34
171
Mistral Medium 3.1
$0.35
172
Aion-2.0
$0.35
173
Gemini 3 Flash Preview
$0.35
174
GLM 4.6V
$0.37
175
CodeLLaMa 7B Instruct Solidity
$0.37
176
Olmo 3 32B Think
$0.38
177
Claude 3.5 Haiku
$0.40
178
MiniMax M2
$0.40
179
Olmo 3.1 32B Think
$0.41
180
Grok Code Fast 1
$0.45
181
Qwen3 VL 30B A3B Thinking
$0.45
182
GPT-5 Mini
$0.46
183
Gemini 2.5 Flash
$0.51
184
GLM 4.6 (exacto)
$0.51
185
Relace Search
$0.52
186
DeepSeek V3.2 Speciale
$0.53
187
Hermes 3 70B Instruct
$0.54
188
Nova 2 Lite
$0.56
189
Gemini 2.5 Flash Preview 09-2025
$0.57
190
MiniMax M1
$0.58
191
Switchpoint Router
$0.59
192
Cogito V2 Preview Llama 405B
$0.61
193
Seed 1.6
$0.61
194
Qwen3.5 Plus 2026-02-15
$0.62
195
Qwen VL Max
$0.62
196
Nano Banana (Gemini 2.5 Flash Image)
$0.63
197
Llama 3.1 70B Hanami x1
$0.63
198
Llemma 7b
$0.64
199
Qwen3 235B A22B Thinking 2507
$0.64
200
Step3
$0.64
201
Kimi K2 0905
$0.66
202
Mixtral 8x22B Instruct
$0.66
203
GPT-5.1 Chat
$0.73
204
GPT-5.1-Codex
$0.74
205
GLM 4.5
$0.74
206
Kimi K2 0905 (exacto)
$0.79
207
Qwen3 Coder Plus
$0.79
208
Miri
$0.82
209
Mistral Large 2411
$0.83
210
R1
$0.84
211
GPT-5 Image Mini
$0.86
212
Claude Haiku 4.5
$0.87
213
Palmyra X5
$0.91
214
Command A
$0.93
215
Mistral Large
$0.93
216
Mistral Large 2407
$0.94
217
Pixtral Large 2411
$0.95
218
GPT-4.1
$0.96
219
Command R+ (08-2024)
$0.99
220
Qwen3 Next 80B A3B Thinking
$1.00
221
Qwen-Max
$1.00
222
Qwen3.5-35B-A3B
$1.01
223
Inflection 3 Productivity
$1.01
224
Qwen3 Max
$1.02
225
Inflection 3 Pi
$1.02
226
Qwen3 Max Thinking
$1.04
227
GPT-4o
$1.05
228
GPT-4o (2024-08-06)
$1.06
229
Kimi K2 Thinking
$1.06
230
Qwen3.5 397B A17B
$1.08
231
SorcererLM 8x22B
$1.12
232
GPT-5 Chat
$1.12
233
Nova Premier 1.0
$1.14
234
GPT-5 Codex
$1.14
235
R1 0528
$1.14
236
GLM 4.6
$1.16
237
Qwen3 VL 235B A22B Thinking
$1.23
238
Goliath 120B
$1.26
239
GLM 4.7
$1.26
240
Sonar
$1.27
241
Qwen3 VL 8B Thinking
$1.32
242
o3 Mini High
$1.35
243
o3 Mini
$1.44
244
Kimi K2.5
$1.46
245
Qwen3.5-27B
$1.49
246
o4 Mini
$1.50
247
GPT-4o (2024-11-20)
$1.50
248
Qwen3.5-122B-A10B
$1.51
249
Morph V3 Fast
$1.58
250
Jamba Large 1.7
$1.71
251
GPT-5.2 Chat
$1.74
252
Qwen Plus 0728 (thinking)
$1.83
253
GPT-4o (2024-05-13)
$1.90
254
GPT-5.2-Codex
$2.06
255
GPT-5.2
$2.14
256
Aion-1.0
$2.17
257
ChatGPT-4o
$2.23
258
Claude Sonnet 4
$2.23
259
GPT-5.1
$2.29
260
o3
$2.29
261
GLM 5
$2.32
262
o4 Mini High
$2.33
263
Claude 3.7 Sonnet
$2.53
264
GPT-5
$2.56
265
Claude Sonnet 4.5
$2.64
266
Grok 3 Beta
$2.67
267
Claude Sonnet 4.6
$2.70
268
Grok 3
$2.78
269
GPT-5.1-Codex-Max
$3.09
270
Sonar Pro
$3.32
271
Claude 3.5 Sonnet
$3.34
272
Sonar Reasoning Pro
$3.49
273
GPT-5 Image
$3.95
274
Gemini 3.1 Pro Preview
$4.10
275
GPT-4 Turbo
$4.20
276
GPT-4 Turbo Preview
$4.42
277
Auto Router
$4.77
278
Claude Opus 4.5
$4.78
279
Grok 4
$5.04
280
Claude Opus 4.6
$5.09
281
Sonar Pro Search
$5.61
282
Nano Banana Pro (Gemini 3 Pro Image Preview)
$5.94
283
Gemini 2.5 Pro Preview 06-05
$6.06
284
Gemini 2.5 Pro
$6.09
285
Gemini 2.5 Pro Preview 05-06
$6.11
286
Gemini 3 Pro Preview
$6.38
287
GPT-4 (older v0314)
$7.96
288
Claude 3.7 Sonnet (thinking)
$8.35
289
GPT-4
$8.55
290
Claude Opus 4
$10.70
291
ALMA
$11.02
292
Claude Opus 4.1
$11.31
293
o3 Pro
$22.85
294
GPT-5.2 Pro
$26.07
295
o1
$27.26
296
o4 Mini Deep Research
$36.45
297
o3 Deep Research
$169.04
298
Sonar Deep Research
$234.22
299
o1-pro
$278.74
Total:$1070.62
Average:$3.58
(299 modelos)
Metrics menu
Reasoning Tokens
Tokens used in the reasoning process
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-5.3 Chat
26K
6
GPT-5.1-Codex
28K
7
DeepSeek V3.1 Terminus
33K
8
DeepSeek V3.2
39K
9
GPT-5.2 Pro
44K
10
GPT-5.2
44K
11
GPT-5.3-Codex
48K
12
GPT-5.1-Codex-Mini
53K
13
DeepSeek V3.2 Exp
57K
14
GLM 4.5V
58K
15
Qwen3.5 Plus 2026-02-15
61K
16
GPT-5 Codex
66K
17
ALMA
78K
18
Mercury 2
80K
19
gpt-oss-120b
81K
20
gpt-oss-120b (exacto)
83K
21
o3 Pro
88K
22
o3
91K
23
GPT-5.1
94K
24
GPT-5.2-Codex
94K
25
o3 Mini High
115K
26
gpt-oss-20b
121K
27
o3 Mini
124K
28
o4 Mini
125K
29
GLM 4.6 (exacto)
125K
30
gpt-oss-safeguard-20b
127K
31
Grok 4 Fast
130K
32
Nemotron Nano 9B V2
130K
33
MiniMax M2.5
136K
34
GPT-5 Mini
136K
35
GPT-5 Image Mini
141K
36
MiniMax M2.1
151K
37
GPT-5.4 Pro
152K
38
Grok Code Fast 1
154K
39
R1 Distill Llama 70B
160K
40
MiniMax M1
161K
41
GLM 4.5
163K
42
R1 Distill Qwen 32B
166K
43
GPT-5 Image
167K
44
R1
177K
45
Aion-2.0
178K
46
Qwen3 14B
178K
47
Kimi Dev 72B
178K
48
GPT-5
181K
49
Grok 4.1 Fast
181K
50
Free Models Router
182K
51
o1
185K
52
Grok 3 Mini
186K
53
Grok 3 Mini Beta
188K
54
o1-pro
189K
55
Seed 1.6
189K
56
Qwen3 32B
194K
57
Seed 1.6 Flash
195K
58
Qwen3 VL 235B A22B Thinking
198K
59
Grok 4
201K
60
Trinity Mini
217K
61
o4 Mini High
219K
62
Qwen3 235B A22B
226K
63
Qwen3 8B
234K
64
R1 0528
237K
65
Step3
242K
66
MiniMax M2
250K
67
GLM 4.6V
255K
68
GPT-5.1-Codex-Max
257K
69
Tongyi DeepResearch 30B A3B
262K
70
Llama 3.3 Nemotron Super 49B V1.5
269K
71
Kimi K2 Thinking
275K
72
Qwen3 30B A3B Thinking 2507
277K
73
Nano Banana Pro (Gemini 3 Pro Image Preview)
305K
74
Gemini 3.1 Pro Preview Custom Tools
306K
75
Qwen3 VL 30B A3B Thinking
311K
76
Qwen3 235B A22B Thinking 2507
315K
77
QwQ 32B
315K
78
Qwen Plus 0728 (thinking)
317K
79
Kimi K2.5
327K
80
Gemini 3.1 Pro Preview
330K
81
Solar Pro 3
333K
82
Nemotron Nano 12B 2 VL
348K
83
Claude 3.7 Sonnet (thinking)
348K
84
Qwen3.5 397B A17B
360K
85
Gemini 3 Pro Preview
364K
86
GPT-5 Nano
371K
87
GLM 4.6
383K
88
Seed-2.0-Mini
401K
89
Gemini 2.5 Pro Preview 06-05
406K
90
Gemini 2.5 Pro Preview 05-06
410K
91
Gemini 2.5 Pro
411K
92
Step 3.5 Flash
425K
93
DeepSeek V3.2 Speciale
437K
94
ERNIE 4.5 21B A3B Thinking
441K
95
GLM 4.7
468K
96
Qwen3.5-35B-A3B
473K
97
Qwen3.5-122B-A10B
474K
98
Step 3.5 Flash
489K
99
Qwen3 VL 8B Thinking
519K
100
Olmo 3 7B Think
547K
101
GLM 5
552K
102
Qwen3 Next 80B A3B Thinking
563K
103
Qwen3.5-27B
609K
104
Qwen3.5-Flash
652K
105
Olmo 3 32B Think
669K
106
GLM 4.7 Flash
682K
107
Olmo 3.1 32B Think
721K
108
Nemotron 3 Nano 30B A3B
727K
109
o4 Mini Deep Research
1.6M
110
o3 Deep Research
1.7M
111
Sonar Deep Research
68.0M
Total:97.5M
Average:878K
(111 modelos)
Metrics menu
Output Tokens
Tokens generated in responses
1
Qwen3 4B
0
2
Gemma 2 27B
47K
3
Mistral Nemo
54K
4
Voxtral Small 24B 2507
55K
5
Aion-1.0-Mini
56K
6
Ministral 3B
57K
7
GPT-5.1 Chat
61K
8
Lumimaid v0.2 8B
62K
9
GPT-5.1-Codex
62K
10
Gemma 2 9B
62K
11
Devstral Small 1.1
63K
12
GPT-3.5 Turbo 16k
63K
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
Llama 3 70B Instruct
72K
29
MythoMax 13B
73K
30
Cogito V2 Preview Llama 405B
73K
31
GPT-4o-mini (2024-07-18)
75K
32
Claude 3.5 Haiku
75K
33
GPT-4o-mini
76K
34
Command R+ (08-2024)
76K
35
Inflection 3 Productivity
77K
36
ReMM SLERP 13B
77K
37
Mistral Small 3.2 24B
78K
38
Saba
78K
39
Inflection 3 Pi
78K
40
Mixtral 8x22B Instruct
79K
41
Mistral 7B Instruct v0.1
79K
42
GPT-4o
81K
43
GPT-4o (2024-08-06)
81K
44
GPT-3.5 Turbo Instruct
83K
45
GPT-4 (older v0314)
83K
46
KAT-Coder-Pro V1
84K
47
Cogito v2.1 671B
84K
48
Mercury Coder
85K
49
Cogito V2 Preview Llama 70B
85K
50
Devstral Medium
85K
51
Aion-RP 1.0 (8B)
85K
52
DeepSeek V3
85K
53
Codestral 2508
85K
54
Mercury
86K
55
Claude 3 Haiku
86K
56
GPT-4.1 Nano
87K
57
Claude 3.5 Sonnet
87K
58
Command R (08-2024)
87K
59
Pixtral 12B
87K
60
GLM 4 32B
87K
61
Gemini 2.0 Flash
88K
62
Hermes 2 Pro - Llama-3 8B
88K
63
Hermes 4 70B
89K
64
DeepSeek V3 0324
89K
65
Noromaid 20B
89K
66
Llama 3 Euryale 70B v2.1
89K
67
Llama 3.1 70B Instruct
90K
68
Nova Lite 1.0
91K
69
UnslopNemo 12B
91K
70
Gemma 3 12B
91K
71
Kimi K2 0905
92K
72
GPT-4
93K
73
Kimi K2 0905 (exacto)
93K
74
Morph V3 Large
93K
75
Devstral 2 2512
94K
76
GPT-4o (2024-05-13)
94K
77
Gemini 2.0 Flash Lite
95K
78
Mixtral 8x7B Instruct
95K
79
Mistral Medium 3
95K
80
GPT-4.1
95K
81
Mistral 7B Instruct v0.2
95K
82
ERNIE 4.5 300B A47B
96K
83
Cydonia 24B V4.1
96K
84
Granite 4.0 Micro
96K
85
GPT-4o Search Preview
97K
86
Gemma 3 4B
97K
87
Mistral Large 2411
97K
88
Gemini 3 Flash Preview
98K
89
GPT-5.1-Codex-Mini
98K
90
GPT-4.1 Mini
99K
91
GPT-4 Turbo (older v1106)
99K
92
Gemma 3 27B
100K
93
GPT-4o-mini Search Preview
100K
94
GPT-5 Chat
100K
95
Sonar Pro Search
102K
96
GPT-5 Codex
102K
97
Gemini 3.1 Flash Lite Preview
102K
98
Trinity Large Preview
103K
99
Qwen2.5 VL 72B Instruct
104K
100
GPT-4 Turbo
104K
101
Llama 3.1 70B Hanami x1
105K
102
Goliath 120B
105K
103
LFM2-8B-A1B
105K
104
Jamba Mini 1.7
106K
105
GPT-5.4
107K
106
Qwen2.5-VL 7B Instruct
107K
107
Llama 4 Scout
107K
108
GPT-3.5 Turbo (older v0613)
109K
109
Molmo2 8B
109K
110
Hunyuan A13B Instruct
110K
111
Pixtral Large 2411
110K
112
Llama 3.3 70B Instruct
111K
113
Kimi K2 0711
112K
114
Llama 3.1 Euryale 70B v2.2
112K
115
Sonar
112K
116
GPT-5.2 Chat
112K
117
Llama 3.2 3B Instruct
113K
118
GPT-5.3-Codex
113K
119
Nova Micro 1.0
113K
120
Llama 4 Maverick
114K
121
Qwen2.5 72B Instruct
114K
122
GPT-4 Turbo Preview
114K
123
ERNIE 4.5 21B A3B
115K
124
Qwen-Turbo
116K
125
ChatGPT-4o
116K
126
SorcererLM 8x22B
116K
127
Sonar Pro
116K
128
Weaver (alpha)
117K
129
GPT-5.3 Chat
118K
130
Claude Opus 4
118K
131
Llama 3.3 Euryale 70B
119K
132
Solar Pro 3
119K
133
Llama 3.1 Nemotron Ultra 253B v1
120K
134
Qwen3 VL 235B A22B Instruct
120K
135
Qwen2.5 7B Instruct
120K
136
Llama 3.2 1B Instruct
121K
137
LFM2-24B-A2B
123K
138
Gemma 3n 4B
124K
139
Claude Sonnet 4
124K
140
Mistral Large
124K
141
Mistral Large 2407
125K
142
Qwen2.5 Coder 32B Instruct
125K
143
DeepSeek V3.1 Terminus (exacto)
126K
144
GPT-4o (2024-11-20)
126K
145
Claude Opus 4.1
126K
146
Rocinante 12B
127K
147
Mistral Large 3 2512
127K
148
Rnj 1 Instruct
131K
149
Qwen-Max
132K
150
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
133K
151
DeepSeek V3.1
133K
152
Phi 4
133K
153
Aurora Alpha
134K
154
GPT-5.2-Codex
135K
155
Qwen3 Coder 480B A35B
136K
156
Palmyra X5
137K
157
Qwen3 Coder Plus
138K
158
Qwen3 Coder 480B A35B (exacto)
139K
159
Llama 3 8B Instruct
139K
160
GPT-5.2
141K
161
Relace Search
141K
162
GPT-5.2 Pro
144K
163
Claude 3.7 Sonnet
144K
164
Qwen3 Coder 30B A3B Instruct
145K
165
Llama 3.1 Nemotron 70B Instruct
146K
166
Miri
147K
167
DeepSeek V3.1 Nex N1
148K
168
Claude Haiku 4.5
149K
169
Qwen3 Max
149K
170
ERNIE 4.5 VL 424B A47B
150K
171
DeepSeek V3.1 Terminus
150K
172
DeepSeek V3.2
151K
173
Claude Sonnet 4.5
151K
174
MiniMax M2-her
152K
175
Qwen3 Coder Flash
152K
176
Switchpoint Router
152K
177
Qwen3 Max Thinking
153K
178
Mistral Medium 3.1
154K
179
Qwen VL Plus
155K
180
Claude Sonnet 4.6
156K
181
GLM 4.5V
156K
182
Qwen3 Next 80B A3B Instruct
156K
183
DeepSeek V3.2 Exp
161K
184
Qwen VL Max
161K
185
Mercury 2
162K
186
Olmo 3.1 32B Instruct
163K
187
Ministral 3 14B 2512
164K
188
gpt-oss-120b
165K
189
gpt-oss-120b (exacto)
166K
190
Claude Opus 4.5
167K
191
Nano Banana (Gemini 2.5 Flash Image)
167K
192
Qwen3 235B A22B Instruct 2507
168K
193
Auto Router
168K
194
Ministral 3 3B 2512
168K
195
Aion-2.0
171K
196
o3 Mini High
171K
197
Grok 3
171K
198
Llama 3.2 11B Vision Instruct
171K
199
Grok 3 Beta
171K
200
o3
172K
201
Qwen3 VL 32B Instruct
172K
202
o3 Pro
173K
203
Qwen3 VL 8B Instruct
177K
204
Ministral 3 8B 2512
178K
205
Claude Opus 4.6
179K
206
o3 Mini
180K
207
Qwen Plus 0728
182K
208
Qwen-Plus
182K
209
Qwen3 30B A3B Instruct 2507
186K
210
Olmo 3 7B Instruct
187K
211
Jamba Large 1.7
187K
212
Gemini 2.5 Flash
187K
213
R1 Distill Llama 70B
187K
214
o4 Mini
192K
215
MiMo-V2-Flash
194K
216
MiniMax M2.5
200K
217
R1 Distill Qwen 32B
203K
218
gpt-oss-20b
205K
219
Gemini 2.5 Flash Lite
208K
220
Nova 2 Lite
213K
221
gpt-oss-safeguard-20b
213K
222
Gemini 2.5 Flash Preview 09-2025
214K
223
Qwen2.5 VL 32B Instruct
215K
224
Gemini 2.5 Flash Lite Preview 09-2025
217K
225
GPT-5.1
217K
226
GPT-5 Mini
217K
227
GPT-5 Image Mini
221K
228
Aion-1.0
223K
229
ERNIE 4.5 VL 28B A3B
224K
230
CodeLLaMa 7B Instruct Solidity
226K
231
GPT-5 Image
226K
232
Qwen3 VL 30B A3B Instruct
228K
233
GLM 4.6 (exacto)
228K
234
MiniMax M2.1
230K
235
MiMo-V2-Flash
231K
236
Llama 3.1 8B Instruct
234K
237
GLM 4.5 Air
236K
238
Kimi Dev 72B
238K
239
Qwen3 14B
241K
240
Qwen3.5 Plus 2026-02-15
242K
241
MiniMax M1
243K
242
Medgemma
243K
243
GPT-5
244K
244
o1
247K
245
GPT-5.4 Pro
249K
246
Sonar Reasoning Pro
252K
247
o1-pro
253K
248
Grok 4 Fast
254K
249
Free Models Router
255K
250
Nemotron Nano 9B V2
265K
251
Qwen3 Coder Next
271K
252
Seed 1.6 Flash
276K
253
Grok 4.1 Fast
280K
254
Qwen3 32B
280K
255
o4 Mini High
286K
256
Grok Code Fast 1
288K
257
Seed 1.6
289K
258
Qwen3 VL 235B A22B Thinking
296K
259
GPT-5.1-Codex-Max
297K
260
Qwen3 235B A22B
300K
261
R1
307K
262
Mistral Small Creative
309K
263
Qwen3 8B
310K
264
Grok 4
312K
265
MiniMax M2
315K
266
Trinity Mini
320K
267
Llama 3.3 Nemotron Super 49B V1.5
330K
268
GLM 4.5
339K
269
Tongyi DeepResearch 30B A3B
341K
270
ALMA
345K
271
Qwen3 30B A3B Thinking 2507
349K
272
Grok 3 Mini
351K
273
Grok 3 Mini Beta
357K
274
GLM 4.6V
375K
275
R1 0528
375K
276
QwQ 32B
387K
277
Nemotron Nano 12B 2 VL
396K
278
Kimi K2 Thinking
398K
279
Gemini 3.1 Pro Preview Custom Tools
408K
280
Step3
408K
281
Qwen3 VL 30B A3B Thinking
423K
282
Gemini 3.1 Pro Preview
432K
283
Qwen3 235B A22B Thinking 2507
441K
284
GPT-5 Nano
443K
285
Llemma 7b
446K
286
Qwen Plus 0728 (thinking)
447K
287
Nano Banana Pro (Gemini 3 Pro Image Preview)
479K
288
Seed-2.0-Mini
486K
289
Qwen3.5 397B A17B
489K
290
Kimi K2.5
497K
291
Solar Pro 3
513K
292
Gemini 3 Pro Preview
514K
293
GLM 4.6
514K
294
DeepSeek V3.2 Speciale
519K
295
Claude 3.7 Sonnet (thinking)
531K
296
Step 3.5 Flash
553K
297
ERNIE 4.5 21B A3B Thinking
585K
298
Gemini 2.5 Pro Preview 06-05
590K
299
Gemini 2.5 Pro Preview 05-06
596K
300
Gemini 2.5 Pro
597K
301
GLM 4.7
603K
302
Olmo 3 7B Think
613K
303
Qwen3.5-122B-A10B
614K
304
Qwen3 VL 8B Thinking
615K
305
Step 3.5 Flash
615K
306
Qwen3 Next 80B A3B Thinking
643K
307
GLM 5
705K
308
Olmo 3 32B Think
733K
309
Qwen3.5-35B-A3B
734K
310
Nemotron 3 Nano 30B A3B
743K
311
Qwen3.5-27B
757K
312
Olmo 3.1 32B Think
787K
313
GLM 4.7 Flash
796K
314
Qwen3.5-Flash
802K
315
Morph V3 Fast
1.2M
316
o4 Mini Deep Research
1.7M
317
Hermes 3 70B Instruct
1.7M
318
o3 Deep Research
1.8M
319
Sonar Deep Research
68.3M
Total:137.0M
Average:430K
(319 modelos)