Sample stimuli

sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9

How to use

from brainscore_vision import load_benchmark
benchmark = load_benchmark("ImageNet-top1")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.876
2
.863
3
.862
4
.857
5
.854
6
.854
7
.854
8
.853
9
.852
10
.851
11
.851
12
.850
13
.845
14
.845
15
.842
16
.841
17
.839
18
.835
19
.829
20
.828
21
.828
22
.827
23
.827
24
.824
25
.822
26
.809
27
.809
28
.805
29
.805
30
.804
31
.802
32
.799
33
.798
34
.795
35
.793
36
.792
37
.792
38
.792
39
.790
40
.783
41
.781
42
.780
43
.780
44
.778
45
.777
46
.777
47
.777
48
.776
49
.775
50
.774
51
.774
52
.772
53
.772
54
.768
55
.767
56
.766
57
.766
58
.764
59
.764
60
.762
61
.761
62
.760
63
.759
64
.758
65
.758
66
.758
67
.757
68
.756
69
.752
70
.752
71
.751
72
.751
73
.750
74
.750
75
.750
76
.749
77
.749
78
.749
79
.748
80
.747
81
.746
82
.745
83
.745
84
.744
85
.744
86
.744
87
.741
88
.740
89
.740
90
.739
91
.739
92
.739
93
.739
94
.736
95
.735
96
.735
97
.733
98
.733
99
.732
100
.732
101
.732
102
.732
103
.732
104
.732
105
.731
106
.730
107
.730
108
.729
109
.729
110
.728
111
.728
112
.726
113
.726
114
.724
115
.723
116
.722
117
.722
118
.722
119
.722
120
.720
121
.718
122
.718
123
.718
124
.718
125
.718
126
.718
127
.715
128
.715
129
.711
130
.709
131
.708
132
.708
133
.707
134
.706
135
.705
136
.704
137
.704
138
.704
139
.703
140
.703
141
.703
142
.702
143
.702
144
.702
145
.702
146
.702
147
.702
148
.702
149
.701
150
.700
151
.699
152
.698
153
.698
154
.698
155
.697
156
.697
157
.694
158
.692
159
.688
160
.687
161
.687
162
.684
163
.684
164
.684
165
.682
166
.681
167
.680
168
.675
169
.675
170
.672
171
.671
172
.670
173
.670
174
.670
175
.664
176
.663
177
.662
178
.654
179
.653
180
.653
181
.653
182
.652
183
.648
184
.648
185
.648
186
.648
187
.648
188
.647
189
.646
190
.646
191
.645
192
.645
193
.645
194
.645
195
.645
196
.644
197
.644
198
.644
199
.644
200
.644
201
.644
202
.644
203
.644
204
.643
205
.642
206
.642
207
.641
208
.641
209
.641
210
.641
211
.640
212
.639
213
.633
214
.632
215
.630
216
.628
217
.622
218
.621
219
.617
220
.616
221
.616
222
.615
223
.610
224
.603
225
.603
226
.602
227
.592
228
.591
229
.588
230
.583
231
.582
232
.577
233
.575
234
.575
235
.575
236
.568
237
.566
238
.563
239
.557
240
.548
241
.538
242
.538
243
.535
244
.534
245
.534
246
.534
247
.534
248
.534
249
.533
250
.533
251
.533
252
.533
253
.533
254
.532
255
.526
256
.519
257
.519
258
.519
259
.519
260
.519
261
.512
262
.508
263
.507
264
.500
265
.498
266
.477
267
.476
268
.471
269
.470
270
.470
271
.463
272
.455
273
.455
274
.437
275
.419
276
.415
277
.414
278
.413
279
.403
280
.402
281
.399
282
.360
283
.355
284
.340
285
.340
286
.340
287
.340
288
.293
289
.283
290
.260
291
.039
292
.019
293
.007
294
.007
295
.005
296
.002
297
.001
298
.001
299
.001
300
.001
301
.001
302
.001
303
.001
304
.001
305
.001
306
.001
307
.001
308
.001
309
.001
310
.001
311
.001
312
.001
313
.001
314
.001
315
.001
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458

Benchmark bibtex

@INPROCEEDINGS{5206848,  
                                                author={J. {Deng} and W. {Dong} and R. {Socher} and L. {Li} and  {Kai Li} and  {Li Fei-Fei}},  
                                                booktitle={2009 IEEE Conference on Computer Vision and Pattern Recognition},   
                                                title={ImageNet: A large-scale hierarchical image database},   
                                                year={2009},  
                                                volume={},  
                                                number={},  
                                                pages={248-255},
                                            }

Ceiling

1.00.

Note that scores are relative to this ceiling.

Data: ImageNet

Metric: top1