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("Geirhos2021silhouette-top1")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.800
2
.794
3
.756
4
.731
5
.731
6
.725
7
.719
8
.719
9
.719
10
.719
11
.713
12
.713
13
.713
14
.706
15
.700
16
.700
17
.694
18
.694
19
.688
20
.688
21
.681
22
.681
23
.669
24
.662
25
.662
26
.662
27
.656
28
.656
29
.656
30
.650
31
.650
32
.650
33
.644
34
.637
35
.637
36
.637
37
.631
38
.631
39
.631
40
.631
41
.625
42
.625
43
.613
44
.613
45
.606
46
.606
47
.606
48
.600
49
.600
50
.600
51
.600
52
.600
53
.600
54
.600
55
.600
56
.600
57
.600
58
.594
59
.588
60
.588
61
.581
62
.581
63
.581
64
.575
65
.575
66
.575
67
.569
68
.569
69
.569
70
.569
71
.562
72
.562
73
.562
74
.562
75
.562
76
.562
77
.556
78
.556
79
.556
80
.556
81
.550
82
.550
83
.550
84
.550
85
.550
86
.550
87
.550
88
.550
89
.550
90
.550
91
.550
92
.550
93
.544
94
.544
95
.544
96
.544
97
.544
98
.544
99
.544
100
.544
101
.544
102
.544
103
.544
104
.544
105
.544
106
.544
107
.537
108
.537
109
.537
110
.537
111
.537
112
.537
113
.537
114
.531
115
.531
116
.531
117
.525
118
.525
119
.525
120
.525
121
.525
122
.525
123
.525
124
.525
125
.525
126
.525
127
.519
128
.519
129
.519
130
.519
131
.519
132
.519
133
.519
134
.519
135
.519
136
.519
137
.519
138
.519
139
.519
140
.512
141
.512
142
.512
143
.512
144
.512
145
.512
146
.512
147
.512
148
.512
149
.506
150
.506
151
.506
152
.506
153
.506
154
.506
155
.506
156
.506
157
.500
158
.500
159
.494
160
.494
161
.494
162
.494
163
.494
164
.487
165
.487
166
.487
167
.487
168
.487
169
.481
170
.481
171
.481
172
.481
173
.481
174
.481
175
.481
176
.481
177
.475
178
.475
179
.475
180
.475
181
.475
182
.475
183
.469
184
.469
185
.463
186
.463
187
.463
188
.463
189
.456
190
.456
191
.456
192
.450
193
.450
194
.450
195
.450
196
.450
197
.450
198
.450
199
.450
200
.450
201
.450
202
.450
203
.444
204
.444
205
.438
206
.438
207
.438
208
.431
209
.431
210
.431
211
.431
212
.431
213
.431
214
.431
215
.431
216
.431
217
.431
218
.425
219
.419
220
.419
221
.412
222
.412
223
.412
224
.406
225
.400
226
.400
227
.400
228
.400
229
.394
230
.394
231
.394
232
.394
233
.394
234
.388
235
.381
236
.375
237
.375
238
.375
239
.375
240
.369
241
.369
242
.369
243
.369
244
.369
245
.362
246
.362
247
.356
248
.356
249
.350
250
.344
251
.344
252
.344
253
.338
254
.338
255
.338
256
.331
257
.331
258
.331
259
.325
260
.325
261
.325
262
.319
263
.319
264
.306
265
.294
266
.294
267
.287
268
.263
269
.263
270
.250
271
.244
272
.237
273
.219
274
.156
275
.125
276
.125
277
.119
278
.113
279
.113
280
.106
281
.087
282
.081
283
.081
284
.075
285
.075
286
.062
287
.062
288
.062
289
.062
290
.062
291
.062
292
.062
293
.062
294
.062
295
.062
296
.062
297
.062
298
.056
299
.056
300
.056
301
.050
302
.044
303
.037
304
.006
305
306
307
308
309
310
311
312
313
314
315
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
459
460
461
462
463

Benchmark bibtex

@article{geirhos2021partial,
              title={Partial success in closing the gap between human and machine vision},
              author={Geirhos, Robert and Narayanappa, Kantharaju and Mitzkus, Benjamin and Thieringer, Tizian and Bethge, Matthias and Wichmann, Felix A and Brendel, Wieland},
              journal={Advances in Neural Information Processing Systems},
              volume={34},
              year={2021},
              url={https://openreview.net/forum?id=QkljT4mrfs}
        }

Ceiling

1.00.

Note that scores are relative to this ceiling.

Data: Geirhos2021silhouette

Metric: top1