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
.756
3
.731
4
.725
5
.719
6
.719
7
.719
8
.713
9
.706
10
.700
11
.694
12
.681
13
.681
14
.669
15
.662
16
.662
17
.656
18
.656
19
.656
20
.650
21
.650
22
.644
23
.637
24
.637
25
.637
26
.631
27
.631
28
.631
29
.631
30
.625
31
.625
32
.613
33
.613
34
.606
35
.606
36
.606
37
.600
38
.600
39
.600
40
.600
41
.600
42
.600
43
.600
44
.600
45
.600
46
.600
47
.594
48
.588
49
.588
50
.581
51
.581
52
.581
53
.575
54
.575
55
.575
56
.569
57
.569
58
.569
59
.569
60
.562
61
.562
62
.562
63
.562
64
.562
65
.562
66
.556
67
.556
68
.556
69
.556
70
.556
71
.550
72
.550
73
.550
74
.550
75
.550
76
.550
77
.550
78
.550
79
.550
80
.550
81
.550
82
.550
83
.550
84
.544
85
.544
86
.544
87
.544
88
.544
89
.544
90
.544
91
.544
92
.544
93
.544
94
.544
95
.544
96
.544
97
.544
98
.537
99
.537
100
.537
101
.537
102
.537
103
.537
104
.537
105
.537
106
.537
107
.531
108
.531
109
.531
110
.525
111
.525
112
.525
113
.525
114
.525
115
.525
116
.525
117
.525
118
.525
119
.525
120
.519
121
.519
122
.519
123
.519
124
.519
125
.519
126
.519
127
.519
128
.519
129
.519
130
.519
131
.519
132
.519
133
.512
134
.512
135
.512
136
.512
137
.512
138
.512
139
.512
140
.512
141
.512
142
.506
143
.506
144
.506
145
.506
146
.506
147
.506
148
.506
149
.506
150
.506
151
.506
152
.500
153
.500
154
.494
155
.494
156
.494
157
.494
158
.494
159
.494
160
.487
161
.487
162
.487
163
.487
164
.487
165
.487
166
.481
167
.481
168
.481
169
.481
170
.481
171
.481
172
.481
173
.481
174
.475
175
.475
176
.475
177
.475
178
.475
179
.475
180
.469
181
.469
182
.463
183
.463
184
.463
185
.463
186
.456
187
.456
188
.456
189
.450
190
.450
191
.450
192
.450
193
.450
194
.450
195
.450
196
.450
197
.450
198
.450
199
.450
200
.444
201
.444
202
.438
203
.438
204
.438
205
.431
206
.431
207
.431
208
.431
209
.431
210
.431
211
.431
212
.431
213
.431
214
.431
215
.425
216
.419
217
.419
218
.412
219
.412
220
.412
221
.406
222
.400
223
.400
224
.400
225
.400
226
.394
227
.394
228
.394
229
.394
230
.394
231
.388
232
.381
233
.375
234
.375
235
.375
236
.375
237
.369
238
.369
239
.369
240
.369
241
.369
242
.362
243
.362
244
.356
245
.356
246
.350
247
.344
248
.344
249
.344
250
.338
251
.338
252
.338
253
.331
254
.331
255
.331
256
.325
257
.325
258
.325
259
.319
260
.319
261
.306
262
.294
263
.294
264
.287
265
.263
266
.263
267
.250
268
.244
269
.237
270
.219
271
.156
272
.125
273
.125
274
.119
275
.113
276
.113
277
.106
278
.094
279
.087
280
.081
281
.081
282
.075
283
.075
284
.062
285
.062
286
.062
287
.062
288
.062
289
.062
290
.062
291
.062
292
.062
293
.062
294
.062
295
.062
296
.062
297
.056
298
.056
299
.056
300
.050
301
.044
302
.037
303
.006
304
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

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