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("Geirhos2021phasescrambling-top1")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.945
2
.944
3
.934
4
.933
5
.928
6
.911
7
.895
8
.895
9
.894
10
.892
11
.883
12
.881
13
.880
14
.880
15
.875
16
.873
17
.873
18
.872
19
.864
20
.856
21
.852
22
.850
23
.844
24
.836
25
.836
26
.833
27
.830
28
.825
29
.822
30
.822
31
.819
32
.819
33
.817
34
.817
35
.814
36
.809
37
.805
38
.803
39
.800
40
.791
41
.789
42
.786
43
.784
44
.781
45
.778
46
.770
47
.769
48
.767
49
.764
50
.761
51
.761
52
.753
53
.752
54
.750
55
.738
56
.727
57
.723
58
.719
59
.717
60
.713
61
.692
62
.691
63
.691
64
.689
65
.689
66
.689
67
.684
68
.680
69
.678
70
.678
71
.678
72
.675
73
.672
74
.670
75
.666
76
.666
77
.664
78
.661
79
.661
80
.661
81
.661
82
.659
83
.659
84
.658
85
.656
86
.656
87
.656
88
.655
89
.653
90
.653
91
.653
92
.653
93
.652
94
.652
95
.650
96
.650
97
.648
98
.648
99
.648
100
.647
101
.645
102
.645
103
.644
104
.644
105
.644
106
.641
107
.641
108
.639
109
.639
110
.639
111
.637
112
.636
113
.636
114
.636
115
.633
116
.633
117
.633
118
.633
119
.633
120
.633
121
.631
122
.630
123
.630
124
.628
125
.627
126
.627
127
.627
128
.625
129
.625
130
.623
131
.623
132
.622
133
.622
134
.620
135
.620
136
.620
137
.620
138
.620
139
.620
140
.620
141
.616
142
.616
143
.614
144
.614
145
.613
146
.613
147
.609
148
.608
149
.606
150
.606
151
.606
152
.606
153
.605
154
.602
155
.598
156
.597
157
.597
158
.597
159
.597
160
.595
161
.595
162
.595
163
.595
164
.595
165
.594
166
.594
167
.594
168
.594
169
.594
170
.594
171
.592
172
.592
173
.589
174
.589
175
.588
176
.588
177
.584
178
.584
179
.584
180
.583
181
.583
182
.580
183
.580
184
.578
185
.577
186
.577
187
.577
188
.577
189
.575
190
.573
191
.573
192
.573
193
.573
194
.573
195
.572
196
.572
197
.569
198
.567
199
.567
200
.567
201
.566
202
.564
203
.564
204
.562
205
.562
206
.559
207
.558
208
.556
209
.553
210
.553
211
.550
212
.550
213
.548
214
.545
215
.545
216
.544
217
.541
218
.539
219
.536
220
.533
221
.530
222
.530
223
.525
224
.523
225
.523
226
.522
227
.522
228
.520
229
.520
230
.520
231
.520
232
.520
233
.519
234
.517
235
.517
236
.516
237
.511
238
.511
239
.511
240
.511
241
.506
242
.505
243
.503
244
.503
245
.498
246
.498
247
.495
248
.494
249
.492
250
.491
251
.489
252
.484
253
.483
254
.481
255
.470
256
.470
257
.463
258
.463
259
.461
260
.461
261
.458
262
.458
263
.445
264
.445
265
.436
266
.430
267
.427
268
.420
269
.417
270
.412
271
.406
272
.398
273
.378
274
.372
275
.323
276
.286
277
.109
278
.105
279
.098
280
.097
281
.086
282
.083
283
.080
284
.073
285
.069
286
.067
287
.064
288
.062
289
.062
290
.062
291
.062
292
.062
293
.062
294
.062
295
.062
296
.062
297
.062
298
.062
299
.062
300
.062
301
.061
302
.059
303
.059
304
.041
305
.037
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: Geirhos2021phasescrambling

Metric: top1