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
.895
2
.895
3
.894
4
.892
5
.883
6
.880
7
.880
8
.875
9
.873
10
.872
11
.856
12
.852
13
.850
14
.844
15
.836
16
.836
17
.833
18
.825
19
.822
20
.822
21
.819
22
.819
23
.817
24
.817
25
.809
26
.805
27
.803
28
.800
29
.791
30
.789
31
.786
32
.784
33
.781
34
.778
35
.770
36
.769
37
.767
38
.764
39
.761
40
.761
41
.753
42
.752
43
.750
44
.738
45
.727
46
.723
47
.719
48
.717
49
.713
50
.692
51
.691
52
.691
53
.689
54
.689
55
.689
56
.684
57
.680
58
.678
59
.678
60
.678
61
.675
62
.672
63
.670
64
.666
65
.666
66
.664
67
.661
68
.661
69
.661
70
.661
71
.659
72
.659
73
.658
74
.656
75
.656
76
.656
77
.655
78
.653
79
.653
80
.653
81
.653
82
.652
83
.652
84
.650
85
.650
86
.648
87
.648
88
.648
89
.647
90
.645
91
.645
92
.645
93
.644
94
.644
95
.644
96
.641
97
.641
98
.639
99
.639
100
.639
101
.637
102
.637
103
.636
104
.636
105
.636
106
.634
107
.633
108
.633
109
.633
110
.633
111
.633
112
.633
113
.631
114
.630
115
.630
116
.630
117
.628
118
.627
119
.627
120
.627
121
.627
122
.625
123
.625
124
.623
125
.622
126
.622
127
.620
128
.620
129
.620
130
.620
131
.620
132
.620
133
.620
134
.620
135
.620
136
.616
137
.616
138
.614
139
.614
140
.613
141
.613
142
.609
143
.608
144
.606
145
.606
146
.606
147
.606
148
.606
149
.605
150
.603
151
.602
152
.598
153
.597
154
.597
155
.597
156
.597
157
.595
158
.595
159
.595
160
.595
161
.595
162
.594
163
.594
164
.594
165
.594
166
.594
167
.594
168
.592
169
.592
170
.589
171
.589
172
.588
173
.588
174
.584
175
.584
176
.584
177
.583
178
.583
179
.580
180
.580
181
.578
182
.577
183
.577
184
.577
185
.577
186
.575
187
.573
188
.573
189
.573
190
.573
191
.573
192
.572
193
.572
194
.569
195
.567
196
.567
197
.567
198
.566
199
.564
200
.564
201
.562
202
.562
203
.559
204
.558
205
.556
206
.553
207
.553
208
.550
209
.550
210
.548
211
.545
212
.545
213
.544
214
.541
215
.539
216
.536
217
.533
218
.530
219
.530
220
.525
221
.523
222
.523
223
.522
224
.522
225
.520
226
.520
227
.520
228
.520
229
.520
230
.519
231
.517
232
.517
233
.516
234
.511
235
.511
236
.511
237
.511
238
.506
239
.505
240
.503
241
.503
242
.498
243
.498
244
.495
245
.494
246
.492
247
.491
248
.489
249
.484
250
.483
251
.481
252
.470
253
.470
254
.463
255
.463
256
.461
257
.461
258
.458
259
.458
260
.445
261
.445
262
.436
263
.430
264
.427
265
.420
266
.417
267
.412
268
.406
269
.398
270
.378
271
.372
272
.323
273
.286
274
.109
275
.105
276
.098
277
.097
278
.086
279
.083
280
.080
281
.073
282
.069
283
.067
284
.064
285
.064
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
.062
299
.061
300
.061
301
.059
302
.059
303
.041
304
.037
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: Geirhos2021phasescrambling

Metric: top1