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-error_consistency")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.734
2
.730
3
.677
4
.624
5
.621
6
.612
7
.606
8
.600
9
.599
10
.596
11
.584
12
.576
13
.576
14
.572
15
.567
16
.562
17
.561
18
.521
19
.512
20
.511
21
.511
22
.506
23
.503
24
.499
25
.478
26
.462
27
.459
28
.448
29
.442
30
.431
31
.419
32
.416
33
.404
34
.404
35
.383
36
.382
37
.378
38
.376
39
.372
40
.367
41
.364
42
.363
43
.363
44
.361
45
.350
46
.347
47
.344
48
.342
49
.339
50
.338
51
.331
52
.320
53
.312
54
.308
55
.307
56
.289
57
.289
58
.289
59
.286
60
.273
61
.269
62
.268
63
.267
64
.256
65
.251
66
.250
67
.250
68
.250
69
.249
70
.247
71
.246
72
.223
73
.222
74
.222
75
.219
76
.214
77
.210
78
.209
79
.207
80
.202
81
.195
82
.192
83
.189
84
.183
85
.182
86
.181
87
.179
88
.177
89
.170
90
.168
91
.165
92
.162
93
.161
94
.161
95
.161
96
.159
97
.158
98
.156
99
.154
100
.153
101
.153
102
.151
103
.150
104
.148
105
.147
106
.146
107
.145
108
.145
109
.144
110
.142
111
.141
112
.139
113
.138
114
.137
115
.134
116
.134
117
.133
118
.130
119
.129
120
.129
121
.125
122
.123
123
.123
124
.121
125
.120
126
.120
127
.119
128
.118
129
.118
130
.118
131
.118
132
.116
133
.114
134
.114
135
.114
136
.114
137
.114
138
.114
139
.112
140
.112
141
.111
142
.111
143
.110
144
.110
145
.109
146
.108
147
.108
148
.107
149
.107
150
.107
151
.107
152
.107
153
.104
154
.101
155
.101
156
.100
157
.100
158
.097
159
.094
160
.094
161
.094
162
.094
163
.093
164
.091
165
.091
166
.091
167
.090
168
.090
169
.089
170
.089
171
.087
172
.084
173
.084
174
.083
175
.083
176
.081
177
.081
178
.080
179
.080
180
.080
181
.080
182
.079
183
.079
184
.079
185
.077
186
.076
187
.075
188
.074
189
.073
190
.069
191
.069
192
.069
193
.068
194
.067
195
.067
196
.066
197
.066
198
.066
199
.063
200
.060
201
.060
202
.060
203
.060
204
.060
205
.060
206
.060
207
.060
208
.060
209
.060
210
.060
211
.060
212
.060
213
.060
214
.060
215
.060
216
.060
217
.060
218
.059
219
.059
220
.057
221
.057
222
.055
223
.055
224
.054
225
.052
226
.052
227
.051
228
.051
229
.051
230
.051
231
.050
232
.049
233
.048
234
.048
235
.048
236
.047
237
.047
238
.045
239
.045
240
.044
241
.044
242
.043
243
.043
244
.042
245
.041
246
.041
247
.040
248
.040
249
.037
250
.034
251
.033
252
.033
253
.033
254
.032
255
.032
256
.031
257
.031
258
.030
259
.030
260
.029
261
.029
262
.029
263
.029
264
.029
265
.028
266
.028
267
.027
268
.027
269
.025
270
.024
271
.023
272
.023
273
.023
274
.022
275
.022
276
.020
277
.019
278
.019
279
.019
280
.018
281
.018
282
.017
283
.017
284
.016
285
.016
286
.015
287
.014
288
.013
289
.013
290
.012
291
.012
292
.011
293
.010
294
.009
295
.008
296
.007
297
.007
298
.006
299
.006
300
.006
301
.005
302
.005
303
.005
304
.003
305
.003
306
.002
307
.001
308
.001
309
.001
310
.001
311
.000
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

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

0.45.

Note that scores are relative to this ceiling.

Data: Geirhos2021phasescrambling

Metric: error_consistency