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("Geirhos2021rotation-top1")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.989
2
.986
3
.985
4
.983
5
.979
6
.977
7
.976
8
.975
9
.969
10
.969
11
.966
12
.966
13
.965
14
.964
15
.960
16
.955
17
.954
18
.953
19
.951
20
.945
21
.945
22
.930
23
.923
24
.922
25
.919
26
.915
27
.907
28
.904
29
.903
30
.898
31
.896
32
.896
33
.895
34
.892
35
.891
36
.886
37
.886
38
.885
39
.882
40
.876
41
.865
42
.864
43
.864
44
.855
45
.849
46
.846
47
.840
48
.836
49
.835
50
.833
51
.832
52
.829
53
.820
54
.799
55
.797
56
.796
57
.795
58
.795
59
.793
60
.787
61
.782
62
.780
63
.779
64
.778
65
.778
66
.777
67
.776
68
.772
69
.771
70
.767
71
.766
72
.765
73
.764
74
.764
75
.760
76
.758
77
.757
78
.752
79
.752
80
.750
81
.745
82
.743
83
.742
84
.742
85
.738
86
.736
87
.736
88
.734
89
.733
90
.733
91
.729
92
.729
93
.729
94
.729
95
.727
96
.727
97
.727
98
.726
99
.725
100
.725
101
.725
102
.724
103
.723
104
.722
105
.720
106
.720
107
.720
108
.719
109
.719
110
.719
111
.718
112
.718
113
.713
114
.709
115
.707
116
.705
117
.704
118
.703
119
.702
120
.701
121
.701
122
.699
123
.698
124
.697
125
.696
126
.695
127
.695
128
.694
129
.693
130
.692
131
.692
132
.691
133
.691
134
.691
135
.690
136
.690
137
.689
138
.689
139
.685
140
.684
141
.684
142
.684
143
.684
144
.684
145
.684
146
.680
147
.679
148
.678
149
.678
150
.678
151
.676
152
.676
153
.674
154
.673
155
.672
156
.671
157
.670
158
.669
159
.668
160
.667
161
.666
162
.665
163
.665
164
.665
165
.662
166
.662
167
.662
168
.661
169
.661
170
.660
171
.657
172
.656
173
.655
174
.655
175
.655
176
.655
177
.654
178
.654
179
.651
180
.651
181
.648
182
.648
183
.647
184
.645
185
.644
186
.641
187
.640
188
.635
189
.634
190
.633
191
.633
192
.632
193
.631
194
.630
195
.629
196
.627
197
.626
198
.625
199
.624
200
.623
201
.622
202
.622
203
.618
204
.617
205
.613
206
.613
207
.603
208
.602
209
.601
210
.600
211
.596
212
.594
213
.593
214
.592
215
.592
216
.591
217
.583
218
.583
219
.580
220
.575
221
.574
222
.573
223
.570
224
.570
225
.569
226
.564
227
.561
228
.561
229
.561
230
.561
231
.560
232
.555
233
.544
234
.544
235
.543
236
.536
237
.528
238
.525
239
.523
240
.523
241
.523
242
.520
243
.519
244
.518
245
.517
246
.515
247
.511
248
.502
249
.497
250
.490
251
.489
252
.487
253
.482
254
.482
255
.482
256
.482
257
.482
258
.459
259
.451
260
.447
261
.440
262
.435
263
.425
264
.420
265
.406
266
.405
267
.399
268
.391
269
.355
270
.354
271
.354
272
.354
273
.354
274
.346
275
.297
276
.145
277
.122
278
.079
279
.077
280
.074
281
.074
282
.074
283
.072
284
.071
285
.068
286
.068
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
.060
300
.060
301
.059
302
.056
303
.054
304
.049
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
464
465
466

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: Geirhos2021rotation

Metric: top1