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("Geirhos2021uniformnoise-top1")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.821
2
.818
3
.816
4
.805
5
.804
6
.799
7
.796
8
.791
9
.776
10
.772
11
.772
12
.765
13
.762
14
.757
15
.750
16
.743
17
.730
18
.724
19
.720
20
.708
21
.704
22
.701
23
.701
24
.701
25
.700
26
.696
27
.696
28
.693
29
.689
30
.686
31
.680
32
.674
33
.671
34
.670
35
.669
36
.657
37
.656
38
.656
39
.654
40
.650
41
.649
42
.647
43
.644
44
.644
45
.641
46
.641
47
.632
48
.632
49
.627
50
.627
51
.626
52
.621
53
.621
54
.618
55
.618
56
.618
57
.616
58
.616
59
.613
60
.604
61
.599
62
.595
63
.586
64
.579
65
.578
66
.575
67
.573
68
.571
69
.568
70
.561
71
.560
72
.560
73
.560
74
.560
75
.555
76
.554
77
.554
78
.551
79
.549
80
.547
81
.546
82
.542
83
.542
84
.540
85
.540
86
.535
87
.530
88
.530
89
.530
90
.524
91
.522
92
.516
93
.515
94
.514
95
.514
96
.511
97
.509
98
.507
99
.507
100
.506
101
.506
102
.506
103
.505
104
.505
105
.504
106
.504
107
.502
108
.502
109
.501
110
.501
111
.499
112
.499
113
.499
114
.497
115
.496
116
.496
117
.496
118
.490
119
.487
120
.486
121
.486
122
.486
123
.481
124
.481
125
.480
126
.479
127
.479
128
.477
129
.477
130
.476
131
.475
132
.475
133
.475
134
.472
135
.471
136
.469
137
.469
138
.468
139
.466
140
.464
141
.463
142
.461
143
.455
144
.453
145
.449
146
.449
147
.445
148
.445
149
.445
150
.445
151
.443
152
.443
153
.440
154
.440
155
.435
156
.430
157
.427
158
.427
159
.420
160
.417
161
.415
162
.414
163
.410
164
.410
165
.407
166
.406
167
.405
168
.405
169
.404
170
.404
171
.396
172
.395
173
.394
174
.393
175
.384
176
.383
177
.381
178
.380
179
.380
180
.375
181
.374
182
.372
183
.371
184
.369
185
.366
186
.366
187
.359
188
.357
189
.355
190
.351
191
.350
192
.350
193
.345
194
.345
195
.344
196
.343
197
.343
198
.343
199
.343
200
.341
201
.340
202
.340
203
.339
204
.339
205
.335
206
.330
207
.330
208
.330
209
.329
210
.329
211
.326
212
.324
213
.323
214
.319
215
.318
216
.318
217
.318
218
.316
219
.315
220
.314
221
.314
222
.311
223
.311
224
.310
225
.309
226
.307
227
.301
228
.300
229
.294
230
.292
231
.291
232
.291
233
.290
234
.287
235
.285
236
.284
237
.281
238
.273
239
.269
240
.269
241
.269
242
.269
243
.265
244
.259
245
.259
246
.258
247
.256
248
.255
249
.250
250
.247
251
.242
252
.231
253
.230
254
.229
255
.226
256
.221
257
.214
258
.212
259
.211
260
.201
261
.196
262
.194
263
.181
264
.180
265
.177
266
.177
267
.177
268
.177
269
.177
270
.158
271
.117
272
.090
273
.089
274
.087
275
.080
276
.077
277
.076
278
.072
279
.069
280
.066
281
.064
282
.062
283
.062
284
.062
285
.062
286
.062
287
.062
288
.062
289
.062
290
.062
291
.062
292
.062
293
.062
294
.062
295
.060
296
.060
297
.059
298
.058
299
.058
300
.058
301
.056
302
.051
303
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

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: Geirhos2021uniformnoise

Metric: top1