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
.897
2
.874
3
.873
4
.846
5
.830
6
.821
7
.818
8
.816
9
.811
10
.805
11
.804
12
.801
13
.799
14
.796
15
.792
16
.791
17
.776
18
.776
19
.772
20
.772
21
.765
22
.762
23
.757
24
.750
25
.749
26
.743
27
.743
28
.730
29
.724
30
.720
31
.708
32
.704
33
.701
34
.701
35
.701
36
.700
37
.696
38
.696
39
.693
40
.689
41
.686
42
.680
43
.674
44
.671
45
.670
46
.669
47
.657
48
.656
49
.656
50
.654
51
.650
52
.649
53
.647
54
.644
55
.644
56
.641
57
.641
58
.632
59
.632
60
.627
61
.627
62
.626
63
.621
64
.621
65
.618
66
.618
67
.618
68
.616
69
.616
70
.613
71
.604
72
.599
73
.595
74
.586
75
.579
76
.578
77
.575
78
.573
79
.571
80
.568
81
.561
82
.560
83
.560
84
.560
85
.560
86
.555
87
.554
88
.554
89
.551
90
.549
91
.547
92
.546
93
.542
94
.542
95
.540
96
.540
97
.535
98
.530
99
.530
100
.530
101
.524
102
.522
103
.516
104
.515
105
.514
106
.511
107
.511
108
.507
109
.507
110
.506
111
.506
112
.505
113
.505
114
.504
115
.501
116
.501
117
.499
118
.499
119
.499
120
.497
121
.496
122
.496
123
.496
124
.490
125
.487
126
.486
127
.486
128
.486
129
.481
130
.481
131
.480
132
.479
133
.479
134
.477
135
.476
136
.475
137
.475
138
.471
139
.469
140
.469
141
.468
142
.466
143
.464
144
.463
145
.461
146
.455
147
.453
148
.449
149
.449
150
.445
151
.445
152
.445
153
.445
154
.443
155
.443
156
.440
157
.440
158
.435
159
.430
160
.427
161
.427
162
.420
163
.417
164
.415
165
.414
166
.410
167
.410
168
.407
169
.406
170
.405
171
.405
172
.404
173
.404
174
.396
175
.395
176
.394
177
.393
178
.384
179
.383
180
.381
181
.380
182
.380
183
.375
184
.374
185
.372
186
.371
187
.369
188
.366
189
.366
190
.359
191
.357
192
.355
193
.351
194
.350
195
.350
196
.345
197
.345
198
.344
199
.343
200
.343
201
.343
202
.343
203
.341
204
.340
205
.340
206
.339
207
.339
208
.335
209
.330
210
.330
211
.330
212
.329
213
.329
214
.326
215
.324
216
.323
217
.319
218
.318
219
.318
220
.318
221
.316
222
.315
223
.314
224
.314
225
.311
226
.311
227
.310
228
.309
229
.307
230
.301
231
.300
232
.294
233
.292
234
.291
235
.291
236
.290
237
.287
238
.285
239
.284
240
.281
241
.273
242
.269
243
.269
244
.269
245
.269
246
.265
247
.259
248
.259
249
.258
250
.256
251
.255
252
.250
253
.247
254
.242
255
.231
256
.230
257
.229
258
.226
259
.221
260
.214
261
.212
262
.211
263
.201
264
.196
265
.194
266
.181
267
.180
268
.177
269
.177
270
.177
271
.177
272
.177
273
.158
274
.117
275
.090
276
.089
277
.087
278
.080
279
.077
280
.076
281
.072
282
.069
283
.066
284
.064
285
.062
286
.062
287
.062
288
.062
289
.062
290
.062
291
.062
292
.062
293
.062
294
.062
295
.062
296
.060
297
.060
298
.059
299
.058
300
.058
301
.058
302
.056
303
.051
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
461

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