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-error_consistency")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.781
2
.754
3
.743
4
.734
5
.731
6
.730
7
.728
8
.723
9
.720
10
.719
11
.686
12
.685
13
.675
14
.674
15
.672
16
.670
17
.661
18
.652
19
.647
20
.647
21
.645
22
.639
23
.637
24
.635
25
.630
26
.627
27
.627
28
.626
29
.619
30
.617
31
.616
32
.614
33
.604
34
.601
35
.601
36
.599
37
.591
38
.590
39
.587
40
.583
41
.580
42
.577
43
.576
44
.576
45
.572
46
.555
47
.537
48
.537
49
.524
50
.522
51
.521
52
.520
53
.520
54
.515
55
.513
56
.509
57
.499
58
.493
59
.493
60
.481
61
.476
62
.475
63
.473
64
.472
65
.462
66
.458
67
.455
68
.447
69
.443
70
.441
71
.418
72
.410
73
.404
74
.401
75
.388
76
.386
77
.381
78
.377
79
.356
80
.354
81
.354
82
.350
83
.348
84
.344
85
.340
86
.338
87
.330
88
.328
89
.322
90
.317
91
.313
92
.309
93
.309
94
.309
95
.291
96
.289
97
.289
98
.285
99
.284
100
.282
101
.279
102
.272
103
.266
104
.265
105
.262
106
.260
107
.257
108
.257
109
.254
110
.253
111
.250
112
.250
113
.249
114
.248
115
.245
116
.244
117
.243
118
.231
119
.231
120
.224
121
.219
122
.209
123
.209
124
.202
125
.196
126
.194
127
.194
128
.194
129
.194
130
.194
131
.193
132
.188
133
.188
134
.183
135
.182
136
.180
137
.179
138
.174
139
.173
140
.172
141
.172
142
.166
143
.162
144
.162
145
.157
146
.157
147
.156
148
.153
149
.149
150
.144
151
.143
152
.137
153
.136
154
.134
155
.133
156
.132
157
.131
158
.130
159
.130
160
.130
161
.130
162
.130
163
.129
164
.127
165
.127
166
.125
167
.122
168
.121
169
.121
170
.121
171
.119
172
.119
173
.118
174
.116
175
.112
176
.105
177
.105
178
.103
179
.102
180
.101
181
.099
182
.098
183
.097
184
.091
185
.090
186
.089
187
.089
188
.089
189
.088
190
.088
191
.088
192
.088
193
.088
194
.088
195
.080
196
.079
197
.079
198
.078
199
.078
200
.078
201
.077
202
.076
203
.075
204
.075
205
.075
206
.073
207
.073
208
.071
209
.069
210
.068
211
.068
212
.067
213
.067
214
.067
215
.064
216
.062
217
.061
218
.061
219
.061
220
.059
221
.059
222
.058
223
.058
224
.058
225
.057
226
.057
227
.057
228
.057
229
.057
230
.056
231
.056
232
.054
233
.054
234
.050
235
.049
236
.049
237
.049
238
.049
239
.048
240
.048
241
.048
242
.048
243
.047
244
.047
245
.047
246
.046
247
.046
248
.046
249
.046
250
.046
251
.045
252
.045
253
.045
254
.044
255
.044
256
.043
257
.043
258
.041
259
.041
260
.040
261
.039
262
.039
263
.038
264
.038
265
.038
266
.038
267
.038
268
.038
269
.038
270
.036
271
.036
272
.036
273
.036
274
.036
275
.035
276
.034
277
.034
278
.033
279
.033
280
.031
281
.031
282
.030
283
.028
284
.027
285
.027
286
.026
287
.024
288
.024
289
.023
290
.023
291
.022
292
.022
293
.022
294
.022
295
.021
296
.021
297
.020
298
.017
299
.016
300
.016
301
.014
302
.013
303
.012
304
.011
305
.011
306
.011
307
.010
308
.010
309
.009
310
.008
311
.006
312
.006
313
.006
314
.005
315
.005
316
.005
317
.005
318
.004
319
.004
320
.003
321
.003
322
.002
323
.001
324
.000
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
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486

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

0.43.

Note that scores are relative to this ceiling.

Data: Geirhos2021uniformnoise

Metric: error_consistency