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("Geirhos2021stylized-error_consistency")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.871
2
.859
3
.851
4
.830
5
.787
6
.758
7
.751
8
.750
9
.746
10
.737
11
.734
12
.723
13
.708
14
.706
15
.705
16
.705
17
.704
18
.702
19
.697
20
.697
21
.693
22
.680
23
.680
24
.678
25
.678
26
.666
27
.654
28
.653
29
.646
30
.646
31
.646
32
.646
33
.628
34
.627
35
.627
36
.623
37
.617
38
.603
39
.600
40
.590
41
.588
42
.583
43
.579
44
.570
45
.566
46
.555
47
.538
48
.521
49
.516
50
.515
51
.511
52
.498
53
.494
54
.491
55
.488
56
.486
57
.479
58
.467
59
.464
60
.463
61
.457
62
.456
63
.454
64
.450
65
.449
66
.443
67
.443
68
.439
69
.438
70
.438
71
.437
72
.434
73
.433
74
.430
75
.430
76
.429
77
.427
78
.422
79
.421
80
.418
81
.418
82
.417
83
.417
84
.417
85
.411
86
.411
87
.409
88
.405
89
.405
90
.400
91
.395
92
.392
93
.391
94
.389
95
.381
96
.370
97
.369
98
.365
99
.362
100
.358
101
.358
102
.351
103
.346
104
.342
105
.341
106
.340
107
.328
108
.324
109
.322
110
.321
111
.320
112
.319
113
.319
114
.317
115
.315
116
.315
117
.315
118
.315
119
.314
120
.314
121
.313
122
.311
123
.307
124
.305
125
.303
126
.302
127
.301
128
.300
129
.299
130
.299
131
.298
132
.297
133
.295
134
.295
135
.293
136
.292
137
.290
138
.289
139
.288
140
.281
141
.281
142
.278
143
.274
144
.274
145
.273
146
.272
147
.271
148
.270
149
.267
150
.266
151
.263
152
.263
153
.262
154
.262
155
.258
156
.255
157
.254
158
.254
159
.254
160
.254
161
.252
162
.251
163
.251
164
.243
165
.236
166
.233
167
.233
168
.232
169
.230
170
.229
171
.229
172
.224
173
.223
174
.219
175
.218
176
.216
177
.213
178
.208
179
.202
180
.202
181
.201
182
.199
183
.198
184
.198
185
.198
186
.198
187
.197
188
.195
189
.195
190
.194
191
.192
192
.192
193
.191
194
.187
195
.185
196
.185
197
.184
198
.182
199
.181
200
.181
201
.176
202
.166
203
.166
204
.163
205
.160
206
.159
207
.159
208
.157
209
.155
210
.154
211
.146
212
.145
213
.141
214
.139
215
.139
216
.134
217
.133
218
.131
219
.131
220
.129
221
.127
222
.127
223
.123
224
.121
225
.121
226
.120
227
.119
228
.119
229
.116
230
.114
231
.113
232
.111
233
.110
234
.110
235
.107
236
.107
237
.106
238
.106
239
.103
240
.103
241
.102
242
.100
243
.098
244
.097
245
.097
246
.097
247
.097
248
.096
249
.096
250
.094
251
.094
252
.093
253
.093
254
.093
255
.093
256
.093
257
.092
258
.090
259
.089
260
.088
261
.088
262
.087
263
.087
264
.086
265
.084
266
.084
267
.084
268
.080
269
.079
270
.078
271
.078
272
.078
273
.075
274
.075
275
.074
276
.070
277
.067
278
.066
279
.065
280
.064
281
.064
282
.064
283
.062
284
.061
285
.060
286
.060
287
.057
288
.057
289
.049
290
.047
291
.046
292
.045
293
.045
294
.044
295
.044
296
.044
297
.040
298
.040
299
.040
300
.038
301
.037
302
.028
303
.026
304
.026
305
.025
306
.016
307
.016
308
.015
309
.015
310
.015
311
.014
312
.012
313
.012
314
.008
315
.006
316
.005
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
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481

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

0.50.

Note that scores are relative to this ceiling.

Data: Geirhos2021stylized

Metric: error_consistency