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("Geirhos2021edge-error_consistency")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
1.2
2
1.2
3
1.2
4
1.0
5
.995
6
.979
7
.899
8
.854
9
.807
10
.753
11
.744
12
.728
13
.719
14
.699
15
.670
16
.645
17
.635
18
.619
19
.618
20
.608
21
.543
22
.543
23
.531
24
.519
25
.516
26
.516
27
.502
28
.395
29
.285
30
.264
31
.264
32
.252
33
.243
34
.232
35
.219
36
.200
37
.198
38
.195
39
.194
40
.192
41
.187
42
.184
43
.183
44
.182
45
.182
46
.175
47
.173
48
.168
49
.163
50
.163
51
.160
52
.158
53
.153
54
.151
55
.151
56
.151
57
.151
58
.148
59
.144
60
.144
61
.140
62
.139
63
.139
64
.139
65
.138
66
.133
67
.132
68
.132
69
.131
70
.128
71
.124
72
.124
73
.124
74
.122
75
.116
76
.116
77
.115
78
.115
79
.115
80
.114
81
.113
82
.113
83
.113
84
.109
85
.109
86
.107
87
.107
88
.107
89
.107
90
.107
91
.107
92
.106
93
.106
94
.106
95
.106
96
.105
97
.105
98
.105
99
.104
100
.104
101
.101
102
.100
103
.099
104
.099
105
.099
106
.098
107
.098
108
.098
109
.098
110
.098
111
.093
112
.092
113
.092
114
.092
115
.092
116
.092
117
.092
118
.092
119
.092
120
.092
121
.092
122
.091
123
.091
124
.091
125
.091
126
.091
127
.091
128
.091
129
.091
130
.090
131
.090
132
.085
133
.085
134
.084
135
.084
136
.084
137
.084
138
.084
139
.084
140
.084
141
.084
142
.084
143
.084
144
.084
145
.084
146
.084
147
.084
148
.084
149
.084
150
.083
151
.083
152
.083
153
.079
154
.078
155
.078
156
.077
157
.077
158
.077
159
.077
160
.077
161
.077
162
.077
163
.077
164
.076
165
.076
166
.076
167
.076
168
.076
169
.076
170
.076
171
.076
172
.076
173
.076
174
.076
175
.075
176
.075
177
.075
178
.075
179
.074
180
.074
181
.074
182
.074
183
.070
184
.070
185
.070
186
.070
187
.069
188
.069
189
.069
190
.069
191
.069
192
.069
193
.069
194
.069
195
.069
196
.069
197
.069
198
.069
199
.069
200
.069
201
.069
202
.069
203
.069
204
.068
205
.068
206
.068
207
.068
208
.068
209
.068
210
.068
211
.068
212
.068
213
.066
214
.064
215
.063
216
.063
217
.063
218
.063
219
.062
220
.062
221
.062
222
.062
223
.062
224
.062
225
.062
226
.062
227
.062
228
.062
229
.062
230
.062
231
.061
232
.061
233
.061
234
.060
235
.059
236
.059
237
.056
238
.056
239
.055
240
.055
241
.055
242
.055
243
.055
244
.055
245
.055
246
.055
247
.055
248
.055
249
.055
250
.055
251
.055
252
.055
253
.055
254
.055
255
.055
256
.055
257
.055
258
.055
259
.055
260
.055
261
.055
262
.055
263
.055
264
.055
265
.055
266
.055
267
.055
268
.055
269
.053
270
.053
271
.053
272
.053
273
.050
274
.046
275
.046
276
.042
277
.042
278
.042
279
.039
280
.039
281
.038
282
.037
283
.036
284
.035
285
.034
286
.034
287
.032
288
.032
289
.032
290
.032
291
.032
292
.032
293
.032
294
.024
295
.024
296
.024
297
.024
298
.024
299
.024
300
.024
301
.023
302
.021
303
.021
304
.021
305
.021
306
.021
307
.015
308
.014
309
.011
310
.010
311
.007
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

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

0.32.

Note that scores are relative to this ceiling.

Data: Geirhos2021edge

Metric: error_consistency