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("Geirhos2021powerequalisation-error_consistency")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.755
2
.718
3
.713
4
.709
5
.707
6
.707
7
.705
8
.680
9
.672
10
.670
11
.668
12
.651
13
.650
14
.647
15
.638
16
.633
17
.599
18
.592
19
.586
20
.579
21
.564
22
.560
23
.548
24
.540
25
.501
26
.494
27
.489
28
.486
29
.482
30
.472
31
.468
32
.467
33
.462
34
.455
35
.453
36
.451
37
.450
38
.427
39
.427
40
.427
41
.397
42
.388
43
.382
44
.380
45
.380
46
.378
47
.363
48
.339
49
.335
50
.323
51
.317
52
.317
53
.315
54
.307
55
.295
56
.292
57
.289
58
.289
59
.287
60
.287
61
.280
62
.278
63
.269
64
.269
65
.260
66
.260
67
.257
68
.248
69
.246
70
.245
71
.237
72
.234
73
.228
74
.227
75
.222
76
.221
77
.217
78
.217
79
.216
80
.214
81
.209
82
.201
83
.197
84
.195
85
.193
86
.190
87
.189
88
.189
89
.187
90
.186
91
.186
92
.185
93
.184
94
.182
95
.181
96
.181
97
.174
98
.173
99
.172
100
.169
101
.167
102
.164
103
.159
104
.155
105
.149
106
.147
107
.145
108
.145
109
.140
110
.134
111
.133
112
.132
113
.132
114
.132
115
.128
116
.127
117
.127
118
.126
119
.125
120
.125
121
.125
122
.122
123
.121
124
.119
125
.119
126
.118
127
.116
128
.115
129
.114
130
.113
131
.112
132
.108
133
.107
134
.105
135
.105
136
.100
137
.098
138
.098
139
.098
140
.098
141
.098
142
.098
143
.097
144
.097
145
.096
146
.096
147
.095
148
.094
149
.094
150
.094
151
.093
152
.091
153
.090
154
.089
155
.089
156
.089
157
.088
158
.088
159
.088
160
.086
161
.085
162
.084
163
.083
164
.083
165
.083
166
.083
167
.083
168
.083
169
.083
170
.083
171
.082
172
.078
173
.078
174
.078
175
.076
176
.075
177
.075
178
.073
179
.070
180
.070
181
.069
182
.068
183
.065
184
.065
185
.065
186
.064
187
.064
188
.063
189
.062
190
.062
191
.062
192
.062
193
.060
194
.059
195
.059
196
.059
197
.057
198
.053
199
.053
200
.053
201
.053
202
.053
203
.053
204
.052
205
.050
206
.048
207
.047
208
.047
209
.046
210
.045
211
.044
212
.043
213
.041
214
.041
215
.040
216
.040
217
.040
218
.040
219
.040
220
.040
221
.039
222
.039
223
.038
224
.038
225
.038
226
.038
227
.038
228
.037
229
.037
230
.037
231
.037
232
.036
233
.036
234
.036
235
.035
236
.035
237
.034
238
.034
239
.034
240
.033
241
.033
242
.033
243
.033
244
.032
245
.032
246
.031
247
.031
248
.031
249
.031
250
.031
251
.031
252
.030
253
.029
254
.028
255
.027
256
.027
257
.027
258
.026
259
.024
260
.024
261
.023
262
.023
263
.023
264
.021
265
.021
266
.020
267
.020
268
.019
269
.019
270
.019
271
.018
272
.018
273
.017
274
.016
275
.015
276
.015
277
.014
278
.014
279
.014
280
.014
281
.013
282
.012
283
.012
284
.011
285
.011
286
.011
287
.010
288
.010
289
.010
290
.009
291
.008
292
.007
293
.006
294
.006
295
.005
296
.004
297
.003
298
.003
299
.003
300
.002
301
.002
302
.001
303
.000
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

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

0.51.

Note that scores are relative to this ceiling.

Data: Geirhos2021powerequalisation

Metric: error_consistency