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("Geirhos2021eidolonI-error_consistency")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.789
2
.783
3
.777
4
.776
5
.731
6
.724
7
.715
8
.698
9
.689
10
.677
11
.667
12
.663
13
.661
14
.655
15
.651
16
.647
17
.646
18
.638
19
.637
20
.637
21
.636
22
.629
23
.629
24
.621
25
.619
26
.619
27
.619
28
.615
29
.614
30
.610
31
.607
32
.603
33
.593
34
.593
35
.584
36
.583
37
.582
38
.577
39
.575
40
.574
41
.574
42
.567
43
.556
44
.553
45
.551
46
.549
47
.546
48
.541
49
.541
50
.537
51
.529
52
.527
53
.527
54
.524
55
.522
56
.520
57
.519
58
.513
59
.513
60
.512
61
.505
62
.499
63
.498
64
.497
65
.492
66
.491
67
.487
68
.482
69
.481
70
.476
71
.476
72
.472
73
.471
74
.470
75
.464
76
.459
77
.459
78
.459
79
.456
80
.453
81
.448
82
.446
83
.445
84
.443
85
.443
86
.443
87
.442
88
.436
89
.435
90
.432
91
.432
92
.431
93
.430
94
.429
95
.424
96
.417
97
.417
98
.416
99
.413
100
.412
101
.409
102
.408
103
.406
104
.403
105
.401
106
.400
107
.400
108
.400
109
.400
110
.394
111
.393
112
.384
113
.383
114
.378
115
.377
116
.371
117
.367
118
.363
119
.359
120
.355
121
.355
122
.354
123
.352
124
.350
125
.349
126
.346
127
.344
128
.341
129
.338
130
.336
131
.336
132
.335
133
.334
134
.333
135
.331
136
.329
137
.328
138
.327
139
.326
140
.325
141
.324
142
.324
143
.318
144
.318
145
.317
146
.309
147
.304
148
.301
149
.299
150
.297
151
.297
152
.297
153
.296
154
.295
155
.295
156
.293
157
.291
158
.290
159
.288
160
.287
161
.287
162
.286
163
.281
164
.281
165
.281
166
.281
167
.281
168
.281
169
.281
170
.281
171
.281
172
.281
173
.281
174
.281
175
.281
176
.281
177
.277
178
.276
179
.274
180
.272
181
.269
182
.264
183
.260
184
.256
185
.255
186
.253
187
.252
188
.251
189
.250
190
.249
191
.247
192
.245
193
.243
194
.242
195
.242
196
.242
197
.241
198
.239
199
.238
200
.235
201
.230
202
.229
203
.223
204
.223
205
.222
206
.218
207
.217
208
.213
209
.210
210
.210
211
.208
212
.208
213
.208
214
.206
215
.204
216
.198
217
.197
218
.196
219
.196
220
.194
221
.192
222
.188
223
.186
224
.182
225
.181
226
.180
227
.180
228
.180
229
.180
230
.180
231
.180
232
.179
233
.179
234
.175
235
.171
236
.169
237
.168
238
.164
239
.161
240
.161
241
.160
242
.160
243
.159
244
.159
245
.156
246
.156
247
.150
248
.149
249
.148
250
.143
251
.141
252
.140
253
.140
254
.138
255
.132
256
.132
257
.131
258
.131
259
.129
260
.126
261
.126
262
.125
263
.122
264
.120
265
.120
266
.113
267
.113
268
.111
269
.107
270
.098
271
.097
272
.097
273
.094
274
.094
275
.094
276
.093
277
.089
278
.085
279
.085
280
.085
281
.085
282
.084
283
.084
284
.077
285
.077
286
.070
287
.065
288
.064
289
.063
290
.059
291
.058
292
.058
293
.057
294
.056
295
.055
296
.051
297
.044
298
.042
299
.041
300
.038
301
.036
302
.029
303
.015
304
.014
305
.013
306
.009
307
.008
308
.008
309
.004
310
.002
311
.002
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

0.39.

Note that scores are relative to this ceiling.

Data: Geirhos2021eidolonI

Metric: error_consistency