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("Geirhos2021eidolonII-error_consistency")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.732
2
.703
3
.699
4
.696
5
.692
6
.680
7
.674
8
.665
9
.664
10
.662
11
.662
12
.659
13
.656
14
.650
15
.650
16
.646
17
.646
18
.643
19
.640
20
.635
21
.632
22
.630
23
.626
24
.625
25
.624
26
.622
27
.617
28
.613
29
.613
30
.613
31
.610
32
.603
33
.602
34
.597
35
.590
36
.588
37
.582
38
.578
39
.577
40
.569
41
.564
42
.559
43
.559
44
.558
45
.558
46
.555
47
.549
48
.547
49
.546
50
.540
51
.538
52
.535
53
.534
54
.534
55
.527
56
.524
57
.522
58
.520
59
.519
60
.518
61
.515
62
.513
63
.512
64
.509
65
.503
66
.501
67
.501
68
.496
69
.495
70
.491
71
.482
72
.481
73
.477
74
.475
75
.473
76
.470
77
.469
78
.465
79
.465
80
.463
81
.458
82
.455
83
.454
84
.454
85
.453
86
.453
87
.451
88
.448
89
.445
90
.443
91
.433
92
.423
93
.423
94
.421
95
.421
96
.416
97
.416
98
.414
99
.411
100
.410
101
.405
102
.401
103
.399
104
.399
105
.394
106
.379
107
.379
108
.375
109
.371
110
.371
111
.366
112
.365
113
.364
114
.363
115
.361
116
.361
117
.359
118
.359
119
.358
120
.354
121
.351
122
.350
123
.345
124
.342
125
.337
126
.331
127
.330
128
.329
129
.329
130
.329
131
.329
132
.329
133
.327
134
.325
135
.320
136
.317
137
.317
138
.315
139
.314
140
.313
141
.313
142
.313
143
.311
144
.311
145
.308
146
.304
147
.302
148
.299
149
.298
150
.298
151
.297
152
.296
153
.296
154
.294
155
.294
156
.289
157
.289
158
.287
159
.287
160
.286
161
.285
162
.279
163
.278
164
.274
165
.270
166
.270
167
.267
168
.266
169
.266
170
.265
171
.260
172
.260
173
.258
174
.257
175
.256
176
.255
177
.254
178
.252
179
.252
180
.252
181
.252
182
.252
183
.252
184
.252
185
.252
186
.252
187
.252
188
.252
189
.252
190
.252
191
.250
192
.247
193
.246
194
.236
195
.235
196
.235
197
.232
198
.226
199
.226
200
.226
201
.226
202
.225
203
.224
204
.224
205
.223
206
.223
207
.216
208
.216
209
.215
210
.206
211
.206
212
.204
213
.198
214
.196
215
.195
216
.191
217
.190
218
.189
219
.189
220
.182
221
.182
222
.180
223
.180
224
.179
225
.178
226
.178
227
.174
228
.174
229
.173
230
.169
231
.166
232
.161
233
.161
234
.158
235
.158
236
.155
237
.154
238
.151
239
.149
240
.145
241
.143
242
.143
243
.143
244
.143
245
.143
246
.143
247
.142
248
.137
249
.136
250
.134
251
.133
252
.130
253
.128
254
.124
255
.124
256
.118
257
.118
258
.116
259
.115
260
.114
261
.114
262
.112
263
.110
264
.109
265
.107
266
.105
267
.105
268
.104
269
.100
270
.098
271
.098
272
.096
273
.089
274
.088
275
.086
276
.086
277
.086
278
.078
279
.075
280
.071
281
.065
282
.065
283
.061
284
.061
285
.058
286
.058
287
.057
288
.053
289
.052
290
.049
291
.049
292
.049
293
.049
294
.048
295
.046
296
.043
297
.042
298
.041
299
.040
300
.039
301
.032
302
.030
303
.030
304
.026
305
.024
306
.024
307
.020
308
.013
309
.010
310
.007
311
.006
312
.003
313
.002
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
457
458
459
460

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

0.45.

Note that scores are relative to this ceiling.

Data: Geirhos2021eidolonII

Metric: error_consistency