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("Geirhos2021sketch-error_consistency")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.776
2
.776
3
.746
4
.742
5
.734
6
.700
7
.699
8
.678
9
.669
10
.666
11
.666
12
.663
13
.658
14
.658
15
.630
16
.594
17
.585
18
.578
19
.576
20
.559
21
.556
22
.539
23
.512
24
.481
25
.461
26
.460
27
.452
28
.425
29
.421
30
.382
31
.336
32
.331
33
.314
34
.293
35
.287
36
.283
37
.278
38
.276
39
.274
40
.274
41
.271
42
.267
43
.267
44
.253
45
.247
46
.245
47
.242
48
.242
49
.234
50
.232
51
.221
52
.220
53
.220
54
.213
55
.212
56
.207
57
.205
58
.204
59
.202
60
.198
61
.198
62
.191
63
.177
64
.172
65
.169
66
.163
67
.163
68
.161
69
.161
70
.160
71
.159
72
.157
73
.155
74
.155
75
.153
76
.153
77
.149
78
.147
79
.145
80
.143
81
.143
82
.142
83
.141
84
.139
85
.138
86
.138
87
.136
88
.135
89
.132
90
.131
91
.127
92
.127
93
.125
94
.125
95
.125
96
.124
97
.124
98
.124
99
.121
100
.120
101
.119
102
.119
103
.119
104
.118
105
.118
106
.117
107
.117
108
.116
109
.115
110
.115
111
.115
112
.114
113
.114
114
.114
115
.113
116
.112
117
.112
118
.112
119
.111
120
.111
121
.111
122
.110
123
.109
124
.107
125
.105
126
.104
127
.104
128
.103
129
.103
130
.103
131
.103
132
.102
133
.102
134
.101
135
.101
136
.099
137
.098
138
.097
139
.097
140
.097
141
.095
142
.095
143
.094
144
.093
145
.092
146
.091
147
.091
148
.090
149
.090
150
.088
151
.088
152
.088
153
.088
154
.086
155
.086
156
.084
157
.083
158
.082
159
.080
160
.078
161
.077
162
.076
163
.075
164
.075
165
.073
166
.073
167
.072
168
.072
169
.070
170
.070
171
.070
172
.069
173
.068
174
.068
175
.068
176
.068
177
.067
178
.067
179
.067
180
.066
181
.066
182
.064
183
.064
184
.064
185
.063
186
.063
187
.063
188
.062
189
.062
190
.061
191
.060
192
.058
193
.058
194
.057
195
.057
196
.056
197
.056
198
.055
199
.055
200
.055
201
.054
202
.053
203
.053
204
.053
205
.052
206
.052
207
.052
208
.051
209
.051
210
.049
211
.049
212
.049
213
.049
214
.048
215
.048
216
.047
217
.047
218
.046
219
.046
220
.046
221
.046
222
.045
223
.045
224
.045
225
.044
226
.043
227
.043
228
.043
229
.042
230
.042
231
.042
232
.042
233
.041
234
.041
235
.041
236
.041
237
.040
238
.039
239
.039
240
.039
241
.039
242
.038
243
.038
244
.038
245
.036
246
.035
247
.034
248
.034
249
.032
250
.032
251
.032
252
.032
253
.032
254
.031
255
.031
256
.031
257
.030
258
.030
259
.030
260
.029
261
.028
262
.027
263
.027
264
.026
265
.026
266
.025
267
.025
268
.025
269
.024
270
.024
271
.024
272
.024
273
.024
274
.023
275
.023
276
.023
277
.023
278
.022
279
.022
280
.021
281
.020
282
.020
283
.018
284
.014
285
.014
286
.014
287
.011
288
.009
289
.005
290
.003
291
.003
292
.002
293
.002
294
.002
295
.002
296
.002
297
.001
298
299
300
301
302
303
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

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

0.37.

Note that scores are relative to this ceiling.

Data: Geirhos2021sketch

Metric: error_consistency