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("Geirhos2021falsecolour-error_consistency")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.818
2
.804
3
.780
4
.757
5
.756
6
.755
7
.754
8
.752
9
.752
10
.739
11
.738
12
.735
13
.726
14
.708
15
.706
16
.702
17
.699
18
.688
19
.688
20
.682
21
.668
22
.667
23
.648
24
.640
25
.633
26
.622
27
.622
28
.617
29
.610
30
.610
31
.605
32
.599
33
.588
34
.581
35
.580
36
.580
37
.579
38
.572
39
.568
40
.566
41
.564
42
.564
43
.560
44
.559
45
.559
46
.558
47
.554
48
.547
49
.546
50
.542
51
.539
52
.537
53
.536
54
.532
55
.532
56
.531
57
.528
58
.520
59
.519
60
.517
61
.511
62
.507
63
.505
64
.504
65
.497
66
.495
67
.493
68
.493
69
.492
70
.487
71
.486
72
.483
73
.475
74
.471
75
.470
76
.462
77
.461
78
.453
79
.449
80
.447
81
.440
82
.434
83
.429
84
.428
85
.419
86
.416
87
.409
88
.407
89
.401
90
.392
91
.390
92
.388
93
.371
94
.368
95
.367
96
.367
97
.364
98
.362
99
.359
100
.356
101
.353
102
.353
103
.353
104
.351
105
.351
106
.348
107
.346
108
.338
109
.338
110
.337
111
.337
112
.336
113
.336
114
.336
115
.336
116
.335
117
.333
118
.333
119
.332
120
.326
121
.324
122
.312
123
.309
124
.309
125
.309
126
.309
127
.306
128
.300
129
.299
130
.299
131
.297
132
.296
133
.295
134
.292
135
.291
136
.289
137
.282
138
.280
139
.269
140
.269
141
.268
142
.267
143
.263
144
.262
145
.257
146
.257
147
.256
148
.256
149
.255
150
.253
151
.252
152
.251
153
.251
154
.249
155
.246
156
.240
157
.238
158
.237
159
.233
160
.231
161
.230
162
.228
163
.226
164
.225
165
.225
166
.223
167
.221
168
.221
169
.220
170
.219
171
.219
172
.218
173
.218
174
.216
175
.215
176
.212
177
.212
178
.212
179
.209
180
.195
181
.193
182
.193
183
.188
184
.187
185
.183
186
.181
187
.179
188
.175
189
.174
190
.164
191
.163
192
.157
193
.157
194
.155
195
.152
196
.145
197
.144
198
.143
199
.139
200
.137
201
.136
202
.123
203
.119
204
.116
205
.114
206
.113
207
.107
208
.107
209
.106
210
.104
211
.103
212
.101
213
.101
214
.100
215
.092
216
.088
217
.087
218
.086
219
.085
220
.082
221
.073
222
.073
223
.070
224
.069
225
.068
226
.067
227
.066
228
.065
229
.064
230
.064
231
.064
232
.063
233
.056
234
.055
235
.055
236
.055
237
.055
238
.055
239
.055
240
.055
241
.055
242
.055
243
.055
244
.055
245
.055
246
.055
247
.054
248
.051
249
.049
250
.048
251
.045
252
.045
253
.043
254
.043
255
.043
256
.043
257
.043
258
.043
259
.039
260
.038
261
.037
262
.036
263
.035
264
.035
265
.034
266
.034
267
.034
268
.034
269
.033
270
.031
271
.029
272
.027
273
.027
274
.025
275
.021
276
.019
277
.019
278
.019
279
.018
280
.017
281
.017
282
.016
283
.016
284
.016
285
.016
286
.015
287
.015
288
.014
289
.013
290
.013
291
.012
292
.011
293
.011
294
.011
295
.010
296
.010
297
.010
298
.010
299
.010
300
.010
301
.010
302
.009
303
.009
304
.009
305
.008
306
.004
307
.004
308
.003
309
.003
310
.003
311
.001
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

0.44.

Note that scores are relative to this ceiling.

Data: Geirhos2021falsecolour

Metric: error_consistency