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("Geirhos2021stylized-top1")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.910
2
.910
3
.786
4
.786
5
.786
6
.786
7
.748
8
.716
9
.716
10
.713
11
.708
12
.700
13
.695
14
.690
15
.672
16
.664
17
.657
18
.655
19
.654
20
.654
21
.650
22
.649
23
.649
24
.644
25
.641
26
.637
27
.631
28
.627
29
.613
30
.609
31
.605
32
.599
33
.599
34
.599
35
.595
36
.594
37
.594
38
.588
39
.586
40
.574
41
.571
42
.571
43
.568
44
.568
45
.566
46
.566
47
.566
48
.561
49
.559
50
.559
51
.557
52
.557
53
.556
54
.551
55
.547
56
.546
57
.546
58
.546
59
.544
60
.544
61
.540
62
.521
63
.521
64
.515
65
.514
66
.512
67
.509
68
.492
69
.492
70
.485
71
.482
72
.481
73
.476
74
.475
75
.466
76
.466
77
.464
78
.464
79
.458
80
.455
81
.450
82
.450
83
.450
84
.448
85
.445
86
.444
87
.441
88
.441
89
.440
90
.440
91
.438
92
.434
93
.431
94
.430
95
.427
96
.427
97
.426
98
.426
99
.426
100
.425
101
.424
102
.422
103
.422
104
.421
105
.420
106
.420
107
.420
108
.419
109
.419
110
.419
111
.417
112
.416
113
.416
114
.416
115
.415
116
.414
117
.412
118
.410
119
.410
120
.410
121
.410
122
.410
123
.410
124
.409
125
.409
126
.409
127
.407
128
.407
129
.407
130
.407
131
.407
132
.406
133
.404
134
.404
135
.404
136
.403
137
.401
138
.401
139
.401
140
.401
141
.400
142
.400
143
.400
144
.399
145
.399
146
.399
147
.399
148
.399
149
.398
150
.398
151
.398
152
.398
153
.398
154
.395
155
.395
156
.395
157
.393
158
.393
159
.390
160
.389
161
.388
162
.386
163
.386
164
.386
165
.386
166
.386
167
.385
168
.385
169
.384
170
.384
171
.383
172
.383
173
.381
174
.381
175
.381
176
.380
177
.379
178
.379
179
.379
180
.378
181
.378
182
.378
183
.375
184
.374
185
.372
186
.371
187
.371
188
.371
189
.371
190
.371
191
.371
192
.370
193
.370
194
.369
195
.367
196
.367
197
.366
198
.366
199
.366
200
.366
201
.365
202
.364
203
.361
204
.360
205
.359
206
.359
207
.359
208
.357
209
.356
210
.356
211
.355
212
.355
213
.354
214
.354
215
.352
216
.352
217
.352
218
.352
219
.351
220
.351
221
.351
222
.350
223
.347
224
.346
225
.346
226
.346
227
.345
228
.344
229
.344
230
.343
231
.341
232
.341
233
.341
234
.340
235
.338
236
.338
237
.335
238
.331
239
.331
240
.329
241
.329
242
.328
243
.325
244
.325
245
.321
246
.315
247
.315
248
.312
249
.312
250
.311
251
.309
252
.306
253
.306
254
.305
255
.305
256
.302
257
.302
258
.301
259
.297
260
.290
261
.289
262
.287
263
.282
264
.279
265
.279
266
.279
267
.279
268
.279
269
.265
270
.265
271
.263
272
.255
273
.254
274
.253
275
.251
276
.241
277
.184
278
.160
279
.087
280
.084
281
.083
282
.072
283
.070
284
.070
285
.068
286
.066
287
.065
288
.065
289
.065
290
.064
291
.062
292
.062
293
.062
294
.062
295
.062
296
.062
297
.062
298
.062
299
.062
300
.062
301
.059
302
.058
303
.058
304
.055
305
.050
306
.045
307
.044
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
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469

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

1.00.

Note that scores are relative to this ceiling.

Data: Geirhos2021stylized

Metric: top1