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("Geirhos2021lowpass-top1")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.818
2
.801
3
.787
4
.779
5
.771
6
.736
7
.708
8
.679
9
.666
10
.657
11
.645
12
.642
13
.641
14
.640
15
.639
16
.632
17
.629
18
.627
19
.626
20
.619
21
.619
22
.616
23
.616
24
.615
25
.615
26
.615
27
.613
28
.611
29
.609
30
.605
31
.603
32
.580
33
.579
34
.570
35
.568
36
.568
37
.561
38
.557
39
.556
40
.555
41
.551
42
.547
43
.544
44
.544
45
.541
46
.541
47
.540
48
.540
49
.539
50
.537
51
.536
52
.530
53
.527
54
.526
55
.526
56
.526
57
.522
58
.519
59
.516
60
.505
61
.505
62
.505
63
.497
64
.495
65
.494
66
.494
67
.489
68
.487
69
.487
70
.486
71
.485
72
.485
73
.484
74
.484
75
.484
76
.484
77
.484
78
.481
79
.481
80
.481
81
.479
82
.477
83
.477
84
.477
85
.476
86
.476
87
.476
88
.476
89
.474
90
.474
91
.474
92
.472
93
.471
94
.469
95
.469
96
.469
97
.468
98
.466
99
.466
100
.464
101
.463
102
.463
103
.461
104
.460
105
.460
106
.460
107
.459
108
.458
109
.456
110
.456
111
.454
112
.454
113
.454
114
.453
115
.453
116
.453
117
.453
118
.453
119
.453
120
.451
121
.450
122
.449
123
.449
124
.449
125
.448
126
.446
127
.446
128
.446
129
.446
130
.445
131
.444
132
.444
133
.443
134
.441
135
.440
136
.440
137
.439
138
.439
139
.439
140
.439
141
.438
142
.436
143
.434
144
.434
145
.432
146
.432
147
.431
148
.431
149
.431
150
.431
151
.427
152
.425
153
.425
154
.425
155
.424
156
.422
157
.422
158
.421
159
.420
160
.420
161
.419
162
.417
163
.415
164
.414
165
.414
166
.412
167
.411
168
.410
169
.410
170
.410
171
.407
172
.404
173
.404
174
.404
175
.399
176
.398
177
.398
178
.396
179
.395
180
.395
181
.395
182
.393
183
.391
184
.390
185
.389
186
.389
187
.388
188
.388
189
.388
190
.385
191
.380
192
.379
193
.379
194
.379
195
.378
196
.376
197
.376
198
.374
199
.374
200
.372
201
.372
202
.369
203
.369
204
.366
205
.365
206
.364
207
.364
208
.361
209
.361
210
.361
211
.360
212
.360
213
.357
214
.357
215
.356
216
.356
217
.355
218
.354
219
.351
220
.349
221
.349
222
.349
223
.349
224
.346
225
.345
226
.345
227
.345
228
.345
229
.345
230
.344
231
.344
232
.343
233
.340
234
.339
235
.338
236
.338
237
.338
238
.335
239
.335
240
.328
241
.328
242
.326
243
.326
244
.326
245
.326
246
.326
247
.321
248
.320
249
.314
250
.312
251
.312
252
.311
253
.309
254
.307
255
.304
256
.302
257
.300
258
.299
259
.297
260
.296
261
.295
262
.294
263
.294
264
.294
265
.292
266
.291
267
.291
268
.291
269
.290
270
.286
271
.286
272
.282
273
.279
274
.259
275
.250
276
.101
277
.101
278
.099
279
.071
280
.070
281
.068
282
.065
283
.064
284
.064
285
.064
286
.062
287
.062
288
.062
289
.062
290
.062
291
.062
292
.062
293
.062
294
.062
295
.062
296
.062
297
.059
298
.058
299
.058
300
.056
301
.056
302
.055
303
.050
304
.049
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
451
452
453
454
455
456
457
458
459
460
461
462
463

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: Geirhos2021lowpass

Metric: top1