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-top1")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.974
2
.973
3
.958
4
.951
5
.946
6
.946
7
.946
8
.945
9
.943
10
.940
11
.938
12
.935
13
.930
14
.927
15
.925
16
.922
17
.919
18
.914
19
.911
20
.910
21
.909
22
.905
23
.905
24
.902
25
.902
26
.897
27
.884
28
.879
29
.873
30
.871
31
.870
32
.869
33
.864
34
.850
35
.833
36
.824
37
.806
38
.799
39
.795
40
.787
41
.784
42
.779
43
.779
44
.767
45
.766
46
.765
47
.760
48
.756
49
.740
50
.736
51
.736
52
.731
53
.730
54
.728
55
.724
56
.721
57
.719
58
.713
59
.713
60
.710
61
.706
62
.695
63
.689
64
.686
65
.682
66
.681
67
.681
68
.680
69
.680
70
.680
71
.680
72
.677
73
.677
74
.677
75
.676
76
.675
77
.674
78
.672
79
.672
80
.670
81
.669
82
.667
83
.661
84
.661
85
.660
86
.660
87
.659
88
.657
89
.656
90
.656
91
.656
92
.656
93
.655
94
.654
95
.654
96
.654
97
.654
98
.652
99
.652
100
.651
101
.651
102
.650
103
.650
104
.649
105
.645
106
.645
107
.645
108
.645
109
.644
110
.642
111
.642
112
.642
113
.642
114
.641
115
.641
116
.637
117
.636
118
.636
119
.634
120
.634
121
.634
122
.632
123
.631
124
.631
125
.631
126
.631
127
.630
128
.630
129
.630
130
.627
131
.626
132
.626
133
.626
134
.625
135
.625
136
.625
137
.621
138
.620
139
.618
140
.616
141
.615
142
.615
143
.614
144
.614
145
.614
146
.613
147
.611
148
.610
149
.610
150
.609
151
.609
152
.608
153
.606
154
.606
155
.604
156
.604
157
.604
158
.604
159
.604
160
.603
161
.601
162
.601
163
.601
164
.601
165
.600
166
.600
167
.599
168
.599
169
.598
170
.596
171
.596
172
.596
173
.596
174
.596
175
.596
176
.595
177
.595
178
.595
179
.595
180
.594
181
.594
182
.593
183
.591
184
.590
185
.588
186
.585
187
.583
188
.583
189
.583
190
.583
191
.581
192
.580
193
.580
194
.574
195
.573
196
.573
197
.571
198
.562
199
.562
200
.562
201
.561
202
.560
203
.560
204
.559
205
.557
206
.557
207
.554
208
.549
209
.547
210
.547
211
.546
212
.546
213
.546
214
.545
215
.544
216
.542
217
.542
218
.540
219
.540
220
.535
221
.532
222
.531
223
.531
224
.529
225
.526
226
.525
227
.524
228
.522
229
.522
230
.521
231
.520
232
.520
233
.519
234
.517
235
.514
236
.514
237
.511
238
.510
239
.509
240
.506
241
.505
242
.505
243
.502
244
.499
245
.499
246
.487
247
.485
248
.485
249
.480
250
.479
251
.472
252
.466
253
.461
254
.461
255
.456
256
.456
257
.455
258
.455
259
.450
260
.450
261
.450
262
.450
263
.450
264
.449
265
.444
266
.438
267
.431
268
.419
269
.410
270
.380
271
.379
272
.364
273
.351
274
.340
275
.334
276
.323
277
.319
278
.281
279
.156
280
.085
281
.083
282
.080
283
.076
284
.076
285
.075
286
.072
287
.065
288
.064
289
.064
290
.062
291
.062
292
.062
293
.062
294
.062
295
.062
296
.062
297
.061
298
.061
299
.061
300
.061
301
.059
302
.056
303
.056
304
.051
305
.046
306
.035
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
464
465
466
467

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: Geirhos2021sketch

Metric: top1