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("Geirhos2021eidolonI-top1")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.654
2
.637
3
.635
4
.630
5
.630
6
.627
7
.625
8
.625
9
.625
10
.625
11
.625
12
.618
13
.614
14
.613
15
.606
16
.606
17
.606
18
.604
19
.603
20
.603
21
.603
22
.603
23
.601
24
.596
25
.595
26
.591
27
.590
28
.588
29
.585
30
.584
31
.583
32
.583
33
.581
34
.579
35
.578
36
.578
37
.576
38
.575
39
.575
40
.575
41
.575
42
.575
43
.571
44
.570
45
.566
46
.565
47
.565
48
.564
49
.562
50
.560
51
.559
52
.559
53
.557
54
.557
55
.556
56
.556
57
.555
58
.552
59
.551
60
.550
61
.550
62
.549
63
.547
64
.547
65
.546
66
.546
67
.546
68
.545
69
.544
70
.542
71
.542
72
.541
73
.541
74
.539
75
.537
76
.537
77
.537
78
.536
79
.536
80
.536
81
.535
82
.535
83
.535
84
.535
85
.534
86
.534
87
.534
88
.534
89
.534
90
.532
91
.532
92
.530
93
.529
94
.529
95
.529
96
.527
97
.527
98
.527
99
.527
100
.526
101
.526
102
.526
103
.526
104
.524
105
.522
106
.522
107
.522
108
.521
109
.521
110
.520
111
.520
112
.520
113
.520
114
.519
115
.519
116
.519
117
.519
118
.519
119
.517
120
.517
121
.516
122
.516
123
.516
124
.516
125
.516
126
.515
127
.515
128
.515
129
.515
130
.515
131
.515
132
.515
133
.515
134
.514
135
.514
136
.514
137
.512
138
.512
139
.512
140
.511
141
.510
142
.510
143
.510
144
.510
145
.510
146
.509
147
.507
148
.507
149
.506
150
.505
151
.505
152
.505
153
.504
154
.502
155
.502
156
.501
157
.501
158
.500
159
.500
160
.499
161
.499
162
.499
163
.497
164
.497
165
.497
166
.497
167
.496
168
.496
169
.495
170
.495
171
.495
172
.494
173
.494
174
.494
175
.492
176
.492
177
.491
178
.490
179
.490
180
.490
181
.489
182
.489
183
.487
184
.486
185
.486
186
.485
187
.485
188
.484
189
.482
190
.482
191
.481
192
.481
193
.481
194
.479
195
.477
196
.477
197
.477
198
.476
199
.476
200
.476
201
.475
202
.475
203
.474
204
.474
205
.474
206
.474
207
.474
208
.474
209
.474
210
.472
211
.471
212
.471
213
.471
214
.471
215
.470
216
.470
217
.469
218
.469
219
.469
220
.468
221
.468
222
.466
223
.465
224
.464
225
.464
226
.464
227
.464
228
.463
229
.463
230
.461
231
.461
232
.460
233
.460
234
.459
235
.458
236
.458
237
.455
238
.454
239
.454
240
.453
241
.453
242
.453
243
.451
244
.450
245
.449
246
.449
247
.448
248
.448
249
.446
250
.445
251
.444
252
.444
253
.443
254
.439
255
.438
256
.434
257
.431
258
.430
259
.430
260
.426
261
.425
262
.425
263
.424
264
.422
265
.419
266
.412
267
.409
268
.404
269
.395
270
.393
271
.376
272
.359
273
.357
274
.280
275
.133
276
.106
277
.101
278
.085
279
.076
280
.075
281
.066
282
.062
283
.062
284
.062
285
.062
286
.062
287
.062
288
.062
289
.062
290
.062
291
.062
292
.062
293
.059
294
.059
295
.056
296
.054
297
.052
298
.051
299
.051
300
.050
301
.050
302
.048
303
.044
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
451
452
453
454
455
456
457
458
459
460

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: Geirhos2021eidolonI

Metric: top1