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("Geirhos2021eidolonII-top1")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.683
2
.675
3
.667
4
.656
5
.655
6
.648
7
.647
8
.647
9
.647
10
.644
11
.637
12
.636
13
.634
14
.634
15
.634
16
.631
17
.622
18
.620
19
.620
20
.617
21
.616
22
.616
23
.616
24
.613
25
.608
26
.605
27
.602
28
.602
29
.600
30
.600
31
.600
32
.600
33
.597
34
.597
35
.597
36
.597
37
.595
38
.594
39
.594
40
.592
41
.592
42
.589
43
.584
44
.581
45
.581
46
.580
47
.580
48
.578
49
.578
50
.578
51
.577
52
.577
53
.577
54
.577
55
.573
56
.573
57
.572
58
.570
59
.570
60
.570
61
.569
62
.569
63
.567
64
.567
65
.567
66
.567
67
.566
68
.566
69
.564
70
.564
71
.562
72
.562
73
.562
74
.561
75
.559
76
.559
77
.559
78
.559
79
.558
80
.558
81
.558
82
.558
83
.558
84
.556
85
.556
86
.555
87
.555
88
.555
89
.553
90
.552
91
.552
92
.552
93
.552
94
.552
95
.550
96
.550
97
.548
98
.548
99
.547
100
.547
101
.545
102
.545
103
.545
104
.544
105
.544
106
.542
107
.542
108
.542
109
.542
110
.541
111
.541
112
.539
113
.539
114
.539
115
.539
116
.539
117
.539
118
.537
119
.537
120
.537
121
.537
122
.536
123
.536
124
.536
125
.536
126
.534
127
.534
128
.534
129
.534
130
.533
131
.533
132
.533
133
.531
134
.531
135
.531
136
.531
137
.531
138
.531
139
.530
140
.530
141
.530
142
.528
143
.528
144
.528
145
.528
146
.528
147
.527
148
.527
149
.525
150
.523
151
.523
152
.522
153
.520
154
.520
155
.519
156
.517
157
.517
158
.517
159
.516
160
.516
161
.516
162
.514
163
.514
164
.514
165
.512
166
.512
167
.511
168
.511
169
.511
170
.509
171
.508
172
.506
173
.506
174
.506
175
.505
176
.505
177
.505
178
.503
179
.502
180
.502
181
.500
182
.498
183
.498
184
.498
185
.497
186
.497
187
.495
188
.495
189
.494
190
.492
191
.492
192
.489
193
.489
194
.487
195
.487
196
.486
197
.486
198
.486
199
.486
200
.486
201
.483
202
.483
203
.481
204
.481
205
.481
206
.480
207
.480
208
.478
209
.477
210
.475
211
.475
212
.475
213
.475
214
.473
215
.473
216
.473
217
.473
218
.473
219
.470
220
.469
221
.467
222
.467
223
.467
224
.464
225
.464
226
.464
227
.463
228
.463
229
.461
230
.459
231
.459
232
.458
233
.456
234
.456
235
.455
236
.455
237
.455
238
.453
239
.453
240
.452
241
.450
242
.448
243
.448
244
.448
245
.448
246
.448
247
.448
248
.447
249
.447
250
.441
251
.441
252
.434
253
.434
254
.433
255
.431
256
.430
257
.430
258
.428
259
.425
260
.423
261
.420
262
.420
263
.419
264
.416
265
.409
266
.408
267
.405
268
.405
269
.405
270
.395
271
.381
272
.353
273
.336
274
.280
275
.128
276
.117
277
.116
278
.084
279
.080
280
.077
281
.077
282
.073
283
.073
284
.067
285
.064
286
.064
287
.062
288
.062
289
.062
290
.062
291
.062
292
.062
293
.062
294
.062
295
.062
296
.062
297
.062
298
.062
299
.062
300
.062
301
.061
302
.059
303
.059
304
.052
305
.045
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: Geirhos2021eidolonII

Metric: top1