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
.722
2
.719
3
.708
4
.695
5
.683
6
.683
7
.675
8
.672
9
.667
10
.664
11
.656
12
.655
13
.650
14
.648
15
.647
16
.647
17
.647
18
.644
19
.637
20
.636
21
.634
22
.634
23
.634
24
.633
25
.633
26
.631
27
.622
28
.620
29
.620
30
.617
31
.616
32
.616
33
.616
34
.613
35
.608
36
.605
37
.602
38
.602
39
.600
40
.600
41
.600
42
.600
43
.598
44
.597
45
.597
46
.597
47
.597
48
.595
49
.594
50
.594
51
.592
52
.592
53
.589
54
.588
55
.584
56
.581
57
.581
58
.580
59
.580
60
.578
61
.578
62
.578
63
.578
64
.577
65
.577
66
.577
67
.577
68
.573
69
.573
70
.572
71
.572
72
.570
73
.570
74
.570
75
.569
76
.569
77
.567
78
.567
79
.567
80
.567
81
.566
82
.566
83
.564
84
.564
85
.562
86
.562
87
.562
88
.561
89
.559
90
.559
91
.559
92
.559
93
.558
94
.558
95
.558
96
.558
97
.558
98
.556
99
.556
100
.555
101
.555
102
.555
103
.553
104
.552
105
.552
106
.552
107
.552
108
.552
109
.550
110
.550
111
.548
112
.548
113
.547
114
.547
115
.545
116
.545
117
.545
118
.544
119
.542
120
.542
121
.542
122
.541
123
.541
124
.539
125
.539
126
.539
127
.539
128
.539
129
.539
130
.537
131
.537
132
.537
133
.537
134
.536
135
.536
136
.536
137
.534
138
.534
139
.534
140
.534
141
.533
142
.533
143
.531
144
.531
145
.531
146
.531
147
.530
148
.530
149
.530
150
.528
151
.528
152
.528
153
.528
154
.527
155
.523
156
.523
157
.522
158
.520
159
.520
160
.519
161
.517
162
.517
163
.517
164
.516
165
.516
166
.516
167
.514
168
.514
169
.514
170
.512
171
.512
172
.511
173
.511
174
.511
175
.509
176
.508
177
.506
178
.506
179
.506
180
.505
181
.505
182
.505
183
.503
184
.502
185
.502
186
.500
187
.498
188
.498
189
.498
190
.497
191
.497
192
.495
193
.495
194
.494
195
.492
196
.492
197
.489
198
.489
199
.487
200
.487
201
.486
202
.486
203
.486
204
.486
205
.486
206
.483
207
.483
208
.481
209
.481
210
.481
211
.480
212
.480
213
.478
214
.477
215
.475
216
.475
217
.475
218
.475
219
.473
220
.473
221
.473
222
.473
223
.473
224
.470
225
.469
226
.467
227
.467
228
.467
229
.464
230
.464
231
.464
232
.463
233
.463
234
.461
235
.459
236
.459
237
.458
238
.456
239
.456
240
.455
241
.455
242
.455
243
.453
244
.453
245
.452
246
.450
247
.448
248
.448
249
.448
250
.448
251
.448
252
.448
253
.447
254
.447
255
.441
256
.441
257
.434
258
.434
259
.433
260
.431
261
.430
262
.430
263
.428
264
.425
265
.423
266
.420
267
.420
268
.419
269
.416
270
.409
271
.408
272
.405
273
.405
274
.405
275
.395
276
.381
277
.353
278
.336
279
.280
280
.128
281
.117
282
.116
283
.084
284
.080
285
.077
286
.077
287
.073
288
.073
289
.067
290
.064
291
.064
292
.062
293
.062
294
.062
295
.062
296
.062
297
.062
298
.062
299
.062
300
.062
301
.062
302
.062
303
.062
304
.062
305
.059
306
.059
307
.052
308
.045
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: Geirhos2021eidolonII

Metric: top1