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("Geirhos2021eidolonIII-error_consistency")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.726
2
.644
3
.641
4
.638
5
.629
6
.610
7
.597
8
.597
9
.596
10
.582
11
.579
12
.578
13
.574
14
.569
15
.567
16
.564
17
.561
18
.558
19
.556
20
.556
21
.554
22
.551
23
.550
24
.548
25
.546
26
.541
27
.535
28
.535
29
.535
30
.521
31
.518
32
.517
33
.511
34
.507
35
.505
36
.502
37
.502
38
.501
39
.501
40
.500
41
.495
42
.494
43
.493
44
.490
45
.489
46
.489
47
.488
48
.484
49
.481
50
.480
51
.477
52
.476
53
.474
54
.473
55
.473
56
.470
57
.469
58
.468
59
.468
60
.468
61
.468
62
.465
63
.464
64
.464
65
.463
66
.459
67
.453
68
.453
69
.453
70
.451
71
.447
72
.445
73
.444
74
.443
75
.442
76
.441
77
.439
78
.438
79
.437
80
.433
81
.433
82
.432
83
.432
84
.429
85
.427
86
.424
87
.423
88
.420
89
.418
90
.418
91
.416
92
.415
93
.415
94
.415
95
.412
96
.412
97
.400
98
.399
99
.397
100
.395
101
.393
102
.391
103
.388
104
.383
105
.380
106
.379
107
.377
108
.373
109
.371
110
.369
111
.368
112
.366
113
.364
114
.363
115
.360
116
.360
117
.358
118
.357
119
.356
120
.353
121
.353
122
.352
123
.350
124
.346
125
.343
126
.340
127
.334
128
.333
129
.327
130
.324
131
.320
132
.320
133
.319
134
.319
135
.319
136
.318
137
.317
138
.316
139
.315
140
.314
141
.313
142
.313
143
.312
144
.309
145
.305
146
.304
147
.302
148
.302
149
.299
150
.299
151
.297
152
.297
153
.296
154
.295
155
.295
156
.294
157
.294
158
.292
159
.292
160
.291
161
.291
162
.291
163
.291
164
.290
165
.290
166
.287
167
.286
168
.286
169
.285
170
.284
171
.284
172
.283
173
.282
174
.281
175
.278
176
.277
177
.276
178
.274
179
.273
180
.273
181
.272
182
.271
183
.267
184
.263
185
.262
186
.261
187
.258
188
.257
189
.256
190
.255
191
.252
192
.252
193
.251
194
.250
195
.247
196
.245
197
.245
198
.244
199
.242
200
.241
201
.240
202
.238
203
.233
204
.231
205
.230
206
.228
207
.226
208
.221
209
.220
210
.219
211
.219
212
.219
213
.215
214
.214
215
.213
216
.212
217
.203
218
.200
219
.196
220
.190
221
.189
222
.174
223
.173
224
.171
225
.168
226
.168
227
.167
228
.167
229
.162
230
.161
231
.157
232
.154
233
.154
234
.151
235
.151
236
.146
237
.145
238
.142
239
.138
240
.137
241
.136
242
.135
243
.132
244
.130
245
.129
246
.129
247
.129
248
.129
249
.129
250
.129
251
.127
252
.126
253
.125
254
.124
255
.124
256
.124
257
.123
258
.123
259
.121
260
.121
261
.117
262
.113
263
.112
264
.112
265
.112
266
.112
267
.112
268
.108
269
.105
270
.105
271
.104
272
.103
273
.101
274
.099
275
.097
276
.096
277
.095
278
.094
279
.093
280
.093
281
.093
282
.091
283
.091
284
.090
285
.090
286
.089
287
.089
288
.085
289
.081
290
.080
291
.079
292
.078
293
.076
294
.071
295
.069
296
.063
297
.062
298
.057
299
.056
300
.042
301
.040
302
.039
303
.037
304
.037
305
.037
306
.037
307
.037
308
.036
309
.034
310
.033
311
.033
312
.028
313
.026
314
.023
315
.018
316
.010
317
.010
318
.007
319
.003
320
.001
321
.000
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
470
471
472
473
474
475
476
477
478
479
480

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

0.46.

Note that scores are relative to this ceiling.

Data: Geirhos2021eidolonIII

Metric: error_consistency