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
.569
16
.567
17
.564
18
.561
19
.558
20
.556
21
.556
22
.554
23
.551
24
.550
25
.548
26
.546
27
.541
28
.535
29
.535
30
.535
31
.523
32
.521
33
.518
34
.517
35
.511
36
.507
37
.505
38
.505
39
.502
40
.502
41
.502
42
.501
43
.501
44
.500
45
.495
46
.494
47
.490
48
.489
49
.489
50
.484
51
.483
52
.480
53
.479
54
.477
55
.477
56
.476
57
.474
58
.473
59
.473
60
.470
61
.469
62
.468
63
.468
64
.468
65
.468
66
.465
67
.464
68
.464
69
.459
70
.453
71
.453
72
.453
73
.451
74
.445
75
.444
76
.443
77
.442
78
.441
79
.439
80
.438
81
.437
82
.433
83
.433
84
.432
85
.432
86
.431
87
.429
88
.427
89
.424
90
.423
91
.420
92
.418
93
.416
94
.415
95
.415
96
.415
97
.415
98
.412
99
.412
100
.400
101
.399
102
.397
103
.395
104
.393
105
.391
106
.391
107
.388
108
.383
109
.380
110
.379
111
.377
112
.373
113
.371
114
.369
115
.368
116
.366
117
.364
118
.363
119
.363
120
.360
121
.360
122
.359
123
.357
124
.356
125
.353
126
.353
127
.352
128
.350
129
.346
130
.343
131
.340
132
.334
133
.333
134
.333
135
.327
136
.324
137
.320
138
.320
139
.319
140
.319
141
.319
142
.318
143
.317
144
.316
145
.315
146
.314
147
.313
148
.313
149
.312
150
.309
151
.307
152
.305
153
.304
154
.302
155
.302
156
.299
157
.299
158
.297
159
.297
160
.296
161
.295
162
.295
163
.294
164
.294
165
.292
166
.292
167
.291
168
.291
169
.291
170
.291
171
.290
172
.290
173
.287
174
.286
175
.286
176
.285
177
.284
178
.284
179
.283
180
.282
181
.281
182
.278
183
.277
184
.276
185
.274
186
.273
187
.273
188
.272
189
.271
190
.267
191
.263
192
.262
193
.261
194
.258
195
.258
196
.257
197
.256
198
.255
199
.252
200
.252
201
.251
202
.250
203
.247
204
.245
205
.245
206
.244
207
.242
208
.241
209
.240
210
.238
211
.233
212
.231
213
.230
214
.228
215
.226
216
.221
217
.220
218
.219
219
.219
220
.219
221
.215
222
.214
223
.213
224
.212
225
.203
226
.200
227
.196
228
.190
229
.189
230
.174
231
.173
232
.171
233
.168
234
.168
235
.167
236
.167
237
.162
238
.161
239
.157
240
.154
241
.154
242
.151
243
.151
244
.146
245
.145
246
.142
247
.138
248
.137
249
.136
250
.135
251
.132
252
.130
253
.129
254
.129
255
.129
256
.129
257
.129
258
.129
259
.127
260
.125
261
.124
262
.124
263
.124
264
.123
265
.123
266
.121
267
.121
268
.117
269
.113
270
.112
271
.112
272
.112
273
.112
274
.112
275
.108
276
.105
277
.105
278
.104
279
.103
280
.101
281
.099
282
.097
283
.096
284
.095
285
.094
286
.093
287
.093
288
.093
289
.091
290
.091
291
.090
292
.090
293
.089
294
.089
295
.085
296
.081
297
.080
298
.079
299
.078
300
.076
301
.071
302
.069
303
.063
304
.062
305
.057
306
.056
307
.042
308
.040
309
.037
310
.037
311
.037
312
.037
313
.037
314
.036
315
.034
316
.033
317
.033
318
.028
319
.026
320
.023
321
.018
322
.010
323
.010
324
.007
325
.003
326
.001
327
.000
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
481
482
483
484
485
486
487
488
489

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