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("Geirhos2021cueconflict-error_consistency")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.943
2
.938
3
.855
4
.840
5
.804
6
.784
7
.780
8
.752
9
.748
10
.740
11
.698
12
.686
13
.656
14
.651
15
.633
16
.611
17
.596
18
.595
19
.571
20
.560
21
.560
22
.546
23
.540
24
.482
25
.477
26
.451
27
.448
28
.441
29
.405
30
.402
31
.394
32
.393
33
.390
34
.383
35
.380
36
.376
37
.372
38
.371
39
.371
40
.357
41
.355
42
.346
43
.345
44
.344
45
.343
46
.332
47
.328
48
.327
49
.325
50
.321
51
.317
52
.316
53
.316
54
.316
55
.313
56
.311
57
.309
58
.309
59
.309
60
.300
61
.299
62
.297
63
.294
64
.293
65
.292
66
.292
67
.284
68
.284
69
.282
70
.278
71
.272
72
.271
73
.271
74
.266
75
.260
76
.255
77
.254
78
.254
79
.253
80
.253
81
.250
82
.244
83
.242
84
.240
85
.238
86
.237
87
.236
88
.236
89
.235
90
.235
91
.233
92
.233
93
.233
94
.233
95
.232
96
.232
97
.229
98
.229
99
.228
100
.228
101
.228
102
.226
103
.226
104
.226
105
.226
106
.220
107
.219
108
.218
109
.213
110
.213
111
.213
112
.212
113
.211
114
.210
115
.210
116
.210
117
.208
118
.208
119
.206
120
.204
121
.204
122
.202
123
.196
124
.191
125
.191
126
.190
127
.189
128
.189
129
.189
130
.189
131
.188
132
.187
133
.186
134
.184
135
.182
136
.181
137
.181
138
.181
139
.180
140
.179
141
.179
142
.177
143
.177
144
.177
145
.175
146
.175
147
.173
148
.173
149
.173
150
.171
151
.167
152
.166
153
.166
154
.165
155
.164
156
.164
157
.163
158
.163
159
.162
160
.162
161
.160
162
.160
163
.160
164
.159
165
.157
166
.157
167
.157
168
.157
169
.156
170
.156
171
.155
172
.155
173
.154
174
.153
175
.153
176
.153
177
.153
178
.153
179
.153
180
.153
181
.153
182
.152
183
.152
184
.149
185
.147
186
.146
187
.146
188
.146
189
.145
190
.144
191
.144
192
.144
193
.144
194
.144
195
.142
196
.142
197
.141
198
.140
199
.137
200
.137
201
.136
202
.136
203
.135
204
.135
205
.135
206
.134
207
.134
208
.133
209
.133
210
.133
211
.132
212
.132
213
.132
214
.132
215
.132
216
.132
217
.131
218
.131
219
.131
220
.130
221
.128
222
.128
223
.128
224
.128
225
.128
226
.128
227
.128
228
.128
229
.128
230
.128
231
.128
232
.128
233
.128
234
.127
235
.127
236
.127
237
.125
238
.125
239
.125
240
.123
241
.122
242
.121
243
.121
244
.121
245
.119
246
.117
247
.114
248
.112
249
.112
250
.110
251
.110
252
.109
253
.107
254
.106
255
.104
256
.102
257
.102
258
.102
259
.101
260
.101
261
.098
262
.098
263
.097
264
.096
265
.096
266
.096
267
.093
268
.091
269
.090
270
.090
271
.088
272
.087
273
.083
274
.083
275
.081
276
.079
277
.078
278
.068
279
.068
280
.068
281
.068
282
.067
283
.066
284
.066
285
.063
286
.060
287
.059
288
.055
289
.053
290
.052
291
.050
292
.049
293
.047
294
.046
295
.045
296
.034
297
.034
298
.032
299
.032
300
.031
301
.028
302
.013
303
.011
304
.011
305
.011
306
.003
307
.003
308
.003
309
.003
310
.003
311
.003
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

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

0.33.

Note that scores are relative to this ceiling.

Data: Geirhos2021cueconflict

Metric: error_consistency