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
.357
42
.355
43
.346
44
.345
45
.344
46
.343
47
.332
48
.328
49
.327
50
.325
51
.321
52
.317
53
.316
54
.316
55
.316
56
.313
57
.311
58
.309
59
.309
60
.309
61
.300
62
.299
63
.297
64
.294
65
.293
66
.292
67
.292
68
.284
69
.284
70
.282
71
.278
72
.272
73
.271
74
.271
75
.266
76
.260
77
.255
78
.254
79
.254
80
.253
81
.253
82
.250
83
.244
84
.242
85
.240
86
.238
87
.237
88
.236
89
.236
90
.235
91
.235
92
.233
93
.233
94
.233
95
.233
96
.232
97
.232
98
.229
99
.229
100
.228
101
.228
102
.228
103
.226
104
.226
105
.226
106
.226
107
.220
108
.219
109
.218
110
.213
111
.213
112
.213
113
.212
114
.211
115
.210
116
.210
117
.210
118
.208
119
.208
120
.206
121
.204
122
.204
123
.202
124
.196
125
.195
126
.191
127
.191
128
.190
129
.189
130
.189
131
.189
132
.189
133
.188
134
.187
135
.186
136
.184
137
.182
138
.181
139
.181
140
.181
141
.180
142
.179
143
.179
144
.177
145
.177
146
.177
147
.175
148
.175
149
.173
150
.173
151
.173
152
.171
153
.167
154
.166
155
.166
156
.165
157
.164
158
.164
159
.163
160
.163
161
.162
162
.162
163
.160
164
.160
165
.160
166
.159
167
.157
168
.157
169
.157
170
.157
171
.156
172
.156
173
.155
174
.155
175
.154
176
.153
177
.153
178
.153
179
.153
180
.153
181
.153
182
.153
183
.153
184
.152
185
.152
186
.149
187
.147
188
.146
189
.146
190
.146
191
.145
192
.144
193
.144
194
.144
195
.144
196
.144
197
.142
198
.142
199
.141
200
.140
201
.137
202
.137
203
.136
204
.136
205
.135
206
.135
207
.135
208
.134
209
.134
210
.133
211
.133
212
.133
213
.132
214
.132
215
.132
216
.132
217
.132
218
.132
219
.131
220
.131
221
.131
222
.130
223
.128
224
.128
225
.128
226
.127
227
.127
228
.127
229
.125
230
.125
231
.125
232
.123
233
.122
234
.121
235
.121
236
.119
237
.117
238
.114
239
.112
240
.112
241
.110
242
.110
243
.109
244
.107
245
.106
246
.104
247
.102
248
.102
249
.102
250
.101
251
.101
252
.098
253
.098
254
.097
255
.096
256
.096
257
.096
258
.093
259
.091
260
.090
261
.090
262
.088
263
.087
264
.083
265
.083
266
.081
267
.079
268
.078
269
.068
270
.068
271
.068
272
.068
273
.067
274
.066
275
.066
276
.063
277
.060
278
.059
279
.055
280
.053
281
.052
282
.050
283
.049
284
.047
285
.046
286
.045
287
.034
288
.034
289
.032
290
.032
291
.031
292
.028
293
.013
294
.011
295
.011
296
.011
297
.003
298
.003
299
.003
300
.003
301
.003
302
.003
303
304
305
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

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