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("Maniquet2024-tasks_consistency")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.789
2
.781
3
.776
4
.774
5
.750
6
.748
7
.747
8
.746
9
.746
10
.746
11
.745
12
.742
13
.742
14
.741
15
.739
16
.738
17
.737
18
.735
19
.734
20
.734
21
.734
22
.732
23
.731
24
.731
25
.729
26
.729
27
.727
28
.727
29
.724
30
.718
31
.717
32
.717
33
.716
34
.716
35
.715
36
.715
37
.713
38
.712
39
.712
40
.711
41
.710
42
.709
43
.707
44
.705
45
.705
46
.703
47
.703
48
.701
49
.701
50
.701
51
.700
52
.699
53
.698
54
.697
55
.695
56
.692
57
.692
58
.691
59
.690
60
.689
61
.688
62
.688
63
.688
64
.688
65
.687
66
.686
67
.686
68
.686
69
.685
70
.685
71
.685
72
.684
73
.684
74
.683
75
.683
76
.681
77
.681
78
.681
79
.681
80
.681
81
.680
82
.680
83
.680
84
.680
85
.679
86
.679
87
.678
88
.678
89
.676
90
.676
91
.676
92
.676
93
.675
94
.674
95
.674
96
.673
97
.672
98
.672
99
.671
100
.669
101
.669
102
.669
103
.668
104
.668
105
.667
106
.667
107
.667
108
.667
109
.667
110
.667
111
.667
112
.667
113
.666
114
.666
115
.666
116
.666
117
.665
118
.663
119
.661
120
.660
121
.660
122
.659
123
.659
124
.658
125
.657
126
.656
127
.656
128
.656
129
.656
130
.656
131
.656
132
.654
133
.653
134
.653
135
.651
136
.650
137
.649
138
.649
139
.649
140
.648
141
.648
142
.648
143
.648
144
.647
145
.647
146
.647
147
.647
148
.646
149
.646
150
.646
151
.646
152
.644
153
.644
154
.644
155
.643
156
.642
157
.640
158
.640
159
.639
160
.638
161
.638
162
.638
163
.635
164
.632
165
.627
166
.625
167
.625
168
.624
169
.624
170
.624
171
.618
172
.617
173
.617
174
.616
175
.616
176
.615
177
.613
178
.613
179
.610
180
.609
181
.609
182
.607
183
.606
184
.604
185
.604
186
.596
187
.578
188
.578
189
.576
190
.569
191
.569
192
.568
193
.565
194
.565
195
.561
196
.554
197
.553
198
.550
199
.550
200
.549
201
.547
202
.545
203
.541
204
.541
205
.541
206
.536
207
.535
208
.534
209
.534
210
.531
211
.531
212
.528
213
.525
214
.525
215
.522
216
.521
217
.521
218
.520
219
.507
220
.507
221
.502
222
.499
223
.498
224
.498
225
.494
226
.484
227
.484
228
.484
229
.484
230
.482
231
.482
232
.479
233
.478
234
.478
235
.476
236
.470
237
.470
238
.470
239
.462
240
.462
241
.461
242
.450
243
.448
244
.437
245
.433
246
.416
247
.412
248
.407
249
.395
250
.395
251
.395
252
.395
253
.383
254
.380
255
.379
256
.367
257
.366
258
.363
259
.358
260
.349
261
.349
262
.344
263
.343
264
.341
265
.326
266
.325
267
.323
268
.323
269
.296
270
.266
271
.237
272
.217
273
.210
274
.204
275
.125
276
.067
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303

Benchmark bibtex

@article {Maniquet2024.04.02.587669,
	author = {Maniquet, Tim and de Beeck, Hans Op and Costantino, Andrea Ivan},
	title = {Recurrent issues with deep neural network models of visual recognition},
	elocation-id = {2024.04.02.587669},
	year = {2024},
	doi = {10.1101/2024.04.02.587669},
	publisher = {Cold Spring Harbor Laboratory},
	URL = {https://www.biorxiv.org/content/early/2024/04/10/2024.04.02.587669},
	eprint = {https://www.biorxiv.org/content/early/2024/04/10/2024.04.02.587669.full.pdf},
	journal = {bioRxiv}
}

Ceiling

1.00.

Note that scores are relative to this ceiling.

Data: Maniquet2024

Metric: tasks_consistency