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
.781
2
.776
3
.774
4
.750
5
.748
6
.747
7
.746
8
.746
9
.745
10
.743
11
.742
12
.741
13
.739
14
.738
15
.737
16
.735
17
.734
18
.734
19
.734
20
.732
21
.731
22
.731
23
.729
24
.729
25
.727
26
.727
27
.724
28
.721
29
.720
30
.720
31
.718
32
.717
33
.717
34
.716
35
.716
36
.715
37
.715
38
.713
39
.712
40
.712
41
.711
42
.711
43
.710
44
.709
45
.707
46
.705
47
.705
48
.705
49
.703
50
.703
51
.701
52
.701
53
.701
54
.700
55
.699
56
.699
57
.698
58
.697
59
.695
60
.692
61
.692
62
.691
63
.690
64
.689
65
.688
66
.688
67
.688
68
.688
69
.687
70
.686
71
.686
72
.686
73
.686
74
.685
75
.685
76
.685
77
.684
78
.684
79
.684
80
.683
81
.683
82
.681
83
.681
84
.681
85
.680
86
.680
87
.680
88
.680
89
.679
90
.679
91
.678
92
.678
93
.676
94
.676
95
.676
96
.676
97
.675
98
.674
99
.674
100
.673
101
.672
102
.672
103
.671
104
.669
105
.669
106
.669
107
.668
108
.668
109
.667
110
.667
111
.667
112
.667
113
.667
114
.667
115
.667
116
.667
117
.666
118
.666
119
.666
120
.666
121
.665
122
.663
123
.661
124
.660
125
.660
126
.659
127
.659
128
.658
129
.657
130
.656
131
.656
132
.656
133
.656
134
.656
135
.656
136
.654
137
.653
138
.653
139
.651
140
.650
141
.649
142
.649
143
.649
144
.648
145
.648
146
.648
147
.648
148
.647
149
.647
150
.647
151
.647
152
.646
153
.646
154
.646
155
.646
156
.644
157
.644
158
.644
159
.643
160
.642
161
.640
162
.640
163
.639
164
.638
165
.638
166
.638
167
.635
168
.632
169
.627
170
.625
171
.625
172
.624
173
.624
174
.624
175
.618
176
.617
177
.617
178
.616
179
.616
180
.615
181
.613
182
.613
183
.610
184
.609
185
.609
186
.607
187
.606
188
.604
189
.604
190
.596
191
.578
192
.578
193
.576
194
.569
195
.569
196
.568
197
.565
198
.565
199
.561
200
.554
201
.553
202
.550
203
.550
204
.549
205
.547
206
.545
207
.541
208
.541
209
.541
210
.536
211
.535
212
.534
213
.534
214
.531
215
.531
216
.528
217
.525
218
.525
219
.522
220
.521
221
.521
222
.520
223
.507
224
.507
225
.502
226
.499
227
.498
228
.498
229
.494
230
.484
231
.484
232
.484
233
.484
234
.482
235
.482
236
.479
237
.478
238
.478
239
.476
240
.470
241
.470
242
.470
243
.462
244
.462
245
.461
246
.450
247
.448
248
.437
249
.433
250
.416
251
.412
252
.407
253
.395
254
.395
255
.395
256
.395
257
.383
258
.380
259
.379
260
.367
261
.366
262
.363
263
.358
264
.349
265
.349
266
.344
267
.343
268
.341
269
.326
270
.325
271
.323
272
.323
273
.296
274
.266
275
.237
276
.217
277
.210
278
.204
279
.125
280
.067
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299

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