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-confusion_similarity")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
1.0
2
1.0
3
1.0
4
1.0
5
1.0
6
1.0
7
1.0
8
1.0
9
1.0
10
.994
11
.955
12
.946
13
.944
14
.928
15
.928
16
.928
17
.917
18
.896
19
.893
20
.892
21
.890
22
.886
23
.878
24
.873
25
.873
26
.858
27
.850
28
.832
29
.832
30
.832
31
.832
32
.831
33
.826
34
.823
35
.822
36
.821
37
.820
38
.818
39
.813
40
.813
41
.808
42
.808
43
.804
44
.803
45
.798
46
.798
47
.794
48
.793
49
.785
50
.763
51
.759
52
.759
53
.753
54
.753
55
.753
56
.751
57
.751
58
.748
59
.743
60
.738
61
.738
62
.737
63
.736
64
.729
65
.710
66
.708
67
.708
68
.695
69
.679
70
.677
71
.669
72
.668
73
.665
74
.665
75
.662
76
.651
77
.645
78
.640
79
.632
80
.632
81
.630
82
.626
83
.603
84
.600
85
.598
86
.596
87
.586
88
.571
89
.569
90
.568
91
.562
92
.562
93
.562
94
.559
95
.555
96
.555
97
.553
98
.553
99
.552
100
.547
101
.546
102
.541
103
.540
104
.538
105
.535
106
.533
107
.533
108
.530
109
.529
110
.524
111
.520
112
.520
113
.516
114
.513
115
.508
116
.508
117
.502
118
.500
119
.498
120
.498
121
.497
122
.496
123
.496
124
.495
125
.494
126
.490
127
.490
128
.488
129
.487
130
.486
131
.482
132
.482
133
.480
134
.475
135
.473
136
.473
137
.472
138
.460
139
.460
140
.459
141
.456
142
.454
143
.453
144
.453
145
.452
146
.450
147
.448
148
.444
149
.441
150
.438
151
.437
152
.436
153
.436
154
.435
155
.431
156
.428
157
.424
158
.419
159
.418
160
.418
161
.416
162
.412
163
.410
164
.409
165
.407
166
.407
167
.406
168
.403
169
.395
170
.392
171
.381
172
.375
173
.371
174
.365
175
.365
176
.362
177
.358
178
.355
179
.351
180
.348
181
.348
182
.346
183
.345
184
.341
185
.341
186
.341
187
.340
188
.337
189
.326
190
.326
191
.324
192
.324
193
.323
194
.322
195
.318
196
.315
197
.314
198
.312
199
.305
200
.302
201
.298
202
.289
203
.287
204
.284
205
.281
206
.280
207
.277
208
.270
209
.270
210
.262
211
.255
212
.249
213
.247
214
.239
215
.238
216
.232
217
.227
218
.220
219
.212
220
.206
221
.197
222
.195
223
.195
224
.194
225
.192
226
.189
227
.186
228
.183
229
.175
230
.167
231
.164
232
.163
233
.162
234
.156
235
.138
236
.123
237
.106
238
.100
239
.098
240
.092
241
.085
242
.062
243
.019
244
.000
245
.000
246
.000
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264

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

0.54.

Note that scores are relative to this ceiling.

Data: Maniquet2024

Metric: confusion_similarity