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
1.0
11
.994
12
.955
13
.946
14
.944
15
.928
16
.928
17
.928
18
.928
19
.917
20
.896
21
.893
22
.892
23
.890
24
.886
25
.886
26
.878
27
.873
28
.873
29
.867
30
.858
31
.850
32
.832
33
.832
34
.832
35
.832
36
.831
37
.826
38
.823
39
.822
40
.821
41
.820
42
.818
43
.813
44
.813
45
.808
46
.808
47
.804
48
.803
49
.798
50
.798
51
.794
52
.793
53
.785
54
.763
55
.759
56
.759
57
.753
58
.753
59
.753
60
.751
61
.751
62
.748
63
.743
64
.738
65
.738
66
.737
67
.736
68
.729
69
.710
70
.708
71
.708
72
.695
73
.689
74
.679
75
.678
76
.677
77
.669
78
.668
79
.665
80
.665
81
.662
82
.651
83
.645
84
.640
85
.634
86
.632
87
.632
88
.630
89
.626
90
.622
91
.607
92
.607
93
.603
94
.600
95
.598
96
.596
97
.587
98
.586
99
.583
100
.571
101
.569
102
.568
103
.565
104
.564
105
.562
106
.562
107
.562
108
.561
109
.560
110
.559
111
.556
112
.555
113
.555
114
.553
115
.553
116
.552
117
.547
118
.546
119
.541
120
.541
121
.540
122
.538
123
.535
124
.533
125
.533
126
.530
127
.529
128
.524
129
.520
130
.520
131
.516
132
.513
133
.508
134
.508
135
.502
136
.502
137
.502
138
.500
139
.498
140
.498
141
.497
142
.496
143
.496
144
.495
145
.494
146
.490
147
.490
148
.488
149
.487
150
.486
151
.486
152
.482
153
.482
154
.480
155
.475
156
.473
157
.473
158
.472
159
.460
160
.460
161
.459
162
.456
163
.454
164
.453
165
.453
166
.452
167
.450
168
.448
169
.444
170
.441
171
.438
172
.437
173
.436
174
.436
175
.435
176
.431
177
.430
178
.428
179
.424
180
.419
181
.418
182
.418
183
.416
184
.412
185
.410
186
.409
187
.407
188
.407
189
.406
190
.406
191
.403
192
.395
193
.392
194
.387
195
.381
196
.375
197
.371
198
.367
199
.365
200
.365
201
.362
202
.358
203
.355
204
.351
205
.348
206
.348
207
.346
208
.345
209
.341
210
.341
211
.341
212
.340
213
.337
214
.326
215
.326
216
.324
217
.324
218
.323
219
.322
220
.318
221
.317
222
.315
223
.314
224
.312
225
.305
226
.302
227
.298
228
.293
229
.289
230
.287
231
.284
232
.281
233
.280
234
.280
235
.277
236
.270
237
.270
238
.262
239
.258
240
.255
241
.249
242
.247
243
.239
244
.238
245
.232
246
.227
247
.220
248
.212
249
.209
250
.206
251
.197
252
.195
253
.195
254
.194
255
.192
256
.189
257
.186
258
.183
259
.175
260
.167
261
.164
262
.163
263
.162
264
.156
265
.138
266
.123
267
.106
268
.100
269
.098
270
.092
271
.085
272
.065
273
.062
274
.019
275
.000
276
.000
277
.000
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

0.54.

Note that scores are relative to this ceiling.

Data: Maniquet2024

Metric: confusion_similarity