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
.950
14
.946
15
.944
16
.928
17
.928
18
.928
19
.928
20
.917
21
.896
22
.893
23
.892
24
.890
25
.886
26
.886
27
.878
28
.873
29
.873
30
.867
31
.858
32
.850
33
.832
34
.832
35
.832
36
.832
37
.831
38
.826
39
.823
40
.822
41
.821
42
.820
43
.818
44
.813
45
.813
46
.808
47
.808
48
.804
49
.803
50
.798
51
.798
52
.794
53
.793
54
.785
55
.763
56
.759
57
.759
58
.753
59
.753
60
.753
61
.751
62
.751
63
.749
64
.748
65
.743
66
.738
67
.738
68
.737
69
.736
70
.729
71
.710
72
.708
73
.708
74
.695
75
.689
76
.679
77
.678
78
.677
79
.669
80
.668
81
.665
82
.665
83
.662
84
.651
85
.645
86
.640
87
.634
88
.632
89
.632
90
.630
91
.626
92
.622
93
.607
94
.607
95
.603
96
.600
97
.598
98
.596
99
.587
100
.586
101
.583
102
.571
103
.569
104
.568
105
.565
106
.564
107
.562
108
.562
109
.562
110
.561
111
.560
112
.559
113
.556
114
.555
115
.555
116
.553
117
.553
118
.552
119
.547
120
.546
121
.543
122
.541
123
.541
124
.540
125
.538
126
.535
127
.533
128
.533
129
.530
130
.529
131
.524
132
.520
133
.520
134
.516
135
.513
136
.508
137
.508
138
.504
139
.502
140
.502
141
.502
142
.500
143
.498
144
.498
145
.497
146
.496
147
.496
148
.495
149
.494
150
.490
151
.490
152
.488
153
.487
154
.486
155
.486
156
.482
157
.482
158
.480
159
.475
160
.473
161
.473
162
.472
163
.465
164
.460
165
.460
166
.459
167
.456
168
.454
169
.453
170
.453
171
.453
172
.452
173
.450
174
.448
175
.446
176
.444
177
.441
178
.440
179
.438
180
.437
181
.436
182
.436
183
.435
184
.431
185
.430
186
.428
187
.424
188
.419
189
.418
190
.418
191
.416
192
.412
193
.410
194
.409
195
.407
196
.407
197
.406
198
.406
199
.403
200
.395
201
.392
202
.387
203
.381
204
.375
205
.371
206
.367
207
.365
208
.365
209
.362
210
.358
211
.355
212
.351
213
.348
214
.348
215
.346
216
.345
217
.341
218
.341
219
.341
220
.340
221
.337
222
.326
223
.326
224
.324
225
.324
226
.323
227
.322
228
.317
229
.315
230
.314
231
.312
232
.305
233
.302
234
.298
235
.293
236
.289
237
.287
238
.284
239
.281
240
.280
241
.280
242
.277
243
.270
244
.270
245
.262
246
.258
247
.257
248
.255
249
.249
250
.247
251
.239
252
.238
253
.232
254
.227
255
.220
256
.212
257
.209
258
.206
259
.197
260
.195
261
.195
262
.194
263
.192
264
.189
265
.186
266
.183
267
.179
268
.175
269
.167
270
.164
271
.163
272
.162
273
.156
274
.138
275
.123
276
.106
277
.100
278
.098
279
.092
280
.085
281
.065
282
.062
283
.060
284
.019
285
.000
286
.000
287
.000
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312

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