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("tong.Coggan2024_fMRI.V2-rdm")
score = benchmark(my_model)

Model scores

Min Alignment Max Alignment

Rank

Model

Score

1
.636
2
.630
3
.626
4
.578
5
.571
6
.570
7
.492
8
.490
9
.485
10
.458
11
.455
12
.438
13
.415
14
.407
15
.383
16
.372
17
.369
18
.361
19
.361
20
.335
21
.335
22
.327
23
.313
24
.311
25
.303
26
.285
27
.281
28
.278
29
.273
30
.269
31
.268
32
.263
33
.262
34
.255
35
.254
36
.252
37
.247
38
.231
39
.227
40
.220
41
.220
42
.216
43
.212
44
.206
45
.206
46
.203
47
.201
48
.200
49
.199
50
.197
51
.194
52
.189
53
.183
54
.181
55
.178
56
.178
57
.175
58
.172
59
.170
60
.167
61
.167
62
.164
63
.163
64
.163
65
.161
66
.159
67
.159
68
.155
69
.149
70
.148
71
.147
72
.145
73
.143
74
.142
75
.141
76
.138
77
.138
78
.137
79
.135
80
.134
81
.133
82
.133
83
.133
84
.131
85
.130
86
.121
87
.121
88
.121
89
.121
90
.121
91
.120
92
.119
93
.118
94
.118
95
.117
96
.116
97
.114
98
.112
99
.111
100
.111
101
.107
102
.107
103
.107
104
.107
105
.106
106
.105
107
.105
108
.104
109
.101
110
.100
111
.100
112
.097
113
.097
114
.097
115
.097
116
.096
117
.094
118
.094
119
.094
120
.092
121
.089
122
.089
123
.088
124
.087
125
.086
126
.085
127
.084
128
.081
129
.080
130
.080
131
.080
132
.079
133
.078
134
.077
135
.076
136
.074
137
.074
138
.073
139
.073
140
.072
141
.072
142
.071
143
.069
144
.067
145
.064
146
.063
147
.063
148
.062
149
.061
150
.061
151
.061
152
.061
153
.061
154
.061
155
.059
156
.058
157
.057
158
.057
159
.057
160
.056
161
.056
162
.055
163
.054
164
.053
165
.052
166
.051
167
.050
168
.048
169
.047
170
.047
171
.047
172
.045
173
.044
174
.044
175
.043
176
.043
177
.041
178
.040
179
.040
180
.040
181
.040
182
.040
183
.038
184
.038
185
.037
186
.037
187
.037
188
.037
189
.037
190
.036
191
.036
192
.036
193
.036
194
.035
195
.035
196
.034
197
.033
198
.033
199
.033
200
.033
201
.032
202
.032
203
.032
204
.031
205
.031
206
.031
207
.030
208
.030
209
.030
210
.030
211
.029
212
.029
213
.028
214
.028
215
.027
216
.026
217
.026
218
.026
219
.025
220
.025
221
.025
222
.025
223
.024
224
.024
225
.024
226
.023
227
.023
228
.023
229
.022
230
.022
231
.021
232
.021
233
.020
234
.020
235
.020
236
.018
237
.018
238
.016
239
.016
240
.016
241
.016
242
.015
243
.015
244
.014
245
.014
246
.014
247
.014
248
.014
249
.013
250
.012
251
.011
252
.011
253
.010
254
.010
255
.010
256
.009
257
.008
258
.008
259
.006
260
.005
261
.005
262
.005
263
.004
264
.004
265
.004
266
.003
267
.003
268
.003
269
.003
270
.003
271
.002
272
.002
273
.002
274
.001
275
.001
276
.001
277
.001
278
.001
279
.000
280
.000
281
.000
282
.000
283
.000
284
.000
285
.000
286
.000
287
.001
288
.001
289
.001
290
.001
291
.002
292
.002
293
.003
294
.003
295
.005
296
297
1.0
298
1.0
299
1.0
300
1.0
301
302
303
304
305
306
307
308

Benchmark bibtex

@inproceedings{santurkar2019computer,
    title={Computer Vision with a Single (Robust) Classifier},
    author={Shibani Santurkar and Dimitris Tsipras and Brandon Tran and Andrew Ilyas and Logan Engstrom and Aleksander Madry},
    booktitle={ArXiv preprint arXiv:1906.09453},
    year={2019}
}

Ceiling

0.45.

Note that scores are relative to this ceiling.

Data: tong.Coggan2024_fMRI.V2

Metric: rdm