Leaderboard Explore Compare Profile Community Blog FAQ Competition 2024 Report Issue

Sample stimuli

How to use

from brainscore_vision import load_benchmark
benchmark = load_benchmark("Zerbe2026_fmri.IT-ood-ridgecv")
score = benchmark(my_model)

Benchmark API

Code examples

Model scores

Score Legend Min Alignment Max Alignment

Rank	Model	Score
1	resnext101_32x48d_wsl	.267
2	resnext101_32x32d_wsl	.263
3	resnext101_32x16d_wsl	.254
4	vit_relpos_base_patch16_clsgap_224:sw_in1k	.251
5	convnext_tiny:in12k_ft_in1k	.243
6	vit_large_patch14_clip_224:laion2b_ft_in12k_in1k	.243
7	dinov2_vitg14_reg_lc	.241
8	deit_small_imagenet_full_seed-0	.244
9	resnet50-moclr8deg	.239
10	deit_large_imagenet_full_seed-0	.242
11	convnext_xxlarge:clip_laion2b_soup_ft_in1k	.235
12	densenet-121	.235
13	pnasnet_large_halfPrecision	.235
14	deit_base_imagenet_full_seed-0	.238
15	ReAlnet01_cornet	.232
16	dinov2_vitl14_lc	.231
17	convnext_large:fb_in22k_ft_in1k	.231
18	ReAlnet04_cornet	.230
19	convnext_tiny_sup	.230
20	focalnet_tiny_lrf_in1k	.230
21	convnext_base_imagenet_full_seed-0	.230
22	ReAlnet03_cornet	.229
23	resnet_50_v2	.229
24	convnext_large_imagenet_full_seed-0	.228
25	convnext_base:clip_laiona_augreg_ft_in1k_384	.228
26	Res2Net50_26w_4s	.228
27	resnet50-SIN_IN_IN	.227
28	dinov2_vitl14_lc_res336	.227
29	vit_large_patch14_clip_336:laion2b_ft_in1k	.225
30	VOneCORnet-S	.224
31	resnet50-SIN_IN	.223
32	resnet152_imagenet_full	.222
33	vit_base_patch16_clip_224:openai_ft_in12k_in1k	.223
34	resnet_50_v1_spiking	.222
35	resnet_50_v1	.222
36	resnet50-sup	.222
37	antialiased-r50	.222
38	resnet50_ewconplus_wzc	.222
39	vit_large_patch14_clip_336:openai_ft_in12k_in1k	.221
40	voneresnet-50	.221
41	eva02_large_in22k	.222
42	resnet50_tutorial	.221
43	seresnext50_32x4d	.224
44	regnety_032	.223
45	vit_base_patch16_clip_224:openai_ft_in1k	.220
46	vit_large_patch14_clip_224:openai_ft_in1k	.220
47	resnet_SIN_IN_FT_IN	.217
48	dinov2_vitl14_reg_lc_featread	.216
49	dinov2_vitl14_reg_lc	.216
50	convnext_femto_ols:d1_in1k	.215
51	convnext_small_imagenet_full_seed-0	.215
52	vit_tiny_r_s16_p8_384:augreg_in21k_ft_in1k	.214
53	voneresnet-50-non_stochastic	.213
54	custom_model_cv_18_dagger_408	.213
55	shufflenet_v2_x1_0	.212
56	convnext_tiny_imagenet_full_seed-0	.212
57	vit_large_patch14_clip_224:openai_ft_in12k_in1k	.211
58	resnet50-vitoimagevidnet8	.211
59	resnet50-VITO-8deg-cc	.211
60	effnetb1_cutmix_augmix_sam_e1_5avg_424x377	.210
61	resnet50_robust_l2_eps1	.210
62	resnext101_32x8d_wsl	.210
63	convnext_large_mlp:clip_laion2b_augreg_ft_in1k_384	.209
64	eicircuit_resnet18_bn_20260919	.212
65	effnetb1_272x240	.208
66	resnet50_imagenet_full	.208
67	cvt_cvt-w24-384-in22k_finetuned-in1k_4	.208
68	convnext_xxlarge_clip	.207
69	vit_huge_clip336_laion	.205
70	efficientnet_b2_imagenet_full	.204
71	vit_relpos_base_patch32_plus_rpn_256:sw_in1k	.203
72	mobilenet_v2_1_4_224	.203
73	efficientnet_b0	.202
74	vit_large_patch14_clip_224:laion2b_ft_in1k	.200
75	cvt_cvt-13-224-in1k_4_LucyV4	.199
76	swin_small_patch4_window7_224:ms_in22k_ft_in1k	.193
77	cvt_cvt-21-224-in1k_4_LucyV4	.191
78	vit_huge_patch14_clip_224:laion2b_ft_in12k_in1k	.190
79	AT_efficientnet-b2	.189
80	AdvProp_efficientnet-b2	.189
81	convnext_xlarge:fb_in22k_ft_in1k	.188
82	cvt_cvt-21-384-in1k_4_LucyV4	.188
83	dinov2_vitg14_lc	.187
84	alexnet	.184
85	AdvProp_efficientnet-b7	.182
86	cvt_cvt-13-384-in22k_finetuned-in1k_4_LucyV4	.183
87	resnet50-SIN	.182
88	ReAlnet01_cornet_fov4	.181
89	effnetb1_cutmixpatch_SAM_robust32_avge6e8e9e10_manylayers_324x288	.180
90	AdvProp_efficientnet-b8	.177
91	cvt_cvt-13-384-in1k_4_LucyV4	.177
92	cvt_cvt-21-384-in22k_finetuned-in1k_4_LucyV4	.175
93	AdvProp_efficientnet-b4	.174
94	AdvProp_efficientnet-b6	.173
95	effnetb1_cutmixpatch_augmix_robust32_avge4e7_manylayers_324x288	.171
96	resnet-50-robust	.169
97	vit_large_clip336_openai	.171
98	ViT_L_32_imagenet1k	.167
99	grcnn	.166
100	AlexNet_SIN	.119
101	AlexNet_SIN_fov12	.098
102	hmax	.074
103	AlexNet_SIN_fov16	.072
104	gabor_filter_entropy_4x4	.060
105	gabor_filter_entropy_4x4_v2	.052
106	gabor_filter_entropy_4x4_v2_forcedCosine	.048
107	gabor_filter_mean_abs_4x4_v2	.023
108	alexnet_training_seed_06	.021
109	alexnet_training_seed_01	.020
110	alexnet_training_seed_10	.019
111	alexnet_training_seed_02	.018
112	alexnet_training_seed_09	.016
113	compact_resnet50_robust_V4	.015
114	alexnet_training_seed_07	.014
115	alexnet_training_seed_03	.011

Benchmark bibtex

@inproceedings{zerbe_laion-fmri_2026,
      title = {{LAION}-{fMRI}: A densely sampled 7T-fMRI dataset providing broad coverage of natural image diversity},
      author = {Zerbe, Josefine and Roth, Johannes and Mell, Maggie Mae and Herholz, Peer and Knapen, Tomas and Hebart, Martin N.},
      year = {2026},
      booktitle = {Vision Sciences Society Annual Meeting},
  }

Ceiling

0.76.

Note that scores are relative to this ceiling.

Data: Zerbe2026_fmri.IT-ood

Metric: ridgecv