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.V4-ood-ridgecv")
score = benchmark(my_model)

Benchmark API

Code examples

Model scores

Score Legend Min Alignment Max Alignment

Rank	Model	Score
1	vit_huge_clip336_laion	.442
2	custom_model_cv_18_dagger_408	.438
3	convnext_large:fb_in22k_ft_in1k	.434
4	convnext_xxlarge:clip_laion2b_soup_ft_in1k	.430
5	cvt_cvt-21-224-in1k_4_LucyV4	.426
6	dinov2_vitg14_reg_lc	.425
7	convnext_xlarge:fb_in22k_ft_in1k	.423
8	cvt_cvt-13-224-in1k_4_LucyV4	.423
9	resnet50_ewconplus_wzc	.420
10	ReAlnet01_cornet	.421
11	ReAlnet03_cornet	.420
12	ReAlnet04_cornet	.419
13	dinov2_vitg14_lc	.418
14	vit_large_clip336_openai	.418
15	pnasnet_large_halfPrecision	.417
16	dinov2_vitl14_lc_res336	.415
17	cvt_cvt-w24-384-in22k_finetuned-in1k_4	.412
18	dinov2_vitl14_reg_lc_featread	.410
19	dinov2_vitl14_reg_lc	.410
20	cvt_cvt-13-384-in1k_4_LucyV4	.409
21	resnet152_imagenet_full	.407
22	vit_tiny_r_s16_p8_384:augreg_in21k_ft_in1k	.407
23	regnety_032	.400
24	convnext_tiny:in12k_ft_in1k	.404
25	cvt_cvt-21-384-in22k_finetuned-in1k_4_LucyV4	.404
26	resnet50-moclr8deg	.403
27	efficientnet_b2_imagenet_full	.403
28	cvt_cvt-13-384-in22k_finetuned-in1k_4_LucyV4	.401
29	deit_small_imagenet_full_seed-0	.394
30	voneresnet-50	.399
31	shufflenet_v2_x1_0	.398
32	VOneCORnet-S	.399
33	effnetb1_272x240	.397
34	seresnext50_32x4d	.396
35	efficientnet_b0	.394
36	vit_large_patch14_clip_224:openai_ft_in12k_in1k	.394
37	convnext_xxlarge_clip	.392
38	AdvProp_efficientnet-b4	.392
39	antialiased-r50	.391
40	resnext101_32x48d_wsl	.392
41	vit_large_patch14_clip_224:openai_ft_in1k	.392
42	AdvProp_efficientnet-b7	.390
43	Res2Net50_26w_4s	.389
44	focalnet_tiny_lrf_in1k	.388
45	cvt_cvt-21-384-in1k_4_LucyV4	.387
46	deit_large_imagenet_full_seed-0	.381
47	convnext_tiny_sup	.386
48	effnetb1_cutmix_augmix_sam_e1_5avg_424x377	.387
49	resnet_SIN_IN_FT_IN	.385
50	resnet50-SIN_IN_IN	.385
51	vit_base_patch16_clip_224:openai_ft_in12k_in1k	.385
52	resnext101_32x16d_wsl	.385
53	mobilenet_v2_1_4_224	.384
54	resnext101_32x32d_wsl	.384
55	vit_relpos_base_patch16_clsgap_224:sw_in1k	.384
56	resnext101_32x8d_wsl	.384
57	convnext_femto_ols:d1_in1k	.383
58	resnet50-vitoimagevidnet8	.383
59	resnet50-VITO-8deg-cc	.383
60	AdvProp_efficientnet-b6	.383
61	AdvProp_efficientnet-b8	.382
62	eicircuit_resnet18_bn_20260919	.375
63	resnet_50_v1_spiking	.379
64	resnet50_tutorial	.379
65	resnet50-sup	.379
66	resnet_50_v1	.379
67	resnet_50_v2	.378
68	resnet50-SIN_IN	.377
69	resnet50_imagenet_full	.377
70	vit_base_patch16_clip_224:openai_ft_in1k	.376
71	convnext_tiny_imagenet_full_seed-0	.375
72	resnet50-SIN	.375
73	AdvProp_efficientnet-b2	.373
74	AT_efficientnet-b2	.373
75	grcnn	.373
76	convnext_large_imagenet_full_seed-0	.373
77	vit_large_patch14_clip_336:openai_ft_in12k_in1k	.373
78	swin_small_patch4_window7_224:ms_in22k_ft_in1k	.369
79	convnext_base_imagenet_full_seed-0	.364
80	densenet-121	.363
81	effnetb1_cutmixpatch_augmix_robust32_avge4e7_manylayers_324x288	.361
82	dinov2_vitl14_lc	.360
83	effnetb1_cutmixpatch_SAM_robust32_avge6e8e9e10_manylayers_324x288	.357
84	voneresnet-50-non_stochastic	.356
85	convnext_large_mlp:clip_laion2b_augreg_ft_in1k_384	.355
86	deit_base_imagenet_full_seed-0	.349
87	convnext_base:clip_laiona_augreg_ft_in1k_384	.354
88	vit_large_patch14_clip_224:laion2b_ft_in12k_in1k	.354
89	vit_huge_patch14_clip_224:laion2b_ft_in12k_in1k	.353
90	convnext_small_imagenet_full_seed-0	.352
91	eva02_large_in22k	.347
92	vit_relpos_base_patch32_plus_rpn_256:sw_in1k	.347
93	ReAlnet01_cornet_fov4	.331
94	resnet50_robust_l2_eps1	.325
95	gabor_filter_entropy_4x4_v2	.319
96	alexnet	.320
97	gabor_filter_entropy_4x4_v2_forcedCosine	.317
98	gabor_filter_entropy_4x4	.307
99	resnet-50-robust	.309
100	vit_large_patch14_clip_336:laion2b_ft_in1k	.310
101	vit_large_patch14_clip_224:laion2b_ft_in1k	.305
102	AlexNet_SIN	.301
103	ViT_L_32_imagenet1k	.267
104	AlexNet_SIN_fov12	.258
105	hmax	.211
106	AlexNet_SIN_fov16	.202
107	gabor_filter_mean_abs_4x4_v2	.179
108	alexnet_training_seed_09	.151
109	alexnet_training_seed_02	.146
110	alexnet_training_seed_06	.146
111	alexnet_training_seed_07	.141
112	alexnet_training_seed_10	.137
113	alexnet_training_seed_03	.136
114	alexnet_training_seed_01	.130
115	compact_resnet50_robust_V4	.116

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

0.79.

Note that scores are relative to this ceiling.

Data: Zerbe2026_fmri.V4-ood

Metric: ridgecv