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.V1-tau-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	.493
2	cvt_cvt-w24-384-in22k_finetuned-in1k_4	.492
3	cvt_cvt-13-384-in1k_4_LucyV4	.491
4	vit_large_clip336_openai	.490
5	vit_large_patch14_clip_224:openai_ft_in1k	.488
6	vit_large_patch14_clip_336:laion2b_ft_in1k	.483
7	vit_large_patch14_clip_224:openai_ft_in12k_in1k	.484
8	cvt_cvt-21-384-in22k_finetuned-in1k_4_LucyV4	.483
9	eva02_large_in22k	.481
10	vit_tiny_r_s16_p8_384:augreg_in21k_ft_in1k	.478
11	vit_relpos_base_patch16_clsgap_224:sw_in1k	.476
12	convnext_large_mlp:clip_laion2b_augreg_ft_in1k_384	.474
13	antialiased-r50	.473
14	resnet_SIN_IN_FT_IN	.474
15	vit_huge_patch14_clip_224:laion2b_ft_in12k_in1k	.472
16	effnetb1_cutmix_augmix_sam_e1_5avg_424x377	.469
17	efficientnet_b2_imagenet_full	.467
18	vit_base_patch16_clip_224:openai_ft_in12k_in1k	.463
19	convnext_femto_ols:d1_in1k	.463
20	swin_small_patch4_window7_224:ms_in22k_ft_in1k	.463
21	resnet50-SIN_IN_IN	.462
22	dinov2_vitl14_lc	.461
23	grcnn	.460
24	voneresnet-50	.460
25	vit_base_patch16_clip_224:openai_ft_in1k	.459
26	vit_large_patch14_clip_224:laion2b_ft_in12k_in1k	.460
27	resnet50-SIN	.458
28	convnext_base:clip_laiona_augreg_ft_in1k_384	.458
29	shufflenet_v2_x1_0	.455
30	deit_base_imagenet_full_seed-0	.436
31	resnet_50_v1	.456
32	resnet_50_v1_spiking	.456
33	resnet50-sup	.456
34	resnet50_tutorial	.456
35	vit_large_patch14_clip_224:laion2b_ft_in1k	.457
36	cvt_cvt-13-384-in22k_finetuned-in1k_4_LucyV4	.455
37	custom_model_cv_18_dagger_408	.452
38	AdvProp_efficientnet-b8	.454
39	pnasnet_large_halfPrecision	.454
40	dinov2_vitg14_reg_lc	.454
41	convnext_xxlarge_clip	.452
42	dinov2_vitl14_reg_lc_featread	.451
43	dinov2_vitl14_reg_lc	.451
44	dinov2_vitg14_lc	.450
45	AdvProp_efficientnet-b6	.449
46	densenet-121	.449
47	focalnet_tiny_lrf_in1k	.448
48	resnext101_32x48d_wsl	.445
49	seresnext50_32x4d	.443
50	AdvProp_efficientnet-b7	.442
51	resnet50_robust_l2_eps1	.442
52	cvt_cvt-13-224-in1k_4_LucyV4	.442
53	resnext101_32x16d_wsl	.439
54	cvt_cvt-21-384-in1k_4_LucyV4	.440
55	vit_large_patch14_clip_336:openai_ft_in12k_in1k	.438
56	convnext_small_imagenet_full_seed-0	.434
57	cvt_cvt-21-224-in1k_4_LucyV4	.435
58	resnet50-moclr8deg	.433
59	convnext_xlarge:fb_in22k_ft_in1k	.432
60	mobilenet_v2_1_4_224	.433
61	resnet50-VITO-8deg-cc	.434
62	resnet50-vitoimagevidnet8	.434
63	resnet-50-robust	.434
64	efficientnet_b0	.432
65	convnext_tiny_sup	.431
66	Res2Net50_26w_4s	.429
67	convnext_xxlarge:clip_laion2b_soup_ft_in1k	.425
68	effnetb1_272x240	.427
69	persistence_memory	.427
70	vit_relpos_base_patch32_plus_rpn_256:sw_in1k	.427
71	deit_large_imagenet_full_seed-0	.408
72	resnet50-SIN_IN	.425
73	convnext_large:fb_in22k_ft_in1k	.423
74	convnext_base_imagenet_full_seed-0	.422
75	AdvProp_efficientnet-b4	.423
76	resnet50_ewconplus_wzc	.422
77	resnext101_32x8d_wsl	.422
78	deit_small_imagenet_full_seed-0	.403
79	resnext101_32x32d_wsl	.420
80	AT_efficientnet-b2	.418
81	AdvProp_efficientnet-b2	.418
82	ReAlnet03_cornet	.411
83	AlexNet_SIN_fov16	.409
84	ReAlnet04_cornet	.411
85	ReAlnet01_cornet	.410
86	resnet152_imagenet_full	.406
87	AlexNet_SIN	.402
88	resnet_50_v2	.403
89	alexnet	.402
90	effnetb1_cutmixpatch_augmix_robust32_avge4e7_manylayers_324x288	.400
91	effnetb1_cutmixpatch_SAM_robust32_avge6e8e9e10_manylayers_324x288	.400
92	compact_resnet50_robust_V4	.399
93	regnety_032	.394
94	AlexNet_SIN_fov12	.393
95	persistence_mem	.393
96	gabor_filter_entropy_4x4_v2_forcedCosine	.374
97	gabor_filter_entropy_4x4_v2	.369
98	convnext_large_imagenet_full_seed-0	.366
99	eicircuit_resnet18_bn_20260919	.350
100	resnet50_imagenet_full	.362
101	convnext_tiny:in12k_ft_in1k	.358
102	ViT_L_32_imagenet1k	.355
103	convnext_tiny_imagenet_full_seed-0	.353
104	gabor_filter_entropy_4x4	.326
105	vonealexnet	.323
106	alexnet_training_seed_02	.316
107	alexnet_training_seed_01	.314
108	alexnet_training_seed_09	.312
109	alexnet_training_seed_10	.308
110	alexnet_training_seed_06	.306
111	alexnet_training_seed_07	.305
112	alexnet_training_seed_03	.275
113	gabor_filter_mean_abs_4x4_v2	.256
114	ReAlnet01_cornet_fov4	.245
115	voneresnet-50-non_stochastic	.236
116	VOneCORnet-S	.155
117	hmax	.125
118	dinov2_vitl14_lc_res336

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

0.81.

Note that scores are relative to this ceiling.

Data: Zerbe2026_fmri.V1-tau

Metric: ridgecv