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.V2-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	.452
2	cvt_cvt-13-384-in1k_4_LucyV4	.446
3	vit_large_clip336_openai	.445
4	deit_small_imagenet_full_seed-0	.427
5	cvt_cvt-w24-384-in22k_finetuned-in1k_4	.444
6	vit_tiny_r_s16_p8_384:augreg_in21k_ft_in1k	.442
7	dinov2_vitl14_lc	.440
8	vit_relpos_base_patch16_clsgap_224:sw_in1k	.439
9	dinov2_vitl14_lc_res336	.438
10	dinov2_vitg14_lc	.435
11	vit_large_patch14_clip_336:laion2b_ft_in1k	.434
12	dinov2_vitl14_reg_lc_featread	.433
13	dinov2_vitl14_reg_lc	.433
14	deit_base_imagenet_full_seed-0	.416
15	dinov2_vitg14_reg_lc	.431
16	focalnet_tiny_lrf_in1k	.430
17	deit_large_imagenet_full_seed-0	.413
18	custom_model_cv_18_dagger_408	.428
19	eva02_large_in22k	.428
20	convnext_xxlarge:clip_laion2b_soup_ft_in1k	.426
21	vit_large_patch14_clip_336:openai_ft_in12k_in1k	.425
22	swin_small_patch4_window7_224:ms_in22k_ft_in1k	.424
23	resnet50-vitoimagevidnet8	.423
24	resnet50-VITO-8deg-cc	.423
25	cvt_cvt-21-384-in22k_finetuned-in1k_4_LucyV4	.422
26	effnetb1_cutmix_augmix_sam_e1_5avg_424x377	.420
27	cvt_cvt-21-224-in1k_4_LucyV4	.418
28	cvt_cvt-21-384-in1k_4_LucyV4	.418
29	resnet50-SIN_IN	.418
30	resnet_SIN_IN_FT_IN	.418
31	resnet50-SIN_IN_IN	.418
32	resnet50-moclr8deg	.417
33	vit_base_patch16_clip_224:openai_ft_in12k_in1k	.416
34	resnet152_imagenet_full	.415
35	resnet50_robust_l2_eps1	.416
36	convnext_large_imagenet_full_seed-0	.415
37	antialiased-r50	.414
38	voneresnet-50-non_stochastic	.415
39	convnext_large:fb_in22k_ft_in1k	.414
40	seresnext50_32x4d	.414
41	vit_large_patch14_clip_224:openai_ft_in1k	.412
42	shufflenet_v2_x1_0	.413
43	resnet_50_v2	.412
44	Res2Net50_26w_4s	.412
45	vit_large_patch14_clip_224:openai_ft_in12k_in1k	.410
46	convnext_xxlarge_clip	.410
47	resnet50_imagenet_full	.410
48	pnasnet_large_halfPrecision	.409
49	voneresnet-50	.408
50	cvt_cvt-13-384-in22k_finetuned-in1k_4_LucyV4	.407
51	resnext101_32x8d_wsl	.405
52	resnet50-SIN	.406
53	resnet_50_v1_spiking	.406
54	resnet_50_v1	.406
55	resnet50-sup	.406
56	densenet-121	.404
57	convnext_tiny_imagenet_full_seed-0	.403
58	convnext_xlarge:fb_in22k_ft_in1k	.402
59	resnext101_32x16d_wsl	.401
60	vit_huge_patch14_clip_224:laion2b_ft_in12k_in1k	.401
61	convnext_tiny_sup	.401
62	convnext_femto_ols:d1_in1k	.401
63	resnet50_tutorial	.401
64	vit_large_patch14_clip_224:laion2b_ft_in12k_in1k	.399
65	resnet50_ewconplus_wzc	.399
66	AdvProp_efficientnet-b6	.398
67	eicircuit_resnet18_bn_20260919	.384
68	vit_large_patch14_clip_224:laion2b_ft_in1k	.395
69	cvt_cvt-13-224-in1k_4_LucyV4	.395
70	grcnn	.392
71	AdvProp_efficientnet-b8	.391
72	effnetb1_272x240	.390
73	ReAlnet04_cornet	.390
74	ReAlnet01_cornet	.389
75	ReAlnet03_cornet	.389
76	efficientnet_b2_imagenet_full	.386
77	AdvProp_efficientnet-b7	.384
78	AdvProp_efficientnet-b4	.385
79	mobilenet_v2_1_4_224	.383
80	convnext_base_imagenet_full_seed-0	.380
81	convnext_base:clip_laiona_augreg_ft_in1k_384	.380
82	convnext_large_mlp:clip_laion2b_augreg_ft_in1k_384	.380
83	convnext_small_imagenet_full_seed-0	.374
84	alexnet	.375
85	resnext101_32x48d_wsl	.369
86	convnext_tiny:in12k_ft_in1k	.369
87	resnet-50-robust	.363
88	effnetb1_cutmixpatch_SAM_robust32_avge6e8e9e10_manylayers_324x288	.362
89	AlexNet_SIN	.360
90	vit_relpos_base_patch32_plus_rpn_256:sw_in1k	.360
91	resnext101_32x32d_wsl	.359
92	gabor_filter_entropy_4x4_v2_forcedCosine	.350
93	VOneCORnet-S	.358
94	gabor_filter_entropy_4x4_v2	.346
95	effnetb1_cutmixpatch_augmix_robust32_avge4e7_manylayers_324x288	.351
96	AlexNet_SIN_fov12	.351
97	AT_efficientnet-b2	.348
98	AdvProp_efficientnet-b2	.348
99	AlexNet_SIN_fov16	.339
100	efficientnet_b0	.339
101	vit_base_patch16_clip_224:openai_ft_in1k	.335
102	gabor_filter_entropy_4x4	.302
103	regnety_032	.284
104	alexnet_training_seed_06	.243
105	alexnet_training_seed_01	.238
106	alexnet_training_seed_10	.238
107	ReAlnet01_cornet_fov4	.235
108	alexnet_training_seed_03	.230
109	alexnet_training_seed_07	.230
110	alexnet_training_seed_02	.222
111	gabor_filter_mean_abs_4x4_v2	.212
112	ViT_L_32_imagenet1k	.207
113	alexnet_training_seed_09	.201
114	compact_resnet50_robust_V4	.148
115	hmax	.087

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.V2-tau

Metric: ridgecv