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-tau-ridgecv")
score = benchmark(my_model)

Benchmark API

Code examples

Model scores

Score Legend Min Alignment Max Alignment

Rank	Model	Score
1	custom_model_cv_18_dagger_408	.406
2	convnext_xxlarge:clip_laion2b_soup_ft_in1k	.403
3	vit_huge_clip336_laion	.392
4	dinov2_vitg14_reg_lc	.377
5	cvt_cvt-w24-384-in22k_finetuned-in1k_4	.369
6	vit_large_clip336_openai	.369
7	dinov2_vitl14_lc_res336	.368
8	vit_large_patch14_clip_224:openai_ft_in1k	.369
9	dinov2_vitg14_lc	.367
10	convnext_large:fb_in22k_ft_in1k	.367
11	cvt_cvt-21-224-in1k_4_LucyV4	.365
12	cvt_cvt-13-224-in1k_4_LucyV4	.361
13	convnext_xxlarge_clip	.359
14	cvt_cvt-13-384-in1k_4_LucyV4	.358
15	resnet50-moclr8deg	.353
16	shufflenet_v2_x1_0	.352
17	vit_large_patch14_clip_336:laion2b_ft_in1k	.352
18	vit_large_patch14_clip_336:openai_ft_in12k_in1k	.352
19	resnet152_imagenet_full	.352
20	eva02_large_in22k	.351
21	convnext_xlarge:fb_in22k_ft_in1k	.351
22	cvt_cvt-21-384-in1k_4_LucyV4	.350
23	cvt_cvt-21-384-in22k_finetuned-in1k_4_LucyV4	.347
24	regnety_032	.343
25	pnasnet_large_halfPrecision	.347
26	dinov2_vitl14_reg_lc_featread	.346
27	dinov2_vitl14_reg_lc	.346
28	voneresnet-50	.345
29	convnext_tiny:in12k_ft_in1k	.344
30	ReAlnet03_cornet	.343
31	ReAlnet01_cornet	.343
32	ReAlnet04_cornet	.343
33	resnet50-vitoimagevidnet8	.341
34	resnet50-VITO-8deg-cc	.341
35	vit_tiny_r_s16_p8_384:augreg_in21k_ft_in1k	.340
36	efficientnet_b2_imagenet_full	.338
37	focalnet_tiny_lrf_in1k	.335
38	seresnext50_32x4d	.335
39	resnet_50_v2	.334
40	efficientnet_b0	.334
41	deit_small_imagenet_full_seed-0	.331
42	vit_relpos_base_patch16_clsgap_224:sw_in1k	.333
43	cvt_cvt-13-384-in22k_finetuned-in1k_4_LucyV4	.333
44	vit_base_patch16_clip_224:openai_ft_in12k_in1k	.331
45	resnet50-SIN	.330
46	resnet50_ewconplus_wzc	.330
47	vit_large_patch14_clip_224:openai_ft_in12k_in1k	.330
48	AT_efficientnet-b2	.327
49	AdvProp_efficientnet-b2	.327
50	effnetb1_272x240	.327
51	VOneCORnet-S	.326
52	vit_base_patch16_clip_224:openai_ft_in1k	.325
53	resnext101_32x48d_wsl	.325
54	AdvProp_efficientnet-b4	.325
55	vit_large_patch14_clip_224:laion2b_ft_in1k	.321
56	convnext_femto_ols:d1_in1k	.320
57	resnext101_32x32d_wsl	.319
58	Res2Net50_26w_4s	.317
59	AdvProp_efficientnet-b8	.314
60	alexnet	.314
61	convnext_tiny_sup	.314
62	convnext_tiny_imagenet_full_seed-0	.315
63	antialiased-r50	.314
64	resnet_SIN_IN_FT_IN	.314
65	resnet50-SIN_IN_IN	.314
66	convnext_large_imagenet_full_seed-0	.314
67	resnet_50_v1_spiking	.313
68	resnet_50_v1	.313
69	resnet50_tutorial	.313
70	resnet50-sup	.313
71	deit_large_imagenet_full_seed-0	.307
72	resnet50-SIN_IN	.310
73	convnext_base:clip_laiona_augreg_ft_in1k_384	.310
74	resnext101_32x8d_wsl	.308
75	swin_small_patch4_window7_224:ms_in22k_ft_in1k	.308
76	AdvProp_efficientnet-b7	.305
77	convnext_base_imagenet_full_seed-0	.306
78	resnext101_32x16d_wsl	.306
79	dinov2_vitl14_lc	.304
80	mobilenet_v2_1_4_224	.301
81	convnext_small_imagenet_full_seed-0	.301
82	AdvProp_efficientnet-b6	.298
83	convnext_large_mlp:clip_laion2b_augreg_ft_in1k_384	.299
84	resnet50_imagenet_full	.298
85	effnetb1_cutmix_augmix_sam_e1_5avg_424x377	.297
86	vit_large_patch14_clip_224:laion2b_ft_in12k_in1k	.295
87	AlexNet_SIN	.295
88	grcnn	.294
89	effnetb1_cutmixpatch_augmix_robust32_avge4e7_manylayers_324x288	.294
90	voneresnet-50-non_stochastic	.291
91	deit_base_imagenet_full_seed-0	.287
92	vit_huge_patch14_clip_224:laion2b_ft_in12k_in1k	.288
93	resnet50_robust_l2_eps1	.282
94	AlexNet_SIN_fov12	.281
95	effnetb1_cutmixpatch_SAM_robust32_avge6e8e9e10_manylayers_324x288	.278
96	vit_relpos_base_patch32_plus_rpn_256:sw_in1k	.276
97	resnet-50-robust	.268
98	densenet-121	.263
99	gabor_filter_entropy_4x4_v2	.254
100	gabor_filter_entropy_4x4_v2_forcedCosine	.253
101	ReAlnet01_cornet_fov4	.252
102	ViT_L_32_imagenet1k	.245
103	gabor_filter_entropy_4x4	.232
104	AlexNet_SIN_fov16	.214
105	gabor_filter_mean_abs_4x4_v2	.167
106	alexnet_training_seed_06	.162
107	alexnet_training_seed_02	.152
108	alexnet_training_seed_03	.152
109	alexnet_training_seed_01	.149
110	alexnet_training_seed_09	.149
111	alexnet_training_seed_07	.147
112	alexnet_training_seed_10	.144
113	compact_resnet50_robust_V4	.074
114	hmax	.070
115	eicircuit_resnet18_bn_20260919

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-tau

Metric: ridgecv