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	vit_large_patch14_clip_224:openai_ft_in1k	.412
41	shufflenet_v2_x1_0	.413
42	resnet_50_v2	.412
43	Res2Net50_26w_4s	.412
44	vit_large_patch14_clip_224:openai_ft_in12k_in1k	.410
45	convnext_xxlarge_clip	.410
46	resnet50_imagenet_full	.410
47	pnasnet_large_halfPrecision	.409
48	voneresnet-50	.408
49	cvt_cvt-13-384-in22k_finetuned-in1k_4_LucyV4	.407
50	resnext101_32x8d_wsl	.405
51	resnet50-SIN	.406
52	resnet_50_v1_spiking	.406
53	resnet_50_v1	.406
54	resnet50-sup	.406
55	densenet-121	.404
56	convnext_tiny_imagenet_full_seed-0	.403
57	convnext_xlarge:fb_in22k_ft_in1k	.402
58	resnext101_32x16d_wsl	.401
59	vit_huge_patch14_clip_224:laion2b_ft_in12k_in1k	.401
60	convnext_tiny_sup	.401
61	convnext_femto_ols:d1_in1k	.401
62	resnet50_tutorial	.401
63	vit_large_patch14_clip_224:laion2b_ft_in12k_in1k	.399
64	resnet50_ewconplus_wzc	.399
65	AdvProp_efficientnet-b6	.398
66	vit_large_patch14_clip_224:laion2b_ft_in1k	.395
67	cvt_cvt-13-224-in1k_4_LucyV4	.395
68	grcnn	.392
69	AdvProp_efficientnet-b8	.391
70	effnetb1_272x240	.390
71	ReAlnet04_cornet	.390
72	ReAlnet01_cornet	.389
73	ReAlnet03_cornet	.389
74	efficientnet_b2_imagenet_full	.386
75	AdvProp_efficientnet-b7	.384
76	AdvProp_efficientnet-b4	.385
77	mobilenet_v2_1_4_224	.383
78	convnext_base_imagenet_full_seed-0	.380
79	convnext_base:clip_laiona_augreg_ft_in1k_384	.380
80	convnext_large_mlp:clip_laion2b_augreg_ft_in1k_384	.380
81	convnext_small_imagenet_full_seed-0	.374
82	alexnet	.375
83	resnext101_32x48d_wsl	.369
84	convnext_tiny:in12k_ft_in1k	.369
85	resnet-50-robust	.363
86	effnetb1_cutmixpatch_SAM_robust32_avge6e8e9e10_manylayers_324x288	.362
87	AlexNet_SIN	.360
88	vit_relpos_base_patch32_plus_rpn_256:sw_in1k	.360
89	resnext101_32x32d_wsl	.359
90	VOneCORnet-S	.358
91	effnetb1_cutmixpatch_augmix_robust32_avge4e7_manylayers_324x288	.351
92	AlexNet_SIN_fov12	.351
93	AT_efficientnet-b2	.348
94	AdvProp_efficientnet-b2	.348
95	AlexNet_SIN_fov16	.339
96	efficientnet_b0	.339
97	vit_base_patch16_clip_224:openai_ft_in1k	.335
98	alexnet_training_seed_06	.243
99	alexnet_training_seed_01	.238
100	alexnet_training_seed_10	.238
101	ReAlnet01_cornet_fov4	.235
102	alexnet_training_seed_03	.230
103	alexnet_training_seed_07	.230
104	alexnet_training_seed_02	.222
105	ViT_L_32_imagenet1k	.207
106	alexnet_training_seed_09	.201
107	compact_resnet50_robust_V4	.148
108	hmax	.087

Benchmark bibtex

None

Ceiling

0.79.

Note that scores are relative to this ceiling.

Data: Zerbe2026_fmri.V2-tau

Metric: ridgecv