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	convnext_tiny:in12k_ft_in1k	.404
24	cvt_cvt-21-384-in22k_finetuned-in1k_4_LucyV4	.404
25	resnet50-moclr8deg	.403
26	efficientnet_b2_imagenet_full	.403
27	cvt_cvt-13-384-in22k_finetuned-in1k_4_LucyV4	.401
28	deit_small_imagenet_full_seed-0	.394
29	voneresnet-50	.399
30	shufflenet_v2_x1_0	.398
31	VOneCORnet-S	.399
32	effnetb1_272x240	.397
33	efficientnet_b0	.394
34	vit_large_patch14_clip_224:openai_ft_in12k_in1k	.394
35	convnext_xxlarge_clip	.392
36	AdvProp_efficientnet-b4	.392
37	antialiased-r50	.391
38	resnext101_32x48d_wsl	.392
39	vit_large_patch14_clip_224:openai_ft_in1k	.392
40	AdvProp_efficientnet-b7	.390
41	Res2Net50_26w_4s	.389
42	focalnet_tiny_lrf_in1k	.388
43	cvt_cvt-21-384-in1k_4_LucyV4	.387
44	deit_large_imagenet_full_seed-0	.381
45	convnext_tiny_sup	.386
46	effnetb1_cutmix_augmix_sam_e1_5avg_424x377	.387
47	resnet_SIN_IN_FT_IN	.385
48	resnet50-SIN_IN_IN	.385
49	vit_base_patch16_clip_224:openai_ft_in12k_in1k	.385
50	resnext101_32x16d_wsl	.385
51	mobilenet_v2_1_4_224	.384
52	resnext101_32x32d_wsl	.384
53	vit_relpos_base_patch16_clsgap_224:sw_in1k	.384
54	resnext101_32x8d_wsl	.384
55	convnext_femto_ols:d1_in1k	.383
56	resnet50-vitoimagevidnet8	.383
57	resnet50-VITO-8deg-cc	.383
58	AdvProp_efficientnet-b6	.383
59	AdvProp_efficientnet-b8	.382
60	resnet_50_v1_spiking	.379
61	resnet50_tutorial	.379
62	resnet50-sup	.379
63	resnet_50_v1	.379
64	resnet_50_v2	.378
65	resnet50-SIN_IN	.377
66	resnet50_imagenet_full	.377
67	vit_base_patch16_clip_224:openai_ft_in1k	.376
68	convnext_tiny_imagenet_full_seed-0	.375
69	resnet50-SIN	.375
70	AdvProp_efficientnet-b2	.373
71	AT_efficientnet-b2	.373
72	grcnn	.373
73	convnext_large_imagenet_full_seed-0	.373
74	vit_large_patch14_clip_336:openai_ft_in12k_in1k	.373
75	swin_small_patch4_window7_224:ms_in22k_ft_in1k	.369
76	convnext_base_imagenet_full_seed-0	.364
77	densenet-121	.363
78	effnetb1_cutmixpatch_augmix_robust32_avge4e7_manylayers_324x288	.361
79	dinov2_vitl14_lc	.360
80	effnetb1_cutmixpatch_SAM_robust32_avge6e8e9e10_manylayers_324x288	.357
81	voneresnet-50-non_stochastic	.356
82	convnext_large_mlp:clip_laion2b_augreg_ft_in1k_384	.355
83	deit_base_imagenet_full_seed-0	.349
84	convnext_base:clip_laiona_augreg_ft_in1k_384	.354
85	vit_large_patch14_clip_224:laion2b_ft_in12k_in1k	.354
86	vit_huge_patch14_clip_224:laion2b_ft_in12k_in1k	.353
87	convnext_small_imagenet_full_seed-0	.352
88	eva02_large_in22k	.347
89	vit_relpos_base_patch32_plus_rpn_256:sw_in1k	.347
90	ReAlnet01_cornet_fov4	.331
91	resnet50_robust_l2_eps1	.325
92	alexnet	.320
93	resnet-50-robust	.309
94	vit_large_patch14_clip_336:laion2b_ft_in1k	.310
95	vit_large_patch14_clip_224:laion2b_ft_in1k	.305
96	AlexNet_SIN	.301
97	ViT_L_32_imagenet1k	.267
98	AlexNet_SIN_fov12	.258
99	hmax	.211
100	AlexNet_SIN_fov16	.202
101	alexnet_training_seed_09	.151
102	alexnet_training_seed_02	.146
103	alexnet_training_seed_06	.146
104	alexnet_training_seed_07	.141
105	alexnet_training_seed_10	.137
106	alexnet_training_seed_03	.136
107	alexnet_training_seed_01	.130
108	compact_resnet50_robust_V4	.116

Benchmark bibtex

None

Ceiling

0.79.

Note that scores are relative to this ceiling.

Data: Zerbe2026_fmri.V4-ood

Metric: ridgecv