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("Hebart2023_fmri.V2-ridgecv")
score = benchmark(my_model)

Benchmark API

Code examples

Model scores

Score Legend Min Alignment Max Alignment

Rank	Model	Score
1	deit3_base_patch16_224_fb_in22k_ft_in1k_gram_aligned_dinov3	.661
2	deit3_base_patch16_224_fb_in22k_ft_in1k	.661
3	cvt_cvt-13-384-in1k_4_LucyV4	.644
4	swin_small_patch4_window7_224:ms_in22k_ft_in1k	.644
5	deit_small_imagenet_full_seed-0	.643
6	vit_tiny_r_s16_p8_384:augreg_in21k_ft_in1k	.640
7	cvt_cvt-w24-384-in22k_finetuned-in1k_4	.636
8	deit3_base_patch16_224_fb_in1k_gram_aligned_dinov3	.630
9	deit3_base_patch16_224_fb_in1k	.630
10	convnext_large:fb_in22k_ft_in1k	.630
11	resnet50_st_wzc_seed7_2_323	.628
12	resnet50_st_wzc_seed6_2_323	.627
13	resnet50-SIN_IN_IN	.626
14	resnet_SIN_IN_FT_IN	.626
15	resnet50_st_wzc_seed3_2_323	.625
16	resnet50_st_wzc_seed5_2_323	.622
17	resnet50_st_wzc_2_323	.618
18	antialiased-r50	.618
19	resnet50_st_wzc_seed4_2_323	.614
20	cvt_cvt-21-224-in1k_4_LucyV4	.614
21	Res2Net50_26w_4s	.613
22	resnext101_32x16d_wsl	.612
23	deit_base_imagenet_full_seed-0	.611
24	resnet50_ewconplus_wzc_seed4_2_323	.611
25	resnet152_imagenet_full	.610
26	resnet50_ewconplus_wzc_seed5_2__323	.610
27	resnet50_ewconplus_wzc_seed3_2_323	.611
28	resnet50_ewconplus_wzc_seed7_2_323	.610
29	voneresnet-50-non_stochastic	.609
30	resnext101_32x8d_wsl	.609
31	focalnet_tiny_lrf_in1k	.608
32	resnet50_st_wzc_noseed_2_323	.608
33	resnet50_ewconplus_wzc_seed6_2_323	.607
34	resnet_50_v1	.607
35	resnet50-sup	.607
36	resnet_50_v1_spiking	.607
37	resnet50_imagenet_full	.606
38	cvt_cvt-13-384-in22k_finetuned-in1k_4_LucyV4	.605
39	resnet50-SIN_IN	.605
40	resnet50-vitoimagevidnet8	.603
41	resnet50-VITO-8deg-cc	.603
42	deit_large_imagenet_full_seed-0	.603
43	resnet50_ewconplus_wzc_seed2_2__323	.603
44	cvt_cvt-21-384-in22k_finetuned-in1k_4_LucyV4	.603
45	resnet50_robust_l2_eps1	.602
46	resnet50-moclr8deg	.600
47	vit_relpos_base_patch16_clsgap_224:sw_in1k	.599
48	vit_large_patch14_clip_336:openai_ft_in12k_in1k	.599
49	cvt_cvt-21-384-in1k_4_LucyV4	.598
50	resnext101_32x32d_wsl	.597
51	resnet_50_v2	.595
52	resnet50_ewconplus_wzc	.596
53	voneresnet-50	.593
54	densenet-121	.592
55	convnext_large_imagenet_full_seed-0	.592
56	convnext_xxlarge:clip_laion2b_soup_ft_in1k	.592
57	custom_model_cv_18_dagger_408	.591
58	resnext101_32x48d_wsl	.590
59	convnext_tiny_sup	.590
60	shufflenet_v2_x1_0	.589
61	vit_large_patch14_clip_336:laion2b_ft_in1k	.588
62	vit_base_patch16_clip_224:openai_ft_in12k_in1k	.587
63	resnet50_tutorial	.586
64	AdvProp_efficientnet-b4	.584
65	deepeisnn_ei_imagenet_resnet18	.584
66	AdvProp_efficientnet-b8	.583
67	resnet50-SIN	.582
68	convnext_xlarge:fb_in22k_ft_in1k	.581
69	vit_large_patch14_clip_224:openai_ft_in1k	.579
70	vit_large_patch14_clip_224:openai_ft_in12k_in1k	.578
71	yudixie_wbh_object_class_scaling_0415_imagenet	.577
72	vit_huge_patch14_clip_224:laion2b_ft_in12k_in1k	.577
73	AdvProp_efficientnet-b6	.577
74	cvt_cvt-13-224-in1k_4_LucyV4	.576
75	convnext_tiny_imagenet_full_seed-0	.572
76	efficientnet_b2_imagenet_full	.572
77	AdvProp_efficientnet-b7	.571
78	convnext_femto_ols:d1_in1k	.569
79	vit_large_patch14_clip_224:laion2b_ft_in1k	.568
80	vit_large_patch14_clip_224:laion2b_ft_in12k_in1k	.565
81	grcnn	.563
82	mobilenet_v2_1_4_224	.562
83	convnext_tiny:in12k_ft_in1k	.554
84	convnext_base:clip_laiona_augreg_ft_in1k_384	.550
85	effnetb1_cutmix_augmix_sam_e1_5avg_424x377	.537
86	convnext_large_mlp:clip_laion2b_augreg_ft_in1k_384	.535
87	convnext_small_imagenet_full_seed-0	.534
88	resnet50_ewconplus_wzc_2_323	.534
89	ReAlnet01_cornet	.530
90	alexnet	.527
91	convnext_base_imagenet_full_seed-0	.526
92	vit_base_patch16_clip_224:openai_ft_in1k	.525
93	ReAlnet03_cornet	.524
94	convnext_base_fb_in22k_ft_in1k_gram_aligned_dinov3	.523
95	convnext_base_fb_in1k	.520
96	ReAlnet04_cornet	.520
97	vit_relpos_base_patch32_plus_rpn_256:sw_in1k	.517
98	effnetb1_272x240	.519
99	AlexNet_SIN	.512
100	AT_efficientnet-b2	.509
101	AdvProp_efficientnet-b2	.509
102	effnetb1_cutmixpatch_SAM_robust32_avge6e8e9e10_manylayers_324x288	.509
103	efficientnet_b0	.505
104	resnet-50-robust	.497
105	AlexNet_SIN_fov12	.496
106	AlexNet_SIN_fov16	.482
107	resnet18_fair	.480
108	effnetb1_cutmixpatch_augmix_robust32_avge4e7_manylayers_324x288	.478
109	VOneCORnet-S	.477
110	deepeisnn_ei_cifar10_vgg19	.465
111	deepeisnn_ei_cifar10_resnet18	.435
112	alexnet_training_seed_06	.409
113	alexnet_training_seed_07	.390
114	alexnet_training_seed_01	.383
115	yudixie_wbh_object_class_scaling_0415_run_2	.381
116	alexnet_training_seed_03	.379
117	alexnet_training_seed_10	.375
118	alexnet_training_seed_02	.369
119	ReAlnet01_cornet_fov4	.370
120	yudixie_wbh_object_class_scaling_0415_run_0	.350
121	yudixie_wbh_object_class_scaling_0415_run_3	.350
122	alexnet_training_seed_09	.350
123	predictive_coding_pc	.351
124	pr1_stl10_disentangled_alpha04	.348
125	yudixie_wbh_object_class_scaling_0415_run_1	.337
126	ViT_L_32_imagenet1k	.308
127	convnext_base_fb_in22k_ft_in1k	.225
128	compact_resnet50_robust_V4	.183
129	convnext_base_fb_in1k_gram_aligned_dinov3	.182
130	pnasnet_large_halfPrecision
131	hmax

Benchmark bibtex

None

Ceiling

0.48.

Note that scores are relative to this ceiling.

Data: Hebart2023_fmri.V2

Metric: ridgecv