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	vit_large_clip336_openai	.633
9	dinov2_vitl14_lc_res336	.631
10	dinov2_vitl14_reg_lc_featread	.631
11	dinov2_vitl14_reg_lc	.631
12	deit3_base_patch16_224_fb_in1k_gram_aligned_dinov3	.630
13	deit3_base_patch16_224_fb_in1k	.630
14	convnext_large:fb_in22k_ft_in1k	.630
15	resnet50_st_wzc_seed7_2_323	.628
16	resnet50_st_wzc_seed6_2_323	.627
17	resnet50-SIN_IN_IN	.626
18	resnet_SIN_IN_FT_IN	.626
19	dinov2_vitl14_lc	.625
20	resnet50_st_wzc_seed3_2_323	.625
21	dinov2_vitg14_lc	.622
22	dinov2_vitg14_reg_lc	.621
23	convnext_large_in22k_supervised	.618
24	antialiased-r50	.618
25	cvt_cvt-21-224-in1k_4_LucyV4	.614
26	Res2Net50_26w_4s	.613
27	resnext101_32x16d_wsl	.612
28	deit_base_imagenet_full_seed-0	.611
29	resnet152_imagenet_full	.610
30	resnet50_ewconplus_wzc_seed5_2__323	.610
31	voneresnet-50-non_stochastic	.609
32	resnext101_32x8d_wsl	.609
33	focalnet_tiny_lrf_in1k	.608
34	eva02_large_in22k	.607
35	resnet50_ewconplus_wzc_seed6_2_323	.607
36	resnet_50_v1	.607
37	resnet50-sup	.607
38	resnet_50_v1_spiking	.607
39	resnet50_imagenet_full	.606
40	cvt_cvt-13-384-in22k_finetuned-in1k_4_LucyV4	.605
41	resnet50-SIN_IN	.605
42	seresnext50_32x4d	.604
43	resnet50-vitoimagevidnet8	.603
44	resnet50-VITO-8deg-cc	.603
45	deit_large_imagenet_full_seed-0	.603
46	resnet50_ewconplus_wzc_seed2_2__323	.603
47	cvt_cvt-21-384-in22k_finetuned-in1k_4_LucyV4	.603
48	resnet50_robust_l2_eps1	.602
49	resnet50-moclr8deg	.600
50	vit_relpos_base_patch16_clsgap_224:sw_in1k	.599
51	vit_large_patch14_clip_336:openai_ft_in12k_in1k	.599
52	cvt_cvt-21-384-in1k_4_LucyV4	.598
53	resnext101_32x32d_wsl	.597
54	resnet_50_v2	.595
55	resnet50_ewconplus_wzc	.596
56	voneresnet-50	.593
57	densenet-121	.592
58	convnext_large_imagenet_full_seed-0	.592
59	convnext_xxlarge:clip_laion2b_soup_ft_in1k	.592
60	custom_model_cv_18_dagger_408	.591
61	resnext101_32x48d_wsl	.590
62	convnext_tiny_sup	.590
63	shufflenet_v2_x1_0	.589
64	vit_large_patch14_clip_336:laion2b_ft_in1k	.588
65	vit_base_patch16_clip_224:openai_ft_in12k_in1k	.587
66	resnet50_tutorial	.586
67	eicircuit_resnet18_bn_20260919	.585
68	AdvProp_efficientnet-b4	.584
69	deepeisnn_ei_imagenet_resnet18	.584
70	AdvProp_efficientnet-b8	.583
71	resnet50-SIN	.582
72	convnext_xlarge:fb_in22k_ft_in1k	.581
73	vit_large_patch14_clip_224:openai_ft_in1k	.579
74	vit_large_patch14_clip_224:openai_ft_in12k_in1k	.578
75	yudixie_wbh_object_class_scaling_0415_imagenet	.577
76	vit_huge_patch14_clip_224:laion2b_ft_in12k_in1k	.577
77	AdvProp_efficientnet-b6	.577
78	cvt_cvt-13-224-in1k_4_LucyV4	.576
79	convnext_tiny_imagenet_full_seed-0	.572
80	efficientnet_b2_imagenet_full	.572
81	AdvProp_efficientnet-b7	.571
82	convnext_xxlarge_clip	.570
83	convnext_femto_ols:d1_in1k	.569
84	vit_large_patch14_clip_224:laion2b_ft_in1k	.568
85	vit_large_patch14_clip_224:laion2b_ft_in12k_in1k	.565
86	grcnn	.563
87	mobilenet_v2_1_4_224	.562
88	convnext_large_clip_laion2b_finelayers	.561
89	convnext_tiny:in12k_ft_in1k	.554
90	convnext_base:clip_laiona_augreg_ft_in1k_384	.550
91	effnetb1_cutmix_augmix_sam_e1_5avg_424x377	.537
92	convnext_large_mlp:clip_laion2b_augreg_ft_in1k_384	.535
93	convnext_small_imagenet_full_seed-0	.534
94	gabor_filter_entropy_4x4_v2_forcedCosine	.532
95	ReAlnet01_cornet	.530
96	alexnet	.527
97	gabor_filter_entropy_4x4_v2	.526
98	convnext_base_imagenet_full_seed-0	.526
99	vit_base_patch16_clip_224:openai_ft_in1k	.525
100	ReAlnet03_cornet	.524
101	convnext_base_fb_in22k_ft_in1k_gram_aligned_dinov3	.523
102	convnext_base_fb_in1k	.520
103	ReAlnet04_cornet	.520
104	vit_relpos_base_patch32_plus_rpn_256:sw_in1k	.517
105	effnetb1_272x240	.519
106	gabor_filter_entropy_4x4	.515
107	AlexNet_SIN	.512
108	AT_efficientnet-b2	.509
109	AdvProp_efficientnet-b2	.509
110	effnetb1_cutmixpatch_SAM_robust32_avge6e8e9e10_manylayers_324x288	.509
111	regnety_032	.505
112	efficientnet_b0	.505
113	resnet-50-robust	.497
114	AlexNet_SIN_fov12	.496
115	AlexNet_SIN_fov16	.482
116	resnet18_fair	.480
117	effnetb1_cutmixpatch_augmix_robust32_avge4e7_manylayers_324x288	.478
118	VOneCORnet-S	.477
119	deepeisnn_ei_cifar10_vgg19	.465
120	deepeisnn_ei_cifar10_resnet18	.435
121	alexnet_training_seed_06	.409
122	alexnet_training_seed_07	.390
123	alexnet_training_seed_01	.383
124	yudixie_wbh_object_class_scaling_0415_run_2	.381
125	alexnet_training_seed_03	.379
126	alexnet_training_seed_10	.375
127	alexnet_training_seed_02	.369
128	ReAlnet01_cornet_fov4	.370
129	yudixie_wbh_object_class_scaling_0415_run_0	.350
130	yudixie_wbh_object_class_scaling_0415_run_3	.350
131	alexnet_training_seed_09	.350
132	predictive_coding_pc	.351
133	pr1_stl10_disentangled_alpha04	.348
134	yudixie_wbh_object_class_scaling_0415_run_1	.337
135	ViT_L_32_imagenet1k	.308
136	convnext_base_fb_in22k_ft_in1k	.225
137	gabor_filter_mean_abs_4x4_v2	.220
138	compact_resnet50_robust_V4	.183
139	convnext_base_fb_in1k_gram_aligned_dinov3	.182
140	vit_huge_clip336_laion
141	pnasnet_large_halfPrecision
142	hmax

Benchmark bibtex

None

Ceiling

0.48.

Note that scores are relative to this ceiling.

Data: Hebart2023_fmri.V2

Metric: ridgecv