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	efficientnet_b1_imagenet_full	.631
10	dinov2_vitl14_lc_res336	.631
11	dinov2_vitl14_reg_lc_featread	.631
12	dinov2_vitl14_reg_lc	.631
13	deit3_base_patch16_224_fb_in1k_gram_aligned_dinov3	.630
14	deit3_base_patch16_224_fb_in1k	.630
15	convnext_large:fb_in22k_ft_in1k	.630
16	resnet50_st_wzc_seed7_2_323	.628
17	resnet50_st_wzc_seed6_2_323	.627
18	resnet50-SIN_IN_IN	.626
19	resnet_SIN_IN_FT_IN	.626
20	dinov2_vitl14_lc	.625
21	resnet50_st_wzc_seed3_2_323	.625
22	dinov2_vitg14_lc	.622
23	dinov2_vitg14_reg_lc	.621
24	convnext_large_in22k_supervised	.618
25	antialiased-r50	.618
26	ijepa_vith14_linhead	.615
27	cvt_cvt-21-224-in1k_4_LucyV4	.614
28	Res2Net50_26w_4s	.613
29	resnext101_32x16d_wsl	.612
30	deit_base_imagenet_full_seed-0	.611
31	resnet152_imagenet_full	.610
32	resnet50_ewconplus_wzc_seed5_2__323	.610
33	voneresnet-50-non_stochastic	.609
34	resnext101_32x8d_wsl	.609
35	focalnet_tiny_lrf_in1k	.608
36	eva02_large_in22k	.607
37	resnet50_ewconplus_wzc_seed6_2_323	.607
38	resnet_50_v1	.607
39	resnet50-sup	.607
40	resnet_50_v1_spiking	.607
41	resnet50_imagenet_full	.606
42	cvt_cvt-13-384-in22k_finetuned-in1k_4_LucyV4	.605
43	resnet50-SIN_IN	.605
44	seresnext50_32x4d	.604
45	resnet50-vitoimagevidnet8	.603
46	resnet50-VITO-8deg-cc	.603
47	deit_large_imagenet_full_seed-0	.603
48	resnet50_ewconplus_wzc_seed2_2__323	.603
49	cvt_cvt-21-384-in22k_finetuned-in1k_4_LucyV4	.603
50	resnet50_robust_l2_eps1	.602
51	resnet50-moclr8deg	.600
52	resnet101_ecoset_full	.600
53	vit_relpos_base_patch16_clsgap_224:sw_in1k	.599
54	vit_large_patch14_clip_336:openai_ft_in12k_in1k	.599
55	cvt_cvt-21-384-in1k_4_LucyV4	.598
56	resnet50_byol_linhead	.598
57	resnext101_32x32d_wsl	.597
58	resnet_50_v2	.595
59	resnet50_ewconplus_wzc	.596
60	resnet152_ecoset_full	.596
61	resnet50_barlowtwins_linhead	.593
62	voneresnet-50	.593
63	densenet-121	.592
64	convnext_large_imagenet_full_seed-0	.592
65	convnext_xxlarge:clip_laion2b_soup_ft_in1k	.592
66	custom_model_cv_18_dagger_408	.591
67	resnext101_32x48d_wsl	.590
68	convnext_tiny_sup	.590
69	shufflenet_v2_x1_0	.589
70	vit_large_patch14_clip_336:laion2b_ft_in1k	.588
71	vit_base_patch16_clip_224:openai_ft_in12k_in1k	.587
72	resnet50_simsiam_linhead	.587
73	resnet50_tutorial	.586
74	eicircuit_resnet18_bn_20260919	.585
75	AdvProp_efficientnet-b4	.584
76	deepeisnn_ei_imagenet_resnet18	.584
77	AdvProp_efficientnet-b8	.583
78	resnet50-SIN	.582
79	convnext_xlarge:fb_in22k_ft_in1k	.581
80	resnet34_ecoset_full	.580
81	vit_large_patch14_clip_224:openai_ft_in1k	.579
82	vit_large_patch14_clip_224:openai_ft_in12k_in1k	.578
83	resnet34_imagenet_full	.578
84	yudixie_wbh_object_class_scaling_0415_imagenet	.577
85	vit_huge_patch14_clip_224:laion2b_ft_in12k_in1k	.577
86	AdvProp_efficientnet-b6	.577
87	cvt_cvt-13-224-in1k_4_LucyV4	.576
88	resnet18_ecoset_full	.576
89	convnext_tiny_imagenet_full_seed-0	.572
90	efficientnet_b2_imagenet_full	.572
91	AdvProp_efficientnet-b7	.571
92	convnext_xxlarge_clip	.570
93	convnext_femto_ols:d1_in1k	.569
94	vit_large_patch14_clip_224:laion2b_ft_in1k	.568
95	efficientnet_b0_imagenet_full	.567
96	resnet18_imagenet_full	.566
97	vit_large_patch14_clip_224:laion2b_ft_in12k_in1k	.565
98	grcnn	.563
99	resnet50_imagenet_100_seed-0	.563
100	mobilenet_v2_1_4_224	.562
101	convnext_large_clip_laion2b_finelayers	.561
102	mehrer2020_alexnet_training_seed_07	.558
103	mehrer2020_alexnet_training_seed_04	.557
104	convnext_tiny:in12k_ft_in1k	.554
105	mehrer2020_alexnet_training_seed_02	.553
106	convnext_base:clip_laiona_augreg_ft_in1k_384	.550
107	mehrer2020_alexnet_training_seed_10	.548
108	mehrer2020_alexnet_training_seed_05	.548
109	mehrer2020_alexnet_training_seed_06	.545
110	mehrer2020_alexnet_training_seed_03	.543
111	resnet50_simclr_linhead_01norm	.543
112	mehrer2020_alexnet_training_seed_09	.541
113	ReAlnet07_cornet	.539
114	mehrer2020_alexnet_training_seed_01	.535
115	effnetb1_cutmix_augmix_sam_e1_5avg_424x377	.537
116	ReAlnet08_cornet	.535
117	mehrer2020_alexnet_training_seed_08	.535
118	convnext_large_mlp:clip_laion2b_augreg_ft_in1k_384	.535
119	convnext_small_imagenet_full_seed-0	.534
120	ReAlnet05_cornet	.532
121	gabor_filter_entropy_4x4_v2_forcedCosine	.532
122	ReAlnet01_cornet_fov12	.532
123	ReAlnet06_cornet	.531
124	ReAlnet01_cornet	.530
125	ReAlnet09_cornet	.527
126	alexnet	.527
127	ReAlnet10_cornet	.526
128	gabor_filter_entropy_4x4_v2	.526
129	convnext_base_imagenet_full_seed-0	.526
130	ReAlnet01_cornet_fov16	.525
131	vit_base_patch16_clip_224:openai_ft_in1k	.525
132	ReAlnet03_cornet	.524
133	convnext_small_imagenet_100_seed-0	.524
134	convnext_base_fb_in22k_ft_in1k_gram_aligned_dinov3	.523
135	deit_small_imagenet_100_seed-0	.522
136	ReAlnet02_cornet	.521
137	convnext_base_fb_in1k	.520
138	ReAlnet04_cornet	.520
139	vit_relpos_base_patch32_plus_rpn_256:sw_in1k	.517
140	effnetb1_272x240	.519
141	gabor_filter_entropy_4x4	.515
142	AlexNet_SIN	.512
143	AT_efficientnet-b2	.509
144	AdvProp_efficientnet-b2	.509
145	effnetb1_cutmixpatch_SAM_robust32_avge6e8e9e10_manylayers_324x288	.509
146	regnety_032	.505
147	efficientnet_b0	.505
148	mehrer2020_alexnet_training_seed_01_fov12	.498
149	resnet-50-robust	.497
150	AlexNet_SIN_fov12	.496
151	resnet50_ecoset_full	.489
152	pnasnet_large_halfPrecision	.491
153	AlexNet_SIN_fov16	.482
154	resnet18_fair	.480
155	effnetb1_cutmixpatch_augmix_robust32_avge4e7_manylayers_324x288	.478
156	VOneCORnet-S	.477
157	mehrer2020_alexnet_training_seed_01_fov16	.477
158	resnet101_imagenet_full	.468
159	deepeisnn_ei_cifar10_vgg19	.465
160	resnet50_vicreg_linhead	.451
161	deepeisnn_ei_cifar10_resnet18	.435
162	alexnet_training_seed_06	.409
163	mehrer2020_alexnet_training_seed_01_fov4	.396
164	alexnet_training_seed_07	.390
165	alexnet_training_seed_01	.383
166	yudixie_wbh_object_class_scaling_0415_run_2	.381
167	alexnet_training_seed_03	.379
168	alexnet_training_seed_10	.375
169	AlexNet_SIN_fov4	.375
170	alexnet_training_seed_02	.369
171	ReAlnet01_cornet_fov4	.370
172	yudixie_wbh_object_class_scaling_0415_run_0	.350
173	yudixie_wbh_object_class_scaling_0415_run_3	.350
174	alexnet_training_seed_09	.350
175	predictive_coding_pc	.351
176	pr1_stl10_disentangled_alpha04	.348
177	yudixie_wbh_object_class_scaling_0415_run_1	.337
178	ViT_L_32_imagenet1k	.308
179	convnext_base_fb_in22k_ft_in1k	.225
180	gabor_filter_mean_abs_4x4_v2	.220
181	compact_resnet50_robust_V4	.183
182	convnext_base_fb_in1k_gram_aligned_dinov3	.182
183	vit_huge_clip336_laion
184	hmax

Benchmark bibtex

None

Ceiling

0.48.

Note that scores are relative to this ceiling.

Data: Hebart2023_fmri.V2

Metric: ridgecv