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("Gifford2022.IT-ridgecv")
score = benchmark(my_model)

Benchmark API

Code examples

Model scores

Score Legend Min Alignment Max Alignment

Rank	Model	Score
1	resnext101_32x32d_wsl	.284
2	vit_large_patch14_clip_224:laion2b_ft_in12k_in1k	.277
3	resnet50-moclr8deg	.278
4	resnext101_32x48d_wsl	.277
5	deit_large_imagenet_full_seed-0	.273
6	convnext_base:clip_laiona_augreg_ft_in1k_384	.269
7	convnext_tiny:in12k_ft_in1k	.266
8	dinov2_vitl14_lc	.265
9	vit_base_patch16_clip_224:openai_ft_in12k_in1k	.264
10	densenet-121	.262
11	convnext_xxlarge:clip_laion2b_soup_ft_in1k	.261
12	vit_relpos_base_patch16_clsgap_224:sw_in1k	.261
13	vit_large_patch14_clip_336:laion2b_ft_in1k	.259
14	resnet50-vitoimagevidnet8	.259
15	resnet50-VITO-8deg-cc	.259
16	resnet50_tutorial	.257
17	convnext_large_imagenet_full_seed-0	.257
18	custom_model_cv_18_dagger_408	.257
19	deit_base_imagenet_full_seed-0	.256
20	convnext_large:fb_in22k_ft_in1k	.252
21	voneresnet-50	.252
22	ReAlnet03_cornet	.252
23	vit_huge_patch14_clip_224:laion2b_ft_in12k_in1k	.251
24	resnet50-SIN_IN_IN	.252
25	ReAlnet01_cornet	.251
26	vit_large_patch14_clip_224:openai_ft_in1k	.250
27	focalnet_tiny_lrf_in1k	.250
28	resnet50_ewconplus_wzc	.250
29	convnext_small_imagenet_full_seed-0	.250
30	resnet50_ewconplus_wzc_seed5_2__323	.249
31	convnext_xlarge:fb_in22k_ft_in1k	.250
32	resnet50_robust_l2_eps1	.248
33	seresnext50_32x4d	.249
34	dinov2_vitl14_reg_lc_featread	.248
35	dinov2_vitl14_reg_lc	.248
36	voneresnet-50-non_stochastic	.247
37	vit_large_patch14_clip_224:openai_ft_in12k_in1k	.247
38	resnet_50_v1	.247
39	resnet50-sup	.247
40	resnet_50_v1_spiking	.247
41	vit_large_patch14_clip_336:openai_ft_in12k_in1k	.247
42	ReAlnet04_cornet	.247
43	shufflenet_v2_x1_0	.248
44	VOneCORnet-S	.246
45	resnet50_st_wzc_seed6_2_323	.246
46	resnet152_imagenet_full	.247
47	antialiased-r50	.246
48	deit_small_imagenet_full_seed-0	.245
49	cvt_cvt-13-384-in22k_finetuned-in1k_4_LucyV4	.243
50	resnet50_ewconplus_wzc_seed6_2_323	.243
51	convnext_tiny_imagenet_full_seed-0	.243
52	convnext_base_imagenet_full_seed-0	.242
53	resnet50_st_wzc_seed7_2_323	.241
54	resnet50_imagenet_full	.241
55	cvt_cvt-w24-384-in22k_finetuned-in1k_4	.240
56	resnet50_st_wzc_seed3_2_323	.239
57	vit_large_patch14_clip_224:laion2b_ft_in1k	.239
58	Res2Net50_26w_4s	.240
59	resnet-50-robust	.239
60	convnext_femto_ols:d1_in1k	.238
61	resnet50_ewconplus_wzc_seed2_2__323	.238
62	resnet50-SIN_IN	.237
63	efficientnet_b0	.236
64	cvt_cvt-13-384-in1k_4_LucyV4	.236
65	convnext_large_mlp:clip_laion2b_augreg_ft_in1k_384	.236
66	vit_tiny_r_s16_p8_384:augreg_in21k_ft_in1k	.235
67	resnet50-SIN	.235
68	vit_base_patch16_clip_224:openai_ft_in1k	.234
69	cvt_cvt-13-224-in1k_4_LucyV4	.233
70	vit_relpos_base_patch32_plus_rpn_256:sw_in1k	.233
71	mobilenet_v2_1_4_224	.232
72	resnet_50_v2	.232
73	swin_small_patch4_window7_224:ms_in22k_ft_in1k	.231
74	AT_efficientnet-b2	.230
75	AdvProp_efficientnet-b2	.230
76	cvt_cvt-21-384-in1k_4_LucyV4	.230
77	cvt_cvt-21-384-in22k_finetuned-in1k_4_LucyV4	.230
78	effnetb1_cutmixpatch_SAM_robust32_avge6e8e9e10_manylayers_324x288	.228
79	resnext101_32x8d_wsl	.226
80	resnet_SIN_IN_FT_IN	.226
81	AdvProp_efficientnet-b6	.224
82	cvt_cvt-21-224-in1k_4_LucyV4	.221
83	vit_large_clip336_openai	.217
84	AdvProp_efficientnet-b7	.215
85	AdvProp_efficientnet-b4	.215
86	effnetb1_cutmixpatch_augmix_robust32_avge4e7_manylayers_324x288	.214
87	effnetb1_272x240	.213
88	AdvProp_efficientnet-b8	.213
89	regnety_032	.210
90	convnext_tiny_sup	.210
91	eicircuit_resnet18_bn_20260919	.210
92	ReAlnet01_cornet_fov4	.212
93	grcnn	.211
94	alexnet	.206
95	efficientnet_b2_imagenet_full	.202
96	ViT_L_32_imagenet1k	.196
97	effnetb1_cutmix_augmix_sam_e1_5avg_424x377	.186
98	AlexNet_SIN_fov12	.176
99	AlexNet_SIN	.173
100	AlexNet_SIN_fov16	.172
101	pr1_stl10_disentangled_alpha04	.162
102	predictive_coding_pc	.147
103	resnet18_fair	.142
104	alexnet_training_seed_06	.103
105	alexnet_training_seed_02	.103
106	gabor_filter_entropy_4x4_v2_forcedCosine	.103
107	gabor_filter_entropy_4x4	.102
108	gabor_filter_entropy_4x4_v2	.101
109	convnext_base_fb_in1k	.098
110	alexnet_training_seed_09	.098
111	alexnet_training_seed_01	.090
112	alexnet_training_seed_03	.087
113	alexnet_training_seed_10	.086
114	alexnet_training_seed_07	.084
115	compact_resnet50_robust_V4	.071
116	gabor_filter_mean_abs_4x4_v2	.066
117	hmax	.050
118	vit_huge_clip336_laion
119	convnext_xxlarge_clip
120	dinov2_vitl14_lc_res336
121	eva02_large_in22k
122	dinov2_vitg14_reg_lc
123	dinov2_vitg14_lc
124	pnasnet_large_halfPrecision
125	resnext101_32x16d_wsl

Benchmark bibtex

@article{gifford_large_2022,
	title = {A large and rich {EEG} dataset for modeling human visual object recognition},
	volume = {264},
	issn = {10538119},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S1053811922008758},
	doi = {10.1016/j.neuroimage.2022.119754},
	journal = {NeuroImage},
	author = {Gifford, Alessandro T. and Dwivedi, Kshitij and Roig, Gemma and Cichy, Radoslaw M.},
	year = {2022},
}

Ceiling

0.42.

Note that scores are relative to this ceiling.

Data: Gifford2022.IT

Metric: ridgecv