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("Papale2025.V4-ridgecv")
score = benchmark(my_model)

Benchmark API

Code examples

Model scores

Score Legend Min Alignment Max Alignment

Rank	Model	Score
1	convnext_xxlarge_clip	.657
2	custom_model_cv_18_dagger_408	.649
3	AdvProp_efficientnet-b2	.648
4	AT_efficientnet-b2	.648
5	shufflenet_v2_x1_0	.628
6	dinov2_vitl14_reg_lc_featread	.624
7	dinov2_vitl14_reg_lc	.624
8	vit_relpos_base_patch16_clsgap_224:sw_in1k	.615
9	cvt_cvt-13-384-in1k_4_LucyV4	.612
10	resnet50-moclr8deg	.607
11	cvt_cvt-21-384-in22k_finetuned-in1k_4_LucyV4	.606
12	voneresnet-50	.605
13	resnet50-vitoimagevidnet8	.603
14	resnet50-VITO-8deg-cc	.603
15	cvt_cvt-21-384-in1k_4_LucyV4	.603
16	cvt_cvt-21-224-in1k_4_LucyV4	.601
17	convnext_tiny:in12k_ft_in1k	.599
18	seresnext50_32x4d	.596
19	cvt_cvt-13-224-in1k_4_LucyV4	.594
20	vit_large_patch14_clip_224:openai_ft_in1k	.593
21	ReAlnet01_cornet	.588
22	ReAlnet03_cornet	.586
23	ReAlnet04_cornet	.586
24	resnet50-SIN	.586
25	resnet152_imagenet_full	.584
26	vit_base_patch16_clip_224:openai_ft_in12k_in1k	.581
27	efficientnet_b0	.580
28	AdvProp_efficientnet-b8	.579
29	resnet50_ewconplus_wzc	.579
30	resnet50_st_wzc_seed3_2_323	.578
31	mobilenet_v2_1_4_224	.575
32	resnet50_st_wzc_seed7_2_323	.573
33	AdvProp_efficientnet-b4	.573
34	resnet50-SIN_IN_IN	.572
35	resnet_SIN_IN_FT_IN	.572
36	convnext_tiny_sup	.568
37	dinov2_vitl14_lc	.567
38	resnet_50_v1_spiking	.566
39	resnet50_tutorial	.566
40	resnet50-sup	.566
41	resnet_50_v1	.566
42	resnet50-SIN_IN	.565
43	focalnet_tiny_lrf_in1k	.563
44	VOneCORnet-S	.557
45	Res2Net50_26w_4s	.556
46	regnety_032	.555
47	AlexNet_SIN	.554
48	resnet50_ewconplus_wzc_seed6_2_323	.552
49	convnext_xlarge:fb_in22k_ft_in1k	.551
50	deit_small_imagenet_full_seed-0	.550
51	vit_tiny_r_s16_p8_384:augreg_in21k_ft_in1k	.550
52	vit_base_patch16_clip_224:openai_ft_in1k	.550
53	efficientnet_b2_imagenet_full	.548
54	resnext101_32x16d_wsl	.547
55	resnext101_32x48d_wsl	.545
56	cvt_cvt-13-384-in22k_finetuned-in1k_4_LucyV4	.544
57	resnet_50_v2	.543
58	vit_large_patch14_clip_224:laion2b_ft_in1k	.543
59	antialiased-r50	.543
60	convnext_base:clip_laiona_augreg_ft_in1k_384	.541
61	resnet50_ewconplus_wzc_seed5_2__323	.538
62	resnet-50-robust	.538
63	convnext_tiny_imagenet_full_seed-0	.534
64	resnext101_32x8d_wsl	.534
65	resnext101_32x32d_wsl	.534
66	deit_large_imagenet_full_seed-0	.533
67	resnet50_ewconplus_wzc_seed2_2__323	.528
68	convnext_large_mlp:clip_laion2b_augreg_ft_in1k_384	.525
69	convnext_large_imagenet_full_seed-0	.523
70	effnetb1_272x240	.522
71	resnet50_robust_l2_eps1	.520
72	AlexNet_SIN_fov12	.519
73	resnet50_imagenet_full	.518
74	convnext_small_imagenet_full_seed-0	.508
75	voneresnet-50-non_stochastic	.508
76	convnext_base_imagenet_full_seed-0	.507
77	vit_relpos_base_patch32_plus_rpn_256:sw_in1k	.507
78	convnext_femto_ols:d1_in1k	.501
79	effnetb1_cutmixpatch_augmix_robust32_avge4e7_manylayers_324x288	.498
80	effnetb1_cutmixpatch_SAM_robust32_avge6e8e9e10_manylayers_324x288	.491
81	resnet18_fair	.491
82	AdvProp_efficientnet-b6	.488
83	AdvProp_efficientnet-b7	.482
84	swin_small_patch4_window7_224:ms_in22k_ft_in1k	.480
85	densenet-121	.478
86	predictive_coding_pc	.458
87	grcnn	.456
88	effnetb1_cutmix_augmix_sam_e1_5avg_424x377	.450
89	pr1_stl10_disentangled_alpha04	.427
90	ViT_L_32_imagenet1k	.420
91	AlexNet_SIN_fov16	.359
92	alexnet_training_seed_02	.325
93	alexnet_training_seed_03	.323
94	alexnet_training_seed_06	.320
95	alexnet_training_seed_01	.314
96	alexnet_training_seed_09	.311
97	alexnet_training_seed_07	.307
98	alexnet_training_seed_10	.305
99	gabor_filter_entropy_4x4_v2_forcedCosine	.284
100	gabor_filter_entropy_4x4_v2	.281
101	gabor_filter_entropy_4x4	.273
102	ReAlnet01_cornet_fov4	.272
103	hmax	.236
104	gabor_filter_mean_abs_4x4_v2	.177
105	compact_resnet50_robust_V4	.134
106	eicircuit_resnet18_bn_20260919
107	vit_huge_clip336_laion
108	vit_large_clip336_openai
109	dinov2_vitl14_lc_res336
110	eva02_large_in22k
111	dinov2_vitg14_reg_lc
112	dinov2_vitg14_lc
113	convnext_base_fb_in1k
114	resnet50_st_wzc_seed6_2_323
115	cvt_cvt-w24-384-in22k_finetuned-in1k_4
116	vit_large_patch14_clip_336:laion2b_ft_in1k
117	vit_large_patch14_clip_336:openai_ft_in12k_in1k
118	vit_huge_patch14_clip_224:laion2b_ft_in12k_in1k
119	vit_large_patch14_clip_224:laion2b_ft_in12k_in1k
120	vit_large_patch14_clip_224:openai_ft_in12k_in1k
121	pnasnet_large_halfPrecision
122	convnext_large:fb_in22k_ft_in1k
123	deit_base_imagenet_full_seed-0
124	convnext_xxlarge:clip_laion2b_soup_ft_in1k

Benchmark bibtex

@article{papale_extensive_2025,
	title = {An extensive dataset of spiking activity to reveal the syntax of the ventral stream},
	volume = {113},
	issn = {08966273},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S089662732400881X},
	doi = {10.1016/j.neuron.2024.12.003},
	journal = {Neuron},
	author = {Papale, Paolo and Wang, Feng and Self, Matthew W. and Roelfsema, Pieter R.},
	year = {2025},
}

Ceiling

0.98.

Note that scores are relative to this ceiling.

Data: Papale2025.V4

Metric: ridgecv