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("Marques2020_Schiller1976-sf_bandwidth")
score = benchmark(my_model)

Benchmark API

Code examples

Model scores

Score Legend Min Alignment Max Alignment

Rank	Model	Score
1	alexnet_early_checkpoint	.985
2	resnet50_primary_visual_cortex	.978
3	vonegrcnn_47e	.977
4	compact_cornets_V4	.975
5	yudixie_resnet50_translation_rotation_0_240908	.970
6	resnet101_ecoset_full	.969
7	effnetb1_cutmixrespatch_SAM_robust32_e2_manylayers_324x288	.967
8	effnetb1_cutmixrespatch_SAM_robust32_e10_manylayers_324x288	.965
9	effnetb1_cutmixpatch_augmix_robust32_e5_324x288	.966
10	effnetb1_cutmixpatch_augmix_robust32_avge4e7_manylayers_324x288	.967
11	effnetb1_cutmixpatch_SAM_robust32_avge6e8e9e10_manylayers_324x288	.966
12	0.5x_resnet-18_LC_w_sh_1_iter	.965
13	compact_vgg19_IT	.964
14	fulltest_microblockvf_nobottleneck_freeat_nopretrain_eps2_m4	.966
15	yudixie_resnet50_category_class_0_240908	.959
16	resnet152_imagenet_full	.957
17	Res2Net50_26w_4s	.956
18	resnet-18-LC_w_sh_1_iter_m	.953
19	resnet-18-LC_w_sh_100_iter_m	.948
20	resnet101	.945
21	yudixie_resnet18_cat_obj_class_all_latents_0_240719	.946
22	yudixie_resnet18_object_class_0_240719	.945
23	resnet-18-LC_w_sh_1_iter_conv_init_m	.942
24	resnet50_FractalDB	.941
25	vonegrcnn_52e_full	.938
26	resnet34_ecoset_full	.939
27	ReAlnet03_cornet	.938
28	AlexNet_SIN	.938
29	efficientnet_b1_imagenet_full	.938
30	ReAlnet09	.936
31	compact_resnet50_robust_V4	.938
32	ReAlnet09_cornet	.939
33	ReAlnet03	.939
34	alexnet	.938
35	alexnet	.934
36	alexnet	.933
37	alexnet	.934
38	alexnet	.934
39	alexnet-baseline	.932
40	ReAlnet10_ALL	.933
41	alexnet	.934
42	ReAlnet08_cornet	.932
43	alexnet	.930
44	BiT-S-R152x2	.931
45	resnext101_32x8d_wsl	.931
46	ReAlnet08	.931
47	r3m_resnet50_nocrop	.928
48	voneresnet-50-non_stochastic	.929
49	resnet18_imagenet_full	.928
50	vggface	.931
51	ReAlnet10_cornet	.928
52	resnet18_ecoset_full	.926
53	mobilenet_v2_1-4_224_pytorch	.927
54	ReAlnet04_cornet	.928
55	ReAlnet10	.925
56	ReAlnet07_cornet	.923
57	ReAlnet04	.925
58	ReAlnet07	.926
59	ReAlnet05	.924
60	artResNet18_1	.926
61	mobilenet_v2_1.0_96	.921
62	yudixie_resnet18_random_0_240719	.924
63	r3m_resnet50	.924
64	ReAlnet05_cornet	.923
65	nasnet_large-tf	.922
66	resnet50-SIN_IN	.922
67	resnet-18-LC_conv_init_m	.922
68	BiT-M-R50x3	.920
69	alexnet_random_linf8_perturb	.920
70	ReAlnet08_ALL	.922
71	ReAlnet06_ALL	.921
72	ReAlnet01	.920
73	ReAlnet06	.919
74	ReAlnet06_cornet	.920
75	inception_v2-tf	.919
76	ReAlnet07_ALL	.921
77	ReAlnet01_cornet	.917
78	ReAlnet05_ALL	.918
79	ReAlnet02_cornet	.918
80	ReAlnet03_ALL	.916
81	ReAlnet04_ALL	.916
82	ReAlnet02_ALL	.918
83	ReAlnet01_ALL	.916
84	resnet152_ecoset_full	.916
85	0.5x_resnet-18	.915
86	yudixie_resnet18_rotation_reg_0_240719	.915
87	ReAlnet02	.915
88	antialiased-rnext101_32x8d	.914
89	convnext_tiny:in12k_ft_in1k	.914
90	ReAlnet09_ALL	.914
91	CORnet-S	.912
92	resnet101_imagenet_full	.911
93	cornet_s	.909
94	efficientnet_b2_imagenet_full	.907
95	BiT-M-R152x2	.907
96	nasnet_mobile	.906
97	mobilenet_v2_1.0_128-tf	.903
98	vit_relpos_base_patch32_plus_rpn_256:sw_in1k	.905
99	yudixie_resnet50_rotation_reg_0_240908	.905
100	mobilenet_v2_0.5_224-tf	.900
101	convnext_xlarge:fb_in22k_ft_in1k	.902
102	BiT-M-R101x3	.900
103	mobilenet_v2_0.5_192-tf	.899
104	r3m_resnet18	.902
105	alexnet_training_seed_01	.901
106	resnet-50_untrained	.901
107	texture_shape_resnet50_trained_on_SIN	.900
108	alexnet_training_seed_10	.900
109	resnet-18-LC_w_sh_100_iter_conv_init_m	.899
110	resnet-50_v1-tf	.898
111	0.5x_resnet-18_LC	.899
112	resnet50-SIN	.898
113	resnet50_finetune_cutmix_e3_robust_linf8255_e0_247x234	.897
114	RN50	.898
115	CLIP_resnet50	.894
116	alexnet_robust_correct	.896
117	resnet50_finetune_cutmix_AVGe2e3_robust_linf8255_e0_247x234	.896
118	CLIP_resnet50_float32	.895
119	resnet50_ewconplus_wzc	.895
120	nasnet_mobile-tf	.895
121	resnet-18-LC_m	.894
122	r3m_resnet34	.894
123	AdvProp_efficientnet-b0	.890
124	yudixie_resnet18_distance_reg_0_240719	.890
125	grcnn_robust_v1	.888
126	voneresnet-50	.887
127	0.5x_resnet-18_LC_w_sh_100_iter	.890
128	antialiased-r50	.887
129	antialias-resnet152	.887
130	resnet50	.885
131	yudixie_resnet50_translation_reg_0_240908	.886
132	grcnn_v2_text_noise	.885
133	deit_small_imagenet_100_seed-0	.882
134	alexnet_training_seed_03	.883
135	BiT-S-R101x3	.882
136	alexnet_training_seed_07	.882
137	resnet50_ecoset_full	.880
138	yudixie_resnet50_cat_obj_class_all_latents_0_240908	.881
139	alexnet_training_seed_09	.881
140	compact_cornets_IT	.877
141	resnet50_random_linf8_perturb	.877
142	BiT-S-R152x4	.876
143	voneresnet-50-robust	.876
144	mobilenet_v2_1.0_160-tf	.874
145	resnet-152_v2-tf	.874
146	densenet-169-keras	.874
147	resnet34_imagenet_full	.875
148	SWSL_resnext101_32x8d	.873
149	VOneCORnet-S	.870
150	resnet50-vicregl0p9	.871
151	resnet50_byol	.870
152	mobilenet_v2_1.0_192-tf	.868
153	yudixie_resnet18_category_class_0_240719	.868
154	vgg_16	.868
155	yudixie_resnet18_distance_rotation_0_240719	.867
156	focalnet_tiny_lrf_in1k	.864
157	grcnn_109	.864
158	convnext_large:fb_in22k_ft_in1k	.863
159	xception	.861
160	vgg-16-keras	.859
161	yudixie_resnet18_translation_rotation_0_240719	.859
162	resnet50	.858
163	resnet_50_v1	.856
164	resnet50_tutorial	.857
165	compact_vgg19_V4	.855
166	yudixie_resnet50_imagenet1kpret_0_240908	.854
167	compact_resnet50_IT	.855
168	inception_v3-tf	.855
169	resnet_50_v1_spiking_l4	.855
170	resnet_50_v1_spiking	.853
171	resnet-18_untrained	.854
172	resnet50-sup	.852
173	yudixie_resnet50_distance_translation_0_240908	.855
174	resnet_50_v1_spiking_l3	.851
175	resnet_50_v1_spiking_l4a	.851
176	resnet-18-LC_d_w_sh_1x1_conv_init_m	.852
177	resnet50_random_l2_perturb	.849
178	BiT-S-R101x1	.847
179	resnet_50_v2	.846
180	BiT-S-R50x3	.846
181	alexnet_training_seed_02	.847
182	effnetb1_272x240	.847
183	resnet-18-LC_w_sh_10_iter_conv_init_m	.845
184	inception_v1	.845
185	yudixie_resnet50_distance_translation_rotation_0_240908	.845
186	AdvProp_efficientnet-b8	.842
187	alexnet_reduced_aliasing_early_checkpoint	.842
188	resnet50-vicregl0p75	.840
189	resnet50_imagenet_full	.841
190	BiT-S-R50x1	.839
191	yudixie_resnet50_object_class_0_240908	.840
192	vit_large_patch14_clip_224:laion2b_ft_in1k	.840
193	resnet50-SIN_IN_IN	.838
194	yudixie_resnet18_imagenet1kpret_0_240719	.836
195	AdvProp_efficientnet-b6	.836
196	0.5x_resnet-18_LC_w_sh_10_iter	.836
197	resnet-152_v1-tf	.834
198	resnet50_simclr	.835
199	deit_large_imagenet_full_seed-0	.834
200	BiT-M-R50x1	.833
201	resnet50_moco_v2	.834
202	SWSL_resnet50	.830
203	yudixie_resnet50_distance_rotation_0_240908	.831
204	resnet-152_v2_pytorch	.830
205	effnetb1_cutmix_augmix_sam_e1_5avg_424x377	.828
206	cvt_cvt-13-224-in1k_4_LucyV4	.828
207	CLIP-RN50	.828
208	barlow-twins-resnet50	.828
209	densenet-169	.827
210	inception_v3	.825
211	mobilenet_v1_0.25_128	.824
212	compact_resnet50_V4	.822
213	alexnet_l2_3_robust	.820
214	resnet-18-LC_1st_conv_m	.818
215	vit_base_patch16_clip_224:openai_ft_in12k_in1k	.814
216	konkle_alexnetgn_ipcl_ref01_primary_model	.813
217	yudixie_resnet18_distance_translation_rotation_0_240719	.814
218	alexnet_training_seed_04	.814
219	deit_base_imagenet_full_seed-0	.813
220	ViT_L_32_imagenet1k	.815
221	vit_large_patch14_clip_224:openai_ft_in12k_in1k	.810
222	BiT-M-R101x1	.809
223	yolos_tiny	.810
224	AdvProp_efficientnet-b7	.809
225	resnet50-simclr-vissl	.805
226	grcnn	.804
227	yudixie_resnet50_random_0_240908	.803
228	yudixie_resnet18_distance_translation_0_240719	.803
229	resnet-101_v1-tf	.795
230	alexnet_training_seed_05	.794
231	mobilenet_v2_0.75_96	.793
232	CORnet-Z	.795
233	resnet-50x2_untrained	.794
234	resnet-18-LC_w_sh_10_iter_m	.793
235	yudixie_resnet50_distance_reg_0_240908	.792
236	vit_base_patch16_clip_224:openai_ft_in1k	.790
237	alexnet_training_seed_08	.787
238	konkle_alexnetgn_ipcl_ref12_supervised_ipcl_aug	.789
239	efficientnet_b0	.787
240	resnet50-moclr8deg	.785
241	inception_v1-tf	.785
242	resnet-18_test_m	.784
243	densenet-121	.783
244	resnet50-vicreg	.783
245	cvt_cvt-21-224-in1k_4_LucyV4	.782
246	AT_efficientnet-b2	.782
247	tf_efficientnetv2_s_in21ft1k_robust_linf12255_400x400	.780
248	blt_vs	.780
249	AdvProp_efficientnet-b2	.779
250	vit_large_patch14_clip_224:laion2b_ft_in12k_in1k	.778
251	mobilenet_v2_0.75_192-tf	.776
252	inception_v4-tf	.777
253	mobilenet_v2_1.4_224-tf	.773
254	vit_large_patch14_clip_224:openai_ft_in1k	.773
255	resnet50_imagenet_100_seed-0	.773
256	pnasnet_large-tf	.767
257	ViT-B/32	.764
258	vit_huge_patch14_clip_224:laion2b_ft_in12k_in1k	.766
259	mobilenet_v2_1_4_224	.765
260	resnet-50_v2-tf	.763
261	vision_transformer_vit_large_patch16_224	.762
262	resnet50-barlow	.755
263	resnet50_imagenet_10_seed-0	.749
264	vonegrcnn_62e_nobn	.749
265	omnivore_swinT	.747
266	mobilenet_v2_0.75_128	.742
267	my-model	.743
268	vit_large_patch14_clip_336:laion2b_ft_in1k	.742
269	briaai_rmbg_1_4	.738
270	yudixie_resnet18_translation_reg_0_240719	.739
271	v1-pyr-nodown	.735
272	deit_small_imagenet_full_seed-0	.736
273	AdvProp_efficientnet-b4	.728
274	shufflenet_v2_x1_0	.729
275	resnet50_linf_4_robust	.727
276	alexnet_linf_8_robust	.724
277	densenet-121-keras	.724
278	efficientnet-b7	.723
279	vit_relpos_base_patch16_clsgap_224:sw_in1k	.724
280	texture_shape_alexnet_trained_on_SIN	.723
281	resnet_SIN_IN_FT_IN	.722
282	vgg_19	.718
283	vonealexnet_gaussian_noise_std4_fixed	.717
284	mobilenet_v2_1_0_128	.718
285	cv_18_dagger_408_pretrained	.716
286	mobilenet_v2_1.0_224-tf	.714
287	resnet50-VITO-8deg-cc	.714
288	vit_huge_patch14_clip_336:laion2b_ft_in12k_in1k	.712
289	convnext_large_imagenet_full_seed-0	.712
290	inception_resnet_v2	.708
291	cvt_cvt-13-384-in22k_finetuned-in1k_4_LucyV4	.704
292	BiT-M-R152x4	.694
293	effnetv2m_custom384	.690
294	custom_model_cv_18_dagger_408	.685
295	mobilenet_v2_0_5_224	.680
296	resnet-101_v2-tf	.674
297	compact_resnet50_robust_IT	.674
298	resnet50-vitoimagevidnet8	.674
299	CORnetZ_CIFAR10_bs32_20_04	.670
300	cvt_cvt-21-384-in1k_4_LucyV4	.666
301	resnet50_l2_3_robust	.667
302	resnet50_robust_l2_eps1	.665
303	convnext_base:clip_laiona_augreg_ft_in1k_384	.664
304	resnet18_imagenet21kP	.664
305	convnext_xxlarge:clip_laion2b_soup_ft_in1k	.663
306	hmax	.662
307	mobilenet_v2_0.5_128	.660
308	resnet50-cifar	.661
309	convnext_tiny_imagenet_full_seed-0	.661
310	mobilenet_v2_0_75_224	.655
311	resnet50_robust_l2_eps3	.653
312	mobilenet_v2_0_5_192	.650
313	convnext_small_imagenet_100_seed-0	.649
314	CLIP_ViT-B_32	.646
315	cvt_cvt-13-384-in1k_4_LucyV4	.644
316	imagenet_l2_3_0	.643
317	imagenet_l2_10_0	.640
318	alexnet	.632
319	mobilenet_v2_0.75_224-tf	.626
320	vgg-19-keras	.617
321	mobilenet_v2_0_75_192	.615
322	omnivore_swinB	.609
323	vit_large_patch14_clip_336:openai_ft_in12k_in1k	.607
324	densenet-201	.604
325	cvt_cvt-w24-384-in22k_finetuned-in1k_4	.601
326	resnet50_linf_8_robust	.596
327	resnet-50-robust	.596
328	mobilenet_v2_1_0_160	.595
329	densenet-201-keras	.590
330	swin_small_patch4_window7_224:ms_in22k_ft_in1k	.586
331	omnivore_swinS	.585
332	vit_tiny_r_s16_p8_384:augreg_in21k_ft_in1k	.584
333	mobilenet_v2_0.35_224	.572
334	cvt_cvt-21-384-in22k_finetuned-in1k_4_LucyV4	.570
335	FrankRobWobv0	.567
336	convnext_femto_ols:d1_in1k	.557
337	alexnet_random_l2_3_perturb	.552
338	mobilenet_v2_1_0_224	.550
339	convnext_base_imagenet_full_seed-0	.546
340	convnext_large_mlp:clip_laion2b_augreg_ft_in1k_384	.532
341	mobilenet_v2_1_0_192	.523
342	mobilenet_v2_0_75_160	.520
343	convnext_small_imagenet_full_seed-0	.501
344	CORnetZ_CIFAR10	.495
345	efficientnet_b0_imagenet_full	.491
346	convnext_small_imagenet_10_seed-0	.488
347	resnet50_imagenet_1_seed-0	.481
348	mobilevit_small	.477
349	mobilenet_v2_0.75_160-tf	.471
350	resnet50-meshes-lt-100-original-pretrained	.456
351	resnet-18-LC_untrained	.454
352	mobilenet_v2_1_3_224	.442
353	alexnet_training_seed_06	.428
354	mobilenet_v2_1.3_224-tf	.399
355	resnet50_pretrained_with_retinal_waves	.397
356	resnet50-meshes-lt-100-original-scratch	.338
357	convnext_tiny_sup	.331
358	convnext_small_imagenet_1_seed-0	.293
359	my-model	.226
360	mobilenet_v2_0.5_160	.103
361	deit_small_imagenet_10_seed-0	.000
362	mobilenet_v2_0.35_160
363	resnet18-supervised
364	fitvid_trained_on_physion
365	openclip
366	resnext101_32x32d_wsl
367	resnext101_32x16d_wsl
368	resnext101_32x48d_wsl
369	resnet50_ImageNet
370	regnet_y_400mf
371	tv_efficientnet-b1
372	alexnet_ks_torevert
373	yudixie_resnet50_imagenet1kpret_0_240312
374	resnet_101_v1
375	resnet_152_v1
376	densenet_201_pytorch
377	pnasnet_large_pytorch
378	inception_v3_pytorch
379	inception_v4
380	nasnet_large
381	deit_small_imagenet_1_seed-0
382	pnasnet_large
383	vonegrcnn_62e_nobn
384	resnet_101_v2
385	vonegrcnn_47e
386	vonegrcnn_52e_full
387	resnet_152_v2

Benchmark bibtex

@article{Schiller1976,
            author = {Schiller, P. H. and Finlay, B. L. and Volman, S. F.},
            doi = {10.1152/jn.1976.39.6.1352},
            issn = {0022-3077},
            journal = {Journal of neurophysiology},
            number = {6},
            pages = {1334--1351},
            pmid = {825624},
            title = {{Quantitative studies of single-cell properties in monkey striate cortex. III. Spatial Frequency}},
            url = {http://www.ncbi.nlm.nih.gov/pubmed/825624},
            volume = {39},
            year = {1976}
            }

Ceiling

0.93.

Note that scores are relative to this ceiling.

Data: Marques2020_Schiller1976

Metric: sf_bandwidth