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_selective")
score = benchmark(my_model)

Benchmark API

Code examples

Model scores

Score Legend Min Alignment Max Alignment

Rank	Model	Score
1	imagenet_l2_10_0	1.0
2	resnext101_32x8d_wsl	1.000
3	BiT-M-R101x1	1.0
4	mobilenet_v2_0.75_160-tf	1.000
5	resnet-50-robust	1.0
6	resnet34_ecoset_full	1.0
7	barlow-twins-resnet50	1.000
8	yudixie_resnet50_distance_translation_rotation_0_240908	.999
9	alexnet_robust_correct	.999
10	fulltest_microblockvf_nobottleneck_freeat_nopretrain_eps2_m4	.999
11	resnet50-vitoimagevidnet8	.999
12	mobilenet_v2_1.0_96	.999
13	resnet50_robust_l2_eps1	.998
14	resnet50_robust_l2_eps3	.999
15	resnet50_l2_3_robust	.996
16	grcnn_v2_text_noise	.999
17	resnet-18-LC_w_sh_10_iter_m	.996
18	resnet50_linf_4_robust	.995
19	blt_vs	.996
20	alexnet_linf_8_robust	.996
21	yudixie_resnet50_category_class_0_240908	.996
22	AdvProp_efficientnet-b8	.998
23	yudixie_resnet50_rotation_reg_0_240908	.997
24	resnet50-moclr8deg	.997
25	resnet50-SIN	.995
26	yudixie_resnet18_cat_obj_class_all_latents_0_240719	.993
27	resnet50_linf_8_robust	.994
28	effnetb1_cutmixpatch_SAM_robust32_avge6e8e9e10_manylayers_324x288	.992
29	vit_relpos_base_patch32_plus_rpn_256:sw_in1k	.994
30	effnetb1_cutmixrespatch_SAM_robust32_e2_manylayers_324x288	.993
31	effnetb1_cutmixpatch_augmix_robust32_avge4e7_manylayers_324x288	.993
32	effnetb1_cutmixrespatch_SAM_robust32_e10_manylayers_324x288	.991
33	resnet-18-LC_1st_conv_m	.992
34	effnetb1_cutmixpatch_augmix_robust32_e5_324x288	.991
35	antialias-resnet152	.990
36	CORnetZ_CIFAR10	.991
37	alexnet_l2_3_robust	.990
38	resnet50_ecoset_full	.990
39	resnet101	.989
40	resnet50_finetune_cutmix_e3_robust_linf8255_e0_247x234	.989
41	BiT-S-R152x2	.990
42	resnet50_FractalDB	.987
43	alexnet_training_seed_06	.989
44	resnet50_primary_visual_cortex	.988
45	vgg-16-keras	.987
46	resnet50-simclr-vissl	.985
47	texture_shape_resnet50_trained_on_SIN	.984
48	vgg-19-keras	.985
49	resnet50_finetune_cutmix_AVGe2e3_robust_linf8255_e0_247x234	.987
50	resnet18_imagenet_full	.984
51	resnet101_ecoset_full	.984
52	alexnet_training_seed_08	.983
53	imagenet_l2_3_0	.984
54	AdvProp_efficientnet-b4	.985
55	vgg_16	.981
56	mobilenet_v2_1.0_128-tf	.980
57	resnet-50_untrained	.979
58	yudixie_resnet50_object_class_0_240908	.978
59	alexnet_training_seed_04	.975
60	yudixie_resnet50_distance_rotation_0_240908	.976
61	yudixie_resnet18_category_class_0_240719	.972
62	cornet_s	.972
63	resnet50_imagenet_10_seed-0	.969
64	voneresnet-50-non_stochastic	.970
65	inception_v1	.969
66	yudixie_resnet18_distance_reg_0_240719	.968
67	BiT-M-R50x3	.969
68	compact_vgg19_V4	.969
69	yudixie_resnet50_distance_translation_0_240908	.967
70	resnet-152_v2_pytorch	.966
71	yudixie_resnet18_translation_rotation_0_240719	.965
72	resnet34_imagenet_full	.967
73	yudixie_resnet18_distance_translation_0_240719	.966
74	resnet_101_v1	.964
75	BiT-S-R50x1	.964
76	voneresnet-50-robust	.963
77	Res2Net50_26w_4s	.960
78	alexnet_training_seed_09	.958
79	voneresnet-50	.959
80	r3m_resnet18	.955
81	grcnn_robust_v1	.954
82	resnet-18-LC_w_sh_1_iter_conv_init_m	.951
83	VOneCORnet-S	.954
84	resnet50-cifar	.951
85	yudixie_resnet50_cat_obj_class_all_latents_0_240908	.950
86	mobilevit_small	.947
87	yudixie_resnet50_translation_rotation_0_240908	.947
88	yudixie_resnet50_translation_reg_0_240908	.945
89	resnet50-vicregl0p9	.945
90	alexnet_training_seed_03	.944
91	resnet18_ecoset_full	.944
92	inception_v2-tf	.944
93	yudixie_resnet18_random_0_240719	.938
94	vonegrcnn_52e_full	.939
95	resnet-18-LC_w_sh_100_iter_conv_init_m	.936
96	yudixie_resnet18_object_class_0_240719	.937
97	resnet101_imagenet_full	.936
98	omnivore_swinB	.934
99	compact_cornets_IT	.934
100	compact_resnet50_robust_IT	.930
101	yudixie_resnet50_distance_reg_0_240908	.929
102	mobilenet_v2_1.0_160-tf	.928
103	antialiased-r50	.927
104	resnet50_imagenet_100_seed-0	.928
105	mobilenet_v2_0.5_192-tf	.926
106	resnet-18-LC_w_sh_100_iter_m	.924
107	briaai_rmbg_1_4	.925
108	grcnn_109	.924
109	CLIP-RN50	.925
110	resnet50_ewconplus_wzc	.922
111	resnet-18_untrained	.922
112	vggface	.921
113	resnet-18-LC_m	.921
114	yudixie_resnet18_distance_rotation_0_240719	.919
115	yudixie_resnet18_translation_reg_0_240719	.919
116	0.5x_resnet-18	.918
117	focalnet_tiny_lrf_in1k	.917
118	vonegrcnn_47e	.916
119	inception_v1-tf	.916
120	alexnet_training_seed_10	.914
121	vision_transformer_vit_large_patch16_224	.915
122	alexnet_random_linf8_perturb	.912
123	yudixie_resnet18_distance_translation_rotation_0_240719	.912
124	alexnet_training_seed_02	.907
125	resnet50-SIN_IN	.907
126	vonealexnet_gaussian_noise_std4_fixed	.905
127	0.5x_resnet-18_LC_w_sh_100_iter	.904
128	resnet-50x2_untrained	.902
129	yudixie_resnet50_random_0_240908	.901
130	mobilenet_v2_0.75_96	.900
131	grcnn	.898
132	resnet50-vicregl0p75	.898
133	xception	.896
134	alexnet_training_seed_01	.894
135	alexnet_early_checkpoint	.893
136	artResNet18_1	.893
137	resnet_101_v2	.891
138	resnet152_ecoset_full	.890
139	alexnet	.888
140	resnet-50_v1-tf	.883
141	convnext_small_imagenet_1_seed-0	.883
142	densenet-169	.882
143	resnet-18-LC_conv_init_m	.879
144	ViT_L_32_imagenet1k	.881
145	vonegrcnn_47e	.879
146	resnet-18-LC_w_sh_10_iter_conv_init_m	.876
147	tf_efficientnetv2_s_in21ft1k_robust_linf12255_400x400	.878
148	r3m_resnet34	.877
149	resnet50_imagenet_full	.876
150	konkle_alexnetgn_ipcl_ref12_supervised_ipcl_aug	.873
151	texture_shape_alexnet_trained_on_SIN	.870
152	compact_resnet50_IT	.870
153	yudixie_resnet18_imagenet1kpret_0_240719	.870
154	compact_resnet50_V4	.867
155	resnet50_tutorial	.867
156	yudixie_resnet50_imagenet1kpret_0_240908	.866
157	resnet_50_v1_spiking	.863
158	0.5x_resnet-18_LC	.865
159	resnet_50_v1_spiking_l4a	.865
160	resnet50_byol	.862
161	resnet_50_v1	.863
162	resnet_50_v1_spiking_l3	.861
163	resnet_50_v1_spiking_l4	.861
164	resnet50-sup	.861
165	alexnet_random_l2_3_perturb	.858
166	resnet_50_v2	.858
167	alexnet_training_seed_07	.858
168	resnet-18_test_m	.857
169	mobilenet_v2_1_0_192	.857
170	yudixie_resnet18_rotation_reg_0_240719	.857
171	vonegrcnn_62e_nobn	.856
172	r3m_resnet50_nocrop	.852
173	convnext_femto_ols:d1_in1k	.852
174	resnet-18-LC_w_sh_1_iter_m	.845
175	ReAlnet10	.845
176	ReAlnet10_cornet	.844
177	CLIP_resnet50	.841
178	BiT-M-R50x1	.841
179	CORnet-S	.839
180	CORnet-Z	.840
181	hmax	.839
182	mobilenet_v2_0.75_128	.840
183	mobilenet_v2_0.5_128	.840
184	0.5x_resnet-18_LC_w_sh_10_iter	.841
185	alexnet	.840
186	0.5x_resnet-18_LC_w_sh_1_iter	.840
187	alexnet-baseline	.840
188	alexnet	.839
189	alexnet	.841
190	resnet-18-LC_d_w_sh_1x1_conv_init_m	.838
191	alexnet	.840
192	CORnetZ_CIFAR10_bs32_20_04	.840
193	alexnet	.840
194	alexnet_reduced_aliasing_early_checkpoint	.839
195	alexnet	.840
196	alexnet	.839
197	ReAlnet02_ALL	.839
198	ReAlnet04_ALL	.840
199	ReAlnet03_ALL	.838
200	ReAlnet05_ALL	.838
201	ReAlnet06_ALL	.839
202	ReAlnet07_ALL	.839
203	ReAlnet09_ALL	.840
204	ReAlnet10_ALL	.839
205	ReAlnet08_ALL	.840
206	AlexNet_SIN	.839
207	ReAlnet04	.841
208	ReAlnet06	.840
209	ReAlnet07	.840
210	ReAlnet08	.840
211	ReAlnet09	.838
212	ReAlnet05	.839
213	ReAlnet01_cornet	.839
214	ReAlnet02_cornet	.839
215	ReAlnet03_cornet	.840
216	ReAlnet04_cornet	.841
217	ReAlnet01_ALL	.839
218	compact_resnet50_robust_V4	.839
219	compact_vgg19_IT	.838
220	ReAlnet05_cornet	.840
221	ReAlnet06_cornet	.839
222	compact_cornets_V4	.839
223	ReAlnet07_cornet	.840
224	ReAlnet08_cornet	.838
225	ReAlnet01	.840
226	ReAlnet09_cornet	.839
227	ReAlnet02	.840
228	ReAlnet03	.839
229	resnet50_pretrained_with_retinal_waves	.838
230	CLIP_resnet50_float32	.837
231	mobilenet_v2_1_4_224	.835
232	mobilenet_v2_1_0_160	.836
233	densenet-169-keras	.831
234	resnet50-SIN_IN_IN	.827
235	resnet50-vicreg	.824
236	BiT-M-R152x2	.825
237	AdvProp_efficientnet-b0	.825
238	mobilenet_v1_0.25_128	.821
239	resnet50-barlow	.820
240	cvt_cvt-13-224-in1k_4_LucyV4	.816
241	vit_tiny_r_s16_p8_384:augreg_in21k_ft_in1k	.814
242	efficientnet_b2_imagenet_full	.814
243	RN50	.813
244	vgg_19	.805
245	efficientnet-b7	.804
246	nasnet_large-tf	.804
247	BiT-M-R152x4	.802
248	mobilenet_v2_0_75_192	.800
249	BiT-S-R101x1	.800
250	mobilenet_v2_0.75_224-tf	.799
251	resnet50-VITO-8deg-cc	.799
252	AdvProp_efficientnet-b7	.800
253	AdvProp_efficientnet-b6	.796
254	mobilenet_v2_1.0_224-tf	.791
255	SWSL_resnext101_32x8d	.782
256	my-model	.782
257	mobilenet_v2_1_0_224	.773
258	resnet50_simclr	.774
259	BiT-M-R101x3	.773
260	resnet50	.767
261	effnetb1_272x240	.768
262	inception_v4-tf	.769
263	resnet50	.767
264	resnet-152_v1-tf	.763
265	SWSL_resnet50	.759
266	densenet-201	.761
267	vit_base_patch16_clip_224:openai_ft_in12k_in1k	.756
268	densenet-121	.754
269	inception_v3	.749
270	omnivore_swinS	.748
271	resnet50_random_linf8_perturb	.743
272	resnet152_imagenet_full	.740
273	convnext_small_imagenet_10_seed-0	.735
274	r3m_resnet50	.733
275	convnext_small_imagenet_full_seed-0	.732
276	v1-pyr-nodown	.731
277	resnet18_imagenet21kP	.728
278	convnext_large_imagenet_full_seed-0	.726
279	resnet50_random_l2_perturb	.721
280	pnasnet_large-tf	.722
281	mobilenet_v2_0.75_192-tf	.720
282	nasnet_mobile-tf	.720
283	konkle_alexnetgn_ipcl_ref01_primary_model	.720
284	mobilenet_v2_0_5_224	.718
285	alexnet_training_seed_05	.710
286	CLIP_ViT-B_32	.708
287	resnet_SIN_IN_FT_IN	.694
288	mobilenet_v2_0.5_224-tf	.694
289	nasnet_mobile	.694
290	efficientnet_b0	.691
291	deit_base_imagenet_full_seed-0	.692
292	deit_small_imagenet_full_seed-0	.688
293	inception_v3-tf	.688
294	BiT-S-R50x3	.687
295	yolos_tiny	.685
296	cvt_cvt-13-384-in22k_finetuned-in1k_4_LucyV4	.683
297	convnext_tiny_imagenet_full_seed-0	.679
298	efficientnet_b1_imagenet_full	.679
299	my-model	.672
300	vit_base_patch16_clip_224:openai_ft_in1k	.671
301	effnetb1_cutmix_augmix_sam_e1_5avg_424x377	.664
302	BiT-S-R152x4	.661
303	mobilenet_v2_1.4_224-tf	.660
304	mobilenet_v2_1.0_192-tf	.653
305	convnext_large:fb_in22k_ft_in1k	.647
306	densenet-201-keras	.643
307	densenet-121-keras	.641
308	convnext_xlarge:fb_in22k_ft_in1k	.640
309	mobilenet_v2_1-4_224_pytorch	.639
310	cvt_cvt-21-224-in1k_4_LucyV4	.638
311	resnet50_moco_v2	.637
312	mobilenet_v2_1.3_224-tf	.636
313	mobilenet_v2_0_5_192	.636
314	FrankRobWobv0	.623
315	mobilenet_v2_0.5_160	.623
316	resnet-101_v2-tf	.620
317	deit_small_imagenet_10_seed-0	.618
318	mobilenet_v2_1_0_128	.617
319	convnext_tiny_sup	.618
320	antialiased-rnext101_32x8d	.613
321	convnext_xxlarge:clip_laion2b_soup_ft_in1k	.608
322	vit_relpos_base_patch16_clsgap_224:sw_in1k	.605
323	convnext_tiny:in12k_ft_in1k	.603
324	efficientnet_b0_imagenet_full	.600
325	effnetv2m_custom384	.599
326	resnet-101_v1-tf	.584
327	mobilenet_v2_1_3_224	.585
328	mobilenet_v2_0_75_160	.583
329	deit_small_imagenet_100_seed-0	.580
330	resnet-50_v2-tf	.579
331	BiT-S-R101x3	.575
332	cvt_cvt-21-384-in1k_4_LucyV4	.575
333	cvt_cvt-13-384-in1k_4_LucyV4	.571
334	vit_huge_patch14_clip_224:laion2b_ft_in12k_in1k	.557
335	resnet-152_v2-tf	.557
336	AT_efficientnet-b2	.550
337	AdvProp_efficientnet-b2	.549
338	convnext_base_imagenet_full_seed-0	.543
339	deit_large_imagenet_full_seed-0	.543
340	inception_resnet_v2	.541
341	vit_huge_patch14_clip_336:laion2b_ft_in12k_in1k	.540
342	convnext_large_mlp:clip_laion2b_augreg_ft_in1k_384	.535
343	shufflenet_v2_x1_0	.534
344	cvt_cvt-w24-384-in22k_finetuned-in1k_4	.532
345	vit_large_patch14_clip_336:openai_ft_in12k_in1k	.527
346	ViT-B/32	.520
347	custom_model_cv_18_dagger_408	.513
348	mobilenet_v2_0.35_224	.498
349	vit_large_patch14_clip_336:laion2b_ft_in1k	.467
350	vit_large_patch14_clip_224:laion2b_ft_in1k	.465
351	omnivore_swinT	.465
352	cv_18_dagger_408_pretrained	.462
353	mobilenet_v2_0_75_224	.456
354	convnext_small_imagenet_100_seed-0	.457
355	resnet50_imagenet_1_seed-0	.443
356	vit_large_patch14_clip_224:laion2b_ft_in12k_in1k	.437
357	resnet-18-LC_untrained	.414
358	convnext_base:clip_laiona_augreg_ft_in1k_384	.413
359	vit_large_patch14_clip_224:openai_ft_in12k_in1k	.409
360	vit_large_patch14_clip_224:openai_ft_in1k	.404
361	swin_small_patch4_window7_224:ms_in22k_ft_in1k	.395
362	cvt_cvt-21-384-in22k_finetuned-in1k_4_LucyV4	.346
363	resnet50-meshes-lt-100-original-pretrained	.161
364	resnet50-meshes-lt-100-original-scratch	.063
365	mobilenet_v2_0.35_160
366	resnet18-supervised
367	fitvid_trained_on_physion
368	openclip
369	resnext101_32x32d_wsl
370	resnext101_32x16d_wsl
371	resnext101_32x48d_wsl
372	resnet50_ImageNet
373	regnet_y_400mf
374	tv_efficientnet-b1
375	alexnet_ks_torevert
376	yudixie_resnet50_imagenet1kpret_0_240312
377	resnet_152_v1
378	densenet_201_pytorch
379	pnasnet_large_pytorch
380	inception_v3_pytorch
381	inception_v4
382	nasnet_large
383	deit_small_imagenet_1_seed-0
384	pnasnet_large
385	vonegrcnn_62e_nobn
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

0.96.

Note that scores are relative to this ceiling.

Data: Marques2020_Schiller1976

Metric: sf_selective