Browse › Computer Vision › Image Classification › CIFAR-100

Image Classification archive 2025-07-28

CIFAR-100 Benchmark (Image Classification)

211 rows 188 with code listed 4 metrics Dataset page

Syntology Since the archive (Syntology): none placed; 48 newer papers judged to report on this board so far.

Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.

Source: Metamorphic Testing for Object Detection Systems

The archive carries no text for this table; the description above is the archive's text for the task Image Classification. archive 2025-07-28

Over time archive 2025-07-28

Direction inferred from the metric name, not from the archive: PARAMS (lower is better), Accuracy (higher is better), Top 1 Accuracy (higher is better). Not inferred (points only, no best-so-far line): Percentage correct. Points are placed at the row's paper date, not an evaluation date; 208 of 211 rows carry one.

The chart needs JavaScript; the table below carries every value.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

Paper Code Ran Syntology Report
1 EffNet-L2 (SAM) 96.08 ✓ Paper Code 2020 official (archive's flag): 7 ran · 15 ran (of which 6 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified report
2 Swin-L + ML-Decoder 95.1 ✓ Paper Code 2021 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified report
3 µ2Net (ViT-L/16) 94.95 ✓ Paper Code 2022 linked, not harvested report
4 ViT-B-16 (ImageNet-21K-P pretrain) 94.2 ✓ Paper Code 2021 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified report
5 CvT-W24 94.09 ✓ Paper Code 2021 official (archive's flag): 10 ran · 39 ran (of which 19 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified report
6 ViT-B/16 (PUGD) 93.95 ✓ Paper Code 2021 linked, not harvested report
7 Heinsen Routing + BEiT-large 16 224 93.8309.8M ✓ Paper Code 2022 linked, not harvested report
8 BiT-L (ResNet) 93.51 ✓ Paper Code 2019 community repositories only · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified report
9 VIT-L/16 (Spinal FC, Background) 93.31 – Paper Code 2023 linked, not harvested report
10 CaiT-M-36 U 224 93.1 ✓ Paper Code 2021 official: no sample here; runs from other or unrecorded repositories · 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified report
11 ViT-L (attn fine-tune) 93.0 ✓ Paper Code 2022 community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
12 TResNet-L-V2 92.6 ✓ Paper Code 2020 linked, not harvested report
13 EfficientNetV2-L 92.3 ✓ Paper Code 2021 official (archive's flag): 1 ran · 55 ran (of which 14 constructed an object rather than computing a result; 43 with no instrument failure: 11 honoured, 0 violated, 32 with no contract checked; 12 where Syntology's instrument failed) · 24 unverified report
14 EfficientNetV2-M 92.2 ✓ Paper Code 2021 official (archive's flag): 1 ran · 55 ran (of which 14 constructed an object rather than computing a result; 43 with no instrument failure: 11 honoured, 0 violated, 32 with no contract checked; 12 where Syntology's instrument failed) · 24 unverified report
15 BiT-M (ResNet) 92.17 ✓ Paper Code 2019 community repositories only · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified report
16 CeiT-S 91.8 ✓ Paper Code 2021 official (archive's flag): 5 ran · 9 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 9 samples that ran constructed an object rather than computing a result report
17 CeiT-S (384 finetune resolution) 91.8 ✓ Paper Code 2021 official (archive's flag): 5 ran · 9 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 9 samples that ran constructed an object rather than computing a result report
18 EfficientNet-B7 91.764M ✓ Paper Code 2019 official: no sample here; runs from other or unrecorded repositories · 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified report
19 EfficientNetV2-S 91.5 ✓ Paper Code 2021 official (archive's flag): 1 ran · 55 ran (of which 14 constructed an object rather than computing a result; 43 with no instrument failure: 11 honoured, 0 violated, 32 with no contract checked; 12 where Syntology's instrument failed) · 24 unverified report
20 GPIPE 91.3 ✓ Paper Code 2018 20 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified report
21 TNT-B 91.165.6M ✓ Paper Code 2021 official (archive's flag): 4 ran · 16 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 1 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified report
22 DeiT-B 90.886M ✓ Paper Code 2020 community repositories only · 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified report
23 GFNet-H-B 90.354M ✓ Paper Code 2021 official (archive's flag): 5 ran · 6 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified report
24 E2E-3M 90.27 ✓ Paper Code 2020 linked, not harvested report
25 Bamboo (ViT-B/16) 90.2 ✓ Paper Code 2022 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
26 PyramidNet-272 (ASAM) 89.90 – Paper Code 2021 linked, not harvested report
27 PyramidNet (SAM) 89.7 – Paper Code 2020 official (archive's flag): 7 ran · 15 ran (of which 6 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified report
28 DVT (T2T-ViT-24) 89.63 ✓ Paper Code 2021 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified report
29 ResMLP-24 89.5 ✓ Paper Code 2021 community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified report
30 PyramidNet-272, S=4 89.4632.8M ✓ Paper Code 2020 linked, not harvested report
31 CeiT-T 89.4 ✓ Paper Code 2021 official (archive's flag): 5 ran · 9 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 9 samples that ran constructed an object rather than computing a result report
32 PyramidNet+ShakeDrop 89.3 ✓ Paper Code 2018 community repositories only · 25 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 2 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 18 unverified report
33 ViT-B/16- SAM 89.1 ✓ Paper Code 2021 linked, not harvested report
34 ConvMLP-M 89.1 ✓ Paper Code 2021 official: harvested, nothing ran · 0 ran · 3 unverified report
35 ConvMLP-L 88.6 ✓ Paper Code 2021 official: harvested, nothing ran · 0 ran · 3 unverified report
36 ResNet-152x4-AGC (ImageNet-21K) 88.54 ✓ Paper Code 2021 linked, not harvested report
37 ColorNet 88.419.0M ✓ Paper Code 2019 linked, not harvested report
38 PyramidNet+ShakeDrop (Fast AA) 88.3 ✓ Paper Code 2019 official (archive's flag): 9 ran · 37 ran (of which 2 constructed an object rather than computing a result; 21 with no instrument failure: 2 honoured, 0 violated, 19 with no contract checked; 16 where Syntology's instrument failed) · 3 unverified report
39 NAT-M4 88.39.0M ✓ Paper Code 2020 official: harvested, nothing ran · 0 ran · 1 unverified report
40 CeiT-T (384 finetune resolution) 88 ✓ Paper Code 2021 official (archive's flag): 5 ran · 9 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 9 samples that ran constructed an object rather than computing a result report
41 NAT-M3 87.77.8M ✓ Paper Code 2020 official: harvested, nothing ran · 0 ran · 1 unverified report
42 ViT-S/16- SAM 87.6 ✓ Paper Code 2021 linked, not harvested report
43 NAT-M2 87.56.4M ✓ Paper Code 2020 official: harvested, nothing ran · 0 ran · 1 unverified report
44 Dynamics 1 87.48 ✓ Paper Code 2022 linked, not harvested report
45 DenseNet-BC-190, S=4 87.4426.3M ✓ Paper Code 2020 linked, not harvested report
46 ConvMLP-S 87.4 ✓ Paper Code 2021 official: harvested, nothing ran · 0 ran · 3 unverified report
47 ResMLP-12 87.0 ✓ Paper Code 2021 community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified report
48 WRN-40-10, S=4 86.90 ✓ Paper Code 2020 linked, not harvested report
49 ResNet50 (A1) 86.925M ✓ Paper Code 2021 official: harvested for another paper · 0 ran · 3 unverified report
50 WRN-28-10 * 3 86.81 ✓ Paper Code 2021 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified report
51 PyramidNet + AA (AMP) 86.64 ✓ Paper Code 2020 official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified report
52 PyramidNet-200 + Shakedrop + Cutmix + PS-KD 86.41 ✓ Paper Code 2020 official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified report
53 Mixer-B/16- SAM 86.4 ✓ Paper Code 2021 linked, not harvested report
54 ResCNet-50 86.31 – Paper Code 2024 linked, not harvested report
55 PyramidNet-200 + Shakedrop + Cutmix 86.19 ✓ Paper Code 2019 community repositories only · 17 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified report
56 MUXNet-m 86.12.1M ✓ Paper Code 2020 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified report
57 NAT-M1 86.03.8M ✓ Paper Code 2020 official: harvested, nothing ran · 0 ran · 1 unverified report
58 WRN-28-10 85.77 ✓ Paper Code 2021 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified report
59 WRN-28-10, S=4 85.74 ✓ Paper Code 2020 linked, not harvested report
60 WRN-28-8 (SAMix+DM) 85.59 – – – not matched report
61 WRN-28-8 +SAMix 85.50 ✓ Paper Code 2021 linked, not harvested report
62 ASANas 85.42 ✓ Paper Code 2019 linked, not harvested report
63 WRN-28-8 (AutoMix+DM) 85.38 – – – not matched report
64 SparseSwin 85.3517.58M ✓ Paper Code 2023 linked, not harvested report
65 WRN-28-8 (PuzzleMix+DM) 85.25 – – – not matched report
66 ResNet-50-SAM 85.2 ✓ Paper Code 2021 linked, not harvested report
67 WRN-28-8 +AutoMix 85.16 ✓ Paper Code 2021 community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified report
68 WaveMixLite-256/7 85.09 ✓ Paper Code 2022 linked, not harvested report
69 MANO-tiny 85.08 ✓ Paper Code 2025 linked, not harvested report
70 WRN 28-14 85.00 ✓ Paper Code 2020 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified report
71 R-Mix (WideResNet 28-10) 85 ✓ Paper Code 2022 linked, not harvested report
72 EEEA-Net-C (b=5)+ CO 84.98 ✓ Paper Code 2021 linked, not harvested report
73 RL-Mix (WideResNet 28-10) 84.9 ✓ Paper Code 2022 linked, not harvested report
74 Wide-ResNet-28-10 84.89 ✓ Paper Code 2022 official: harvested, nothing ran · 0 ran · 1 unverified report
75 SENet + ShakeEven + Cutout 84.59 ✓ Paper Code 2017 community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified report
76 ResNeXt-50(32x4d) + SAMix 84.42 ✓ Paper Code 2021 linked, not harvested report
77 WRN-28-10 with reSGHMC 84.38 ✓ Paper Code 2020 official (archive's flag): 1 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result report
78 PyramidNet-272 + SWA 84.16 ✓ Paper Code 2018 official (archive's flag): 2 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified report
79 WRN28-10 84.05 ✓ Paper Code 2020 official: harvested, nothing ran · 0 ran · 1 unverified report
80 HCGNet-A3 84.0411.4M ✓ Paper Code 2019 official (archive's flag): 3 ran · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified report
81 WideResNet 28-10 + CutMix (OneCycleLR scheduler) 83.97 ✓ Paper Code 2022 linked, not harvested report
82 DenseNet-BC-190 + FMix 83.95 ✓ Paper Code 2020 official (archive's flag): 5 ran · 8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified report
83 ORN 83.85 ✓ Paper Code 2017 linked, not harvested report
84 Grafit (ResNet-50) 83.7 ✓ Paper – 2020 no code linked report
85 ResNeXt-50(32x4d) + AutoMix 83.64 ✓ Paper Code 2021 community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified report
86 CCT-7/3x1+HTM+VTM 83.57 ✓ Paper Code 2022 official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result report
87 HCGNet-A2 83.463.1M ✓ Paper Code 2019 official (archive's flag): 3 ran · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified report
88 Res2NeXt-29 83.44 ✓ Paper Code 2019 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified report
89 DenseNet-BC-190 + Mixup 83.20 ✓ Paper Code 2017 community repositories only · 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified report
90 SSAL-DenseNet 190-40 83.2 ✓ Paper Code 2021 linked, not harvested report
91 EnAET 83.13 ✓ Paper Code 2019 linked, not harvested report
92 WRN 28-10 83.06 ✓ Paper Code 2020 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified report
93 R-Mix (ResNeXt 29-4-24) 83.02 ✓ Paper Code 2022 linked, not harvested report
94 Wide ResNet+Cutout+no BN scale/offset learning 82.95 ✓ Paper Code 2019 linked, not harvested report
95 WRN-16-8 with reSGHMC 82.95 ✓ Paper Code 2020 official (archive's flag): 1 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result report
96 DenseNet-BC 82.82 ✓ Paper Code 2016 community repositories only · 48 ran (of which 0 constructed an object rather than computing a result; 32 with no instrument failure: 2 honoured, 0 violated, 30 with no contract checked; 16 where Syntology's instrument failed) · 23 unverified report
97 ABNet-2G-R3-Combined 82.784 – Paper Code 2024 linked, not harvested report
98 CCT-7/3x1* 82.72 ✓ Paper Code 2021 community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified report
99 EXACT (WRN-28-10) 82.68 – Paper Code 2022 linked, not harvested report
100 SKNet-29 (ResNeXt-29, 16×32d) 82.67 ✓ Paper Code 2019 community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified report
101 DenseNet 82.62 ✓ Paper Code 2016 community repositories only · 48 ran (of which 0 constructed an object rather than computing a result; 32 with no instrument failure: 2 honoured, 0 violated, 30 with no contract checked; 16 where Syntology's instrument failed) · 23 unverified report
102 Shared WRN 82.57 ✓ Paper Code 2019 linked, not harvested report
103 Transformer local-attention (NesT-B) 82.56 ✓ Paper Code 2021 official (archive's flag): 9 ran · 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 3 honoured, 1 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified report
104 RL-Mix (ResNeXt 29-4-24) 82.43 ✓ Paper Code 2022 linked, not harvested report
105 Mixer-S/16- SAM 82.4 ✓ Paper Code 2021 linked, not harvested report
106 R-Mix (WideResNet 16-8) 82.32 ✓ Paper Code 2022 linked, not harvested report
107 ResNeXt 29-4-24 + CutMix (OneCycleLR scheduler) 82.3 ✓ Paper Code 2022 linked, not harvested report
108 WARN 82.18 ✓ Paper Code 2018 linked, not harvested report
109 RL-Mix (WideResNet 16-8) 82.16 ✓ Paper Code 2022 linked, not harvested report
110 WRN+SWA 82.15 ✓ Paper Code 2018 official (archive's flag): 2 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified report
111 Manifold Mixup 81.96 ✓ Paper Code 2018 official: no sample here; runs from other or unrecorded repositories · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified report
112 HCGNet-A1 81.871.1M ✓ Paper Code 2019 official (archive's flag): 3 ran · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified report
113 WideResNet 16-8 + CutMix (OneCycleLR scheduler) 81.79 ✓ Paper Code 2022 linked, not harvested report
114 Residual Gates + WRN 81.73 ✓ Paper – 2016 no code linked report
115 kNN-CLIP 81.7 ✓ Paper – 2022 no code linked report
116 AA-Wide-ResNet 81.6 ✓ Paper Code 2019 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified report
117 PDO-eConv (p8, 4.6M) 81.6 ✓ Paper Code 2020 official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
118 SEER (RegNet10B) 81.53 ✓ Paper Code 2022 linked, not harvested report
119 R-Mix (PreActResNet-18) 81.49 ✓ Paper Code 2022 linked, not harvested report
120 ResNet50 (FSGDM) 81.44 – Paper Code 2024 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result report
121 Wide-ResNet-40-2 81.19 ✓ Paper Code 2022 official: harvested, nothing ran · 0 ran · 1 unverified report
122 Wide ResNet 81.15 ✓ Paper Code 2016 official (archive's flag): 3 ran · 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified report
123 CoPaNet-R-164 81.10 ✓ Paper Code 2017 linked, not harvested report
124 ABNet-2G-R3 80.830 – Paper Code 2024 linked, not harvested report
125 RL-Mix (PreActResNet-18) 80.75 ✓ Paper Code 2022 linked, not harvested report
126 PreActResNet-18 + CutMix (OneCycleLR scheduler) 80.6 ✓ Paper Code 2022 linked, not harvested report
127 GAC-SNN 80.45 – Paper Code 2023 official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified report
128 ABNet-2G-R2 80.354 – Paper Code 2024 linked, not harvested report
129 SimpleNetv2 80.29 ✓ Paper Code 2018 linked, not harvested report
130 UPANets 80.29 ✓ Paper Code 2021 linked, not harvested report
131 PreActResNet-18 + SageMix 80.16 ✓ Paper Code 2022 official: harvested, nothing ran · 0 ran · 1 unverified report
132 ResNet56 with reSGHMC 80.14 ✓ Paper Code 2020 official (archive's flag): 1 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result report
133 PDO-eConv (p8, 2.62M) 79.99 ✓ Paper Code 2020 official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
134 VGG11B(3x) + LocalLearning 79.9 ✓ Paper Code 2019 linked, not harvested report
135 NNCLR 79 ✓ Paper Code 2021 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result report
136 ABNet-2G-R1 78.792 – Paper Code 2024 linked, not harvested report
137 PreActResNet18 (AMP) 78.49 ✓ Paper Code 2020 official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified report
138 SimpleNetv1 78.37 ✓ Paper Code 2016 community repositories only · 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified report
139 ViT (lightweight, MAE pre-trained) 78.273.64M – Paper – 2024 no code linked report
140 PDC 77.9 ✓ Paper Code 2021 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified report
141 MobileNetV3-large x1.0 (BSConv-U) 77.7 ✓ Paper Code 2020 linked, not harvested report
142 CCT-6/3x1 77.313.17M ✓ Paper Code 2021 community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified report
143 ResNet-1001 77.3 ✓ Paper Code 2016 community repositories only · 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified report
144 Evolution 77 ✓ Paper Code 2017 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
145 DIANet 76.98 ✓ Paper Code 2019 official (archive's flag): 5 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 15 unverified report
146 LP-BNN (ours) + cutout 76.85 ✓ Paper Code 2020 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified report
147 ResNet-18+MM+FRL 76.64 ✓ Paper – 2020 no code linked report
148 ResNet32 with reSGHMC 76.55 ✓ Paper Code 2020 official (archive's flag): 1 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result report
149 MomentumNet 76.38 ✓ Paper Code 2021 linked, not harvested report
150 SSCNN 75.7 ✓ Paper Code 2014 0 ran · 2 unverified report
151 Exponential Linear Units 75.7 ✓ Paper Code 2015 5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified report
152 ResNet-9 75.59 ✓ Paper Code 2022 linked, not harvested report
153 Stochastic Depth 75.42 ✓ Paper Code 2016 community repositories only · 8 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified report
154 ResNet v2-110 (Mish activation) 74.41 ✓ Paper Code 2019 official (archive's flag): 6 ran · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified report
155 Dspike (ResNet-18) 74.24 – Paper – 2021 no code linked report
156 ResNet20 with reSGHMC 74.14 ✓ Paper Code 2020 official (archive's flag): 1 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result report
157 MixMatch 74.1 ✓ Paper Code 2019 community repositories only · 47 ran (of which 8 constructed an object rather than computing a result; 27 with no instrument failure: 8 honoured, 0 violated, 19 with no contract checked; 20 where Syntology's instrument failed) · 16 unverified report
158 Beta-Rank 74.0174.01 – Paper Code 2023 linked, not harvested report
159 PreResNet-110 73.98 – Paper Code 2023 linked, not harvested report
160 ABNet-2G-R0 73.930 – Paper Code 2024 linked, not harvested report
161 Fractional MP 73.6 ✓ Paper Code 2014 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
162 ResNet+ELU 73.5 – Paper Code 2016 linked, not harvested report
163 PDO-eConv (p6m,0.37M) 73 ✓ Paper Code 2020 official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
164 SOPCNN 72.964,252,298 ✓ Paper Code 2020 linked, not harvested report
165 PDO-eConv (p6,0.36M) 72.87 ✓ Paper Code 2020 official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
166 Tuned CNN 72.6 ✓ Paper Code 2015 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
167 ResNet-110 (SAP) 72.537 – Paper – 2024 no code linked report
168 CMsC 72.4 ✓ Paper – 2015 no code linked report
169 Fitnet4-LSUV 72.3 ✓ Paper Code 2015 official: harvested, nothing ran · 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified report
170 GAN+ResNet 71.52 – Paper Code 2024 linked, not harvested report
171 kMobileNet V3 Large 16ch 71.360.52M ✓ Paper Code 2022 linked, not harvested report
172 BNM NiN 71.1 ✓ Paper Code 2015 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified report
173 OTTT 71.05 – Paper Code 2022 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified report
174 MIM 70.8 ✓ Paper – 2015 no code linked report
175 WaveMix-Lite-256/7 70.20 – Paper Code 2022 linked, not harvested report
176 IM-Loss (VGG-16) 70.18 – Paper – 2022 no code linked report
177 NiN+APL 69.2 ✓ Paper Code 2014 linked, not harvested report
178 SWWAE 69.1 ✓ Paper Code 2015 linked, not harvested report
179 NiN+Superclass+CDJ 69 ✓ Paper – 2017 no code linked report
180 Spectral Representations for Convolutional Neural Networks 68.4 – Paper – 2015 no code linked report
181 ReActNet-18 68.34 – Paper Code 2021 official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified report
182 VDN 67.8 – Paper Code 2015 linked, not harvested report
183 DCNN+GFE 67.7 – Paper – 2017 no code linked report
184 Tree+Max-Avg pooling 67.6 – Paper Code 2015 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
185 HD-CNN 67.4 – Paper Code 2014 linked, not harvested report
186 Universum Prescription 67.2 – Paper – 2015 no code linked report
187 ResNet50 Without Transfer Learning 67.060 – Paper Code 2020 linked, not harvested report
188 AlexNet (KP) 66.78 – Paper – 2021 no code linked report
189 ACN 66.3 – Paper Code 2014 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
190 DLME (ResNet-18, linear) 66.1 – Paper Code 2022 official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result report
191 ResNet-18 (modified) 66 – Paper Code 2022 linked, not harvested report
192 DSN 65.4 – Paper Code 2014 20 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified report
193 NiN 64.3 – Paper Code 2013 community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified report
194 Tree Priors 63.2 – Paper – 2013 no code linked report
195 DNN+Probabilistic Maxout 61.9 – Paper – 2013 no code linked report
196 Maxout Network (k=2) 61.43 – Paper Code 2013 0 ran · 3 unverified report
197 ResNet20+UnsharpMaskLayer 60.36 – Paper Code 2019 linked, not harvested report
198 Convolutional Linear Transformer for Vision (CLTV) 60.11 – Paper Code 2022 linked, not harvested report
199 FatNet of ResNet-18 60 – Paper Code 2022 linked, not harvested report
200 Optical Simulation of FatNet 60 – Paper Code 2022 linked, not harvested report
201 RReLU 59.8 – Paper Code 2015 linked, not harvested report
202 Stochastic Pooling 57.5 – Paper Code 2013 linked, not harvested report
203 Sign-symmetry 48.75 – Paper Code 2015 linked, not harvested report
204 AlexNet (DFA) 48.03 – Paper – 2021 no code linked report
205 CNN39 42.64 – Paper Code 2020 official (archive's flag): 7 ran · 15 ran (of which 6 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified report
206 CNN36 36.07 – Paper Code 2020 official (archive's flag): 7 ran · 15 ran (of which 6 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified report
207 CNN37 35.05 – Paper Code 2021 official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
208 AlexNet (FA) 19.49 – Paper – 2021 no code linked report
209 efficient adaptive ensembling 96.808 ✓ Paper – 2022 no code linked report
210 Label-Ranker 90.82% – Paper Code 2025 linked, not harvested report
211 DGMMC-S 91.2 – Paper Code 2024 linked, not harvested report

All 211 rows shown. 208 link to a paper page on this site; 155 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”: of the code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and U are unverified (harvested, no recorded run). Of the N, C constructed an object rather than computing a result (a part of N, never taken away from it), K ran with no instrument failure (honoured or violated the contract Syntology drafted, or ran with no contract checked) and I are failures of Syntology's instrument, not of the code (a wrong contract draft, or a contract check that could not run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 107 rows have a graph line, from 75 distinct papers. Rows whose paper has a sample that ran: 93 (79 with a run with no instrument failure, 14 where every run was a failure of Syntology's instrument). Papers: 67 with a sample that ran: 57 with a run with no instrument failure, 10 where every run was a failure of Syntology's instrument. Whose code ran. When the archive marks a repository official for the row's paper, the cell starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code): “official (archive's flag): N ran” counts the samples from it that ran, instrument failures included; “official: harvested, nothing ran”; when it has no sample for this paper and other samples ran, “community repositories only” if every one came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, and “official: no sample here; runs from other or unrecorded repositories” if any came from a repository named in the paper or found in its text by Syntology, or has no repository recorded; “official: harvested for another paper” (no sample from it is linked to this paper) or “official: not harvested”. No state is printed when the archive marks none official. The cell's tooltip names the repositories the samples that ran came from. Of the 107 rows with a graph line, 91 have an archive-official repository: on 53 a sample from it ran (40 with a run with no instrument failure), on 22 the samples that ran came from community repositories only, and on 3 from other or unrecorded repositories. The filters above hide rows and never renumber them; the first two count, by default, only a run with no instrument failure, and offer any run, instrument failures included. Counting each paper once, of 1,326 samples: 912 ran (of which 204 constructed an object rather than computing a result; 664 with no instrument failure: 70 honoured, 18 violated, 576 with no contract checked; 248 where Syntology's instrument failed) · 414 unverified. Separately, 408 of those 1,326 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. Per-sample status is on the paper page; each Ran cell links to that paper's sample list. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Since the archive Syntology

Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 104 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,494 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 48 proposed a result; of those 48, 48 gave no cell that passed the extractor's own checks, 0 were rejected by the independent check, 0 await a verdict and 0 were placed. Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.

Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)

Paper arXiv date Ran Syntology Outcome
Rethinking Pairwise Token Interaction in Spiking Transformers arXiv:2609.26297 22 Sep 2026 repository linked, no samples harvested refused by a rule: the table's column header does not name the leaderboard's metric
Sparse Competition during Training For the Emergence of Specialized Modules arXiv:2608.30978 31 Aug 2026 7 harvested: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified refused by a rule: the model gave no value to check against the cell
Fine-Tuning of Transformer models with Frames arXiv:2608.26430 26 Aug 2026 4 harvested: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models arXiv:2608.06901 7 Aug 2026 repository linked, no samples harvested refused by a rule: the table's column header does not name the leaderboard's metric
SpecDrop: Parameter-Free Category-Conditioned Routing for Modular Specialization arXiv:2608.04084 4 Aug 2026 2 harvested: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result refused by a rule: the number the model quoted is not the number printed in the cell it pointed at
Gecko: Fast Private Inference via Secure Public Encoder Offloading arXiv:2608.02378 3 Aug 2026 2 harvested: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified refused by a rule: the table's column header does not name the leaderboard's metric
BiKAN: Restoring Collapsed Basis of Binary Kolmogorov--Arnold Networks arXiv:2608.01490 2 Aug 2026 17 harvested: 13 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified refused by a rule: the model pointed at a header row
SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions arXiv:2607.18290 30 Jun 2026 6 harvested: 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 5 samples that ran constructed an object rather than computing a result refused by a rule: the number the model quoted is not the number printed in the cell it pointed at
Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator arXiv:2607.18101 20 Jul 2026 held, no recorded run refused by a rule: the table's column header does not name the leaderboard's metric
PsiLogic: Chaos-Aware Active Cancellation for Adam with a Fair Cross-Domain Benchmark arXiv:2607.16268 5 Jul 2026 14 harvested: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified refused by a rule: the model pointed at a header row
Reducing Per-Sample Interference in Stochastic Optimization arXiv:2607.16261 28 Jun 2026 4 harvested: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified refused by a rule: the table's column header does not name the leaderboard's metric
EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI arXiv:2607.06982 8 Jul 2026 held, no recorded run refused by a rule: the table's column header does not name the leaderboard's metric
Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective arXiv:2607.03784 4 Jul 2026 2 harvested: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Zeta: Dual Whitening for Matrix Optimization via Coordinate-Adaptive Preconditioning arXiv:2606.14187 12 Jun 2026 11 harvested: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Eigenvectors of Experts are Training-free Non-collapsing Routers arXiv:2605.30992 29 May 2026 11 harvested: 10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 1 unverified refused by a rule: the table's column header does not name the leaderboard's metric
SIKA-GP: Accelerating Gaussian Process Inference with Sparse Inducing Kernel... arXiv:2605.26509 26 May 2026 6 harvested: 5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified refused by a rule: the number the model quoted is not the number printed in the cell it pointed at
Quaternion Self-Attention with Shared Scores arXiv:2605.24920 24 May 2026 3 harvested: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified refused by a rule: the model pointed at a header row
Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language... arXiv:2605.22484 21 May 2026 1 harvested: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result refused by rules: the model pointed at a header row; the number the model quoted is not the number printed in the cell it pointed at
Not All Timesteps Matter Equally: Selective Alignment Knowledge Distillation for... arXiv:2605.14252 14 May 2026 20 harvested: 15 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 11 where Syntology's instrument failed) · 5 unverified refused by a rule: the table's column header does not name the leaderboard's metric
A Composite Activation Function for Learning Stable Binary Representations arXiv:2605.11558 12 May 2026 repository linked, no samples harvested refused by a rule: the row label the model quoted is not the row's label
BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models arXiv:2605.08110 27 Apr 2026 9 harvested: 7 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified refused by a rule: the table's column header does not name the leaderboard's metric
When Losses Align: Gradient-Based Composite Loss Weighting for Efficient Pretraining arXiv:2605.07756 8 May 2026 2 harvested: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified refused by a rule: the model gave no value to check against the cell
Improving Diversity in Black-box Few-shot Knowledge Distillation arXiv:2604.25795 28 Apr 2026 3 harvested: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Stylistic-STORM (ST-STORM) : Perceiving the Semantic Nature of Appearance arXiv:2604.16086 17 Apr 2026 13 harvested: 12 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Batch Loss Score for Dynamic Data Pruning arXiv:2604.04681 6 Apr 2026 held, no recorded run refused by a rule: the number the model quoted is not the number printed in the cell it pointed at
No Hard Negatives Required: Concept Centric Learning Leads to Compositionality without... arXiv:2603.25722 26 Mar 2026 repository linked, no samples harvested refused by a rule: the table's column header does not name the leaderboard's metric
SFedHIFI: Fire Rate-Based Heterogeneous Information Fusion for Spiking Federated Learning arXiv:2603.14956 16 Mar 2026 9 harvested: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified refused by a rule: the table's column header does not name the leaderboard's metric
HTMuon: Improving Muon via Heavy-Tailed Spectral Correction arXiv:2603.10067 10 Mar 2026 5 harvested: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Combining Adam and its Inverse Counterpart to Enhance Generalization of Deep Learning... arXiv:2603.07122 7 Mar 2026 repository linked, no samples harvested refused by a rule: the number the model quoted is not the number printed in the cell it pointed at
Margin and Consistency Supervision for Calibrated and Robust Vision Models arXiv:2603.05812 6 Mar 2026 repository linked, no samples harvested refused by a rule: the table's column header does not name the leaderboard's metric
On the Generalization Behavior of Deep Residual Networks From a Dynamical System Perspective arXiv:2602.20921 24 Feb 2026 repository linked, no samples harvested refused by rules: the row label the model quoted is not the row's label; the number the model quoted is not the number printed in the cell it pointed at
CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model... arXiv:2602.20419 23 Feb 2026 1 harvested: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result refused by a rule: the row label the model quoted is not the row's label
Hyperbolic Busemann Neural Networks arXiv:2602.18858 21 Feb 2026 7 harvested: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified refused by a rule: the table's column header does not name the leaderboard's metric
FedHENet: A Frugal Federated Learning Framework for Heterogeneous Environments arXiv:2602.13024 13 Feb 2026 4 harvested: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Collaborative Threshold Watermarking arXiv:2602.10765 11 Feb 2026 repository linked, no samples harvested refused by rules: the model pointed at a header row; the model gave no value to check against the cell
Vision Transformer Finetuning Benefits from Non-Smooth Components arXiv:2602.06883 6 Feb 2026 10 harvested: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified refused by a rule: the model gave no value to check against the cell
MultiModal Fine-tuning with Synthetic Captions arXiv:2601.21426 29 Jan 2026 15 harvested: 14 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 12 where Syntology's instrument failed) · 1 unverified refused by a rule: the number the model quoted is not the number printed in the cell it pointed at
HexFormer: Hyperbolic Vision Transformer with Exponential Map Aggregation arXiv:2601.19849 27 Jan 2026 4 harvested: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified refused by a rule: the number the model quoted is not the number printed in the cell it pointed at
CliffordNet: All You Need is Geometric Algebra arXiv:2601.06793 11 Jan 2026 6 harvested: 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 5 samples that ran constructed an object rather than computing a result refused by a rule: several configurations of the method, and no metric direction to pick one
DeepLeak: Privacy Enhancing Hardening of Model Explanations Against Membership Leakage arXiv:2601.03429 6 Jan 2026 13 harvested: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Normalized Conditional Mutual Information Surrogate Loss for Deep Neural Classifiers arXiv:2601.02543 5 Jan 2026 2 harvested: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Simplex Deep Linear Discriminant Analysis arXiv:2601.01679 4 Jan 2026 1 harvested: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result refused by a rule: the model pointed at a header row
Hilbert-Guided Sparse Local Attention arXiv:2511.05832 8 Nov 2025 10 harvested: 8 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified refused by a rule: the table's column header does not name the leaderboard's metric
VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set arXiv:2510.21323 24 Oct 2025 1 harvested: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified refused by a rule: the row is an ablation variant, not the method itself
QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks arXiv:2510.03276 28 Sep 2025 9 harvested: 5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified refused by a rule: the table's column header does not name the leaderboard's metric
StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold arXiv:2510.01938 2 Oct 2025 held, no recorded run refused by a rule: the table's column header does not name the leaderboard's metric
CIARD: Cyclic Iterative Adversarial Robustness Distillation arXiv:2509.12633 16 Sep 2025 1 harvested: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified refused by a rule: the table's column header does not name the leaderboard's metric
SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation arXiv:2509.03897 4 Sep 2025 4 harvested: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified refused by a rule: the table's column header does not name the leaderboard's metric

Syntology 48 newer papers judged to report on this board: the papers counted above as having proposed a result (0 placed); every one is listed here and in the JSON twin. The order is the arXiv identifier's, newest first, not a rank. The judgement is the model's, read from the paper's own tables; the outcome is what Syntology's checks did with it, and no value from a paper that was not placed is printed. “refused by a rule” names the extractor's rule; “no cell passed the extractor's checks” means the extractor's record holds no cell for this board, passed or refused. The 48 counted above as giving no cell that passed the extractor's own checks are the 48 marked “refused by a rule”. Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections