Browse › Computer Vision › Image Classification › CIFAR-10
Image Classification archive 2025-07-28
CIFAR-10 Benchmark (Image Classification)
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.
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
The chart needs JavaScript; the table below carries every value.
Direction inferred from the metric name, not from the archive: Top-1 Accuracy (higher is better), Accuracy (higher is better), Top 1 Accuracy (higher is better), F1 (higher is better), Cross Entropy Loss (lower is better). Not inferred (points only, no best-so-far line): Percentage correct, Parameters. Points are placed at the row's paper date; 263 of 265 rows carry one.
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 | ViT-H/14 | 99.5 | ✓ | Paper | Code | 2020 | 281 of 419 ran · 138 unverified | report | ||||||
| 2 | DINOv2 (ViT-g/14, frozen model, linear eval) | 99.5 | ✓ | Paper | Code | 2023 | 21 of 46 ran · 25 unverified | report | ||||||
| 3 | µ2Net (ViT-L/16) | 99.49 | ✓ | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 4 | ViT-L/16 | 99.42 | ✓ | Paper | Code | 2020 | 281 of 419 ran · 138 unverified | report | ||||||
| 5 | CaiT-M-36 U 224 | 99.4 | ✓ | Paper | Code | 2021 | 5 of 11 ran · 6 unverified | report | ||||||
| 6 | CvT-W24 | 99.39 | ✓ | Paper | Code | 2021 | 29 of 47 ran · 18 unverified | report | ||||||
| 7 | BiT-L (ResNet) | 99.37 | ✓ | Paper | Code | 2019 | 3 of 10 ran · 7 unverified | report | ||||||
| 8 | RDNet-L (224 res, IN-1K pretrained) | 99.31 | ✓ | Paper | Code | 2024 | 3 of 3 ran · 0 unverified | report | ||||||
| 9 | RDNet-B (224 res, IN-1K pretrained) | 99.31 | ✓ | Paper | Code | 2024 | 3 of 3 ran · 0 unverified | report | ||||||
| 10 | ViT-B (attn fine-tune) | 99.3 | ✓ | Paper | Code | 2022 | 1 of 1 ran · 0 unverified | report | ||||||
| 11 | Heinsen Routing + BEiT-large 16 224 | 99.2 | ✓ | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 12 | ViT-B/16 (PUGD) | 99.13 | ✓ | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 13 | Astroformer | 99.12 | 99.12 | ✓ | Paper | Code | 2023 | 1 of 1 ran · 0 unverified | report | |||||
| 14 | DeiT-B | 99.1 | ✓ | Paper | Code | 2020 | 12 of 19 ran · 7 unverified | report | ||||||
| 15 | TNT-B | 99.1 | ✓ | Paper | Code | 2021 | 16 of 24 ran · 8 unverified | report | ||||||
| 16 | CeiT-S (384 finetune resolution) | 99.1 | ✓ | Paper | Code | 2021 | 9 of 11 ran · 2 unverified | report | ||||||
| 17 | EfficientNetV2-L | 99.1 | ✓ | Paper | Code | 2021 | 41 of 79 ran · 38 unverified | report | ||||||
| 18 | AutoFormer-S | 384 | 99.1 | ✓ | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 19 | VIT-L/16 (Spinal FC, Background) | 99.05 | – | Paper | Code | 2023 | linked, not harvested | report | ||||||
| 20 | LaNet | 99.03 | – | Paper | Code | 2019 | linked, not harvested | report | ||||||
| 21 | GPIPE + transfer learning | 99 | ✓ | Paper | Code | 2018 | 1 of 25 ran · 24 unverified | report | ||||||
| 22 | TResNet-XL | 99 | – | Paper | Code | 2020 | linked, not harvested | report | ||||||
| 23 | CeiT-S | 99 | – | Paper | Code | 2021 | 9 of 11 ran · 2 unverified | report | ||||||
| 24 | EfficientNetV2-M | 99.0 | – | Paper | Code | 2021 | 41 of 79 ran · 38 unverified | report | ||||||
| 25 | GFNet-H-B | 99.0 | ✓ | Paper | Code | 2021 | 6 of 10 ran · 4 unverified | report | ||||||
| 26 | BiT-M (ResNet) | 98.91 | – | Paper | Code | 2019 | 3 of 10 ran · 7 unverified | report | ||||||
| 27 | EfficientNet-B7 | 98.9 | – | Paper | Code | 2019 | 171 of 302 ran · 131 unverified | report | ||||||
| 28 | RDNet-T (224 res, IN-1K pretrained) | 98.88 | – | Paper | Code | 2024 | 3 of 3 ran · 0 unverified | report | ||||||
| 29 | ASF-former-B | 98.8% | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 30 | PyramidNet-272, S=4 | 98.71 | – | Paper | Code | 2020 | linked, not harvested | report | ||||||
| 31 | EfficientNetV2-S | 98.7 | – | Paper | Code | 2021 | 41 of 79 ran · 38 unverified | report | ||||||
| 32 | ASF-former-S | 98.7 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 33 | PyramidNet-272 (ASAM) | 98.68 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 34 | PyramidNet + ShakeDrop + Fast AA + FMix | 98.64 | – | Paper | Code | 2020 | 8 of 8 ran · 0 unverified | report | ||||||
| 35 | ViT-B/16- SAM | 98.6 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 36 | ConvMLP-M | 98.6 | ✓ | Paper | Code | 2021 | 0 of 3 ran · 3 unverified | report | ||||||
| 37 | ConvMLP-L | 98.6 | ✓ | Paper | Code | 2021 | 0 of 3 ran · 3 unverified | report | ||||||
| 38 | DVT (T2T-ViT-24) | 98.53 | – | Paper | Code | 2021 | 2 of 3 ran · 1 unverified | report | ||||||
| 39 | E2E-3M | 98.52 | – | Paper | Code | 2020 | linked, not harvested | report | ||||||
| 40 | CeiT-T | 98.5 | – | Paper | Code | 2021 | 9 of 11 ran · 2 unverified | report | ||||||
| 41 | NAT-M4 | 98.4 | 98.4 | 6.9M | ✓ | Paper | Code | 2020 | 0 of 1 ran · 1 unverified | report | ||||
| 42 | WRN-40-10, S=4 | 98.38 | – | Paper | Code | 2020 | linked, not harvested | report | ||||||
| 43 | WRN-28-10, S=4 | 98.32 | – | Paper | Code | 2020 | linked, not harvested | report | ||||||
| 44 | Shake-Shake 26 2x96d, S=4 | 98.31 | – | Paper | Code | 2020 | linked, not harvested | report | ||||||
| 45 | Dynamics 2 | 98.31 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 46 | PyramidNet+ShakeDrop (Fast AA) | 98.3 | – | Paper | Code | 2019 | 22 of 40 ran · 18 unverified | report | ||||||
| 47 | ResNet50 (A1) | 98.3 | – | Paper | Code | 2021 | 0 of 3 ran · 3 unverified | report | ||||||
| 48 | NoisyDARTS-A-t | 98.28 | – | Paper | Code | 2020 | linked, not harvested | report | ||||||
| 49 | NAT-M3 | 98.2 | 98.2 | 6.2M | ✓ | Paper | Code | 2020 | 0 of 1 ran · 1 unverified | report | ||||
| 50 | LeViT-192 | 98.2 | – | Paper | Code | 2021 | 23 of 30 ran · 7 unverified | report | ||||||
| 51 | ResNet-152-SAM | 98.2 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 52 | ViT-S/16- SAM | 98.2 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 53 | Bamboo (ViT-B/16) | 98.2 | – | Paper | Code | 2022 | 3 of 3 ran · 0 unverified | report | ||||||
| 54 | DE ELBo (ViT-B/16) | 98.2 | – | Paper | Code | 2025 | linked, not harvested | report | ||||||
| 55 | LeViT-256 | 98.1 | ✓ | Paper | Code | 2021 | 23 of 30 ran · 7 unverified | report | ||||||
| 56 | PyramidNet + AA (AMP) | 98.02 | – | Paper | Code | 2020 | 0 of 12 ran · 12 unverified | report | ||||||
| 57 | EnAET | 98.01 | – | Paper | Code | 2019 | linked, not harvested | report | ||||||
| 58 | MUXNet-m | 98.0 | 98.0 | – | Paper | Code | 2020 | 3 of 5 ran · 2 unverified | report | |||||
| 59 | LeViT-384 | 98 | – | Paper | Code | 2021 | 23 of 30 ran · 7 unverified | report | ||||||
| 60 | CCT-7/3x1* | 98 | – | Paper | Code | 2021 | 3 of 6 ran · 3 unverified | report | ||||||
| 61 | ConvMLP-S | 98 | ✓ | Paper | Code | 2021 | 0 of 3 ran · 3 unverified | report | ||||||
| 62 | Proxyless-G + c/o | 97.92 | – | Paper | Code | 2018 | 5 of 27 ran · 22 unverified | report | ||||||
| 63 | NAT-M2 | 97.9 | 97.9 | 4.6M | ✓ | Paper | Code | 2020 | 0 of 1 ran · 1 unverified | report | ||||
| 64 | WRN-28-10+AutoDropout+RandAugment | 97.9 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 65 | SENet + ShakeShake + Cutout | 97.88 | – | Paper | Code | 2017 | 2 of 9 ran · 7 unverified | report | ||||||
| 66 | HCGNet-A3 | 97.86 | – | Paper | Code | 2019 | 4 of 5 ran · 1 unverified | report | ||||||
| 67 | Wide-ResNet-28-10 | 97.85 | – | Paper | Code | 2022 | 0 of 1 ran · 1 unverified | report | ||||||
| 68 | ResNeXt-50 (AutoMix) | 97.84 | – | Paper | Code | 2021 | 4 of 6 ran · 2 unverified | report | ||||||
| 69 | ResNet-152x4-AGC (ImageNet-21K) | 97.82 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 70 | Mixer-B/16- SAM | 97.8 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 71 | CCT-7/3x1+VTM | 97.78 | – | Paper | Code | 2022 | 1 of 1 ran · 0 unverified | report | ||||||
| 72 | WRN-28-10 | 97.73 | – | Paper | Code | 2021 | 1 of 1 ran · 0 unverified | report | ||||||
| 73 | HCGNet-A2 | 97.71 | – | Paper | Code | 2019 | 4 of 5 ran · 1 unverified | report | ||||||
| 74 | WRN + fixup init + mixup + cutout | 97.7 | – | Paper | Code | 2019 | 2 of 4 ran · 2 unverified | report | ||||||
| 75 | NoisyDARTS-a | 97.61 | – | Paper | Code | 2020 | linked, not harvested | report | ||||||
| 76 | TransBoost-ResNet50 | 97.61 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 77 | LeViT-128 | 97.6 | – | Paper | Code | 2021 | 23 of 30 ran · 7 unverified | report | ||||||
| 78 | DenseNet-BC-190 + batchboost | 97.54 | – | Paper | Code | 2020 | linked, not harvested | report | ||||||
| 79 | LeViT-128S | 97.5 | ✓ | Paper | Code | 2021 | 23 of 30 ran · 7 unverified | report | ||||||
| 80 | Shared WRN | 97.47 | – | Paper | Code | 2019 | linked, not harvested | report | ||||||
| 81 | Manifold Mixup WRN 28-10 | 97.45 | – | Paper | Code | 2018 | 2 of 11 ran · 9 unverified | report | ||||||
| 82 | WRN 28-14 | 97.45 | – | Paper | Code | 2020 | 1 of 3 ran · 2 unverified | report | ||||||
| 83 | SparseSwin | 97.43 | – | Paper | Code | 2023 | linked, not harvested | report | ||||||
| 84 | WRN-28-10 with reSGHMC | 97.42 | – | Paper | Code | 2020 | 2 of 2 ran · 0 unverified | report | ||||||
| 85 | NAT-M1 | 97.4 | 97.4 | 4.3M | ✓ | Paper | Code | 2020 | 0 of 1 ran · 1 unverified | report | ||||
| 86 | ResNet-50-SAM | 97.4 | ✓ | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 87 | DenseNet-BC-190 + Mixup | 97.3 | ✓ | Paper | Code | 2017 | 30 of 47 ran · 17 unverified | report | ||||||
| 88 | kNN-CLIP | 97.3 | ✓ | Paper | – | 2022 | no code linked | report | ||||||
| 89 | WaveMixLite-144/7 | 97.29 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 90 | Transformer local-attention (NesT-B) | 97.2 | – | Paper | Code | 2021 | 7 of 26 ran · 19 unverified | report | ||||||
| 91 | ShakeShake-2x64d + SWA | 97.12 | – | Paper | Code | 2018 | 5 of 9 ran · 4 unverified | report | ||||||
| 92 | PyramidNet-200 + CutMix | 97.12 | – | Paper | Code | 2019 | 17 of 24 ran · 7 unverified | report | ||||||
| 93 | Wide-ResNet-40-2 | 97.05 | – | Paper | Code | 2022 | 0 of 1 ran · 1 unverified | report | ||||||
| 94 | ORN | 97.02 | – | Paper | Code | 2017 | linked, not harvested | report | ||||||
| 95 | WRN-16-8 with reSGHMC | 96.87 | – | Paper | Code | 2020 | 2 of 2 ran · 0 unverified | report | ||||||
| 96 | ResNet_XnIDR | 96.87 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 97 | HCGNet-A1 | 96.85 | – | Paper | Code | 2019 | 4 of 5 ran · 1 unverified | report | ||||||
| 98 | WRN 28-10 | 96.81 | – | Paper | Code | 2020 | 1 of 3 ran · 2 unverified | report | ||||||
| 99 | AutoDropout | 96.8 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 100 | WRN-28-10 + SWA | 96.79 | – | Paper | Code | 2018 | 5 of 9 ran · 4 unverified | report | ||||||
| 101 | ConvMixer-256/16 | 96.74 | – | Paper | Code | 2022 | 8 of 8 ran · 0 unverified | report | ||||||
| 102 | EXACT (WRN-28-10) | 96.73 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 103 | Wide ResNet+cutout | 96.71 | – | Paper | Code | 2019 | linked, not harvested | report | ||||||
| 104 | Deep pyramidal residual network | 96.69 | – | Paper | Code | 2016 | 1 of 1 ran · 0 unverified | report | ||||||
| 105 | CoPaNet-R-164 | 96.62 | – | Paper | Code | 2017 | linked, not harvested | report | ||||||
| 106 | DenseNet (DenseNet-BC-190) | 96.54 | – | Paper | Code | 2016 | 18 of 71 ran · 53 unverified | report | ||||||
| 107 | SKNet-29 (ResNeXt-29, 16×32d) | 96.53 | – | Paper | Code | 2019 | 3 of 3 ran · 0 unverified | report | ||||||
| 108 | Fractional MP | 96.5 | – | Paper | Code | 2014 | 0 of 3 ran · 3 unverified | report | ||||||
| 109 | PDO-eConv (p8, 4.6M) | 96.5 | – | Paper | Code | 2020 | 0 of 7 ran · 7 unverified | report | ||||||
| 110 | UPANets | 96.47 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 111 | GAC-SNN | 96.46 | – | Paper | Code | 2023 | 7 of 12 ran · 5 unverified | report | ||||||
| 112 | ViT (lightweight, MAE pretrained) | 96.41 | – | Paper | – | 2024 | no code linked | report | ||||||
| 113 | NAS-RL | 96.4 | – | Paper | Code | 2016 | 5 of 5 ran · 0 unverified | report | ||||||
| 114 | VGG11B(2x) + LocalLearning + CO | 96.4 | – | Paper | Code | 2019 | linked, not harvested | report | ||||||
| 115 | ABNet-2G-R3-Combined | 96.378 | – | Paper | Code | 2024 | linked, not harvested | report | ||||||
| 116 | Residual Gates + WRN | 96.35 | – | Paper | – | 2016 | no code linked | report | ||||||
| 117 | PDO-eConv (p8, 2.62M) | 96.32 | – | Paper | Code | 2020 | 0 of 7 ran · 7 unverified | report | ||||||
| 118 | SimpleNetv2 | 96.29 | – | Paper | Code | 2018 | linked, not harvested | report | ||||||
| 119 | ResNet56 with reSGHMC | 96.12 | – | Paper | Code | 2020 | 2 of 2 ran · 0 unverified | report | ||||||
| 120 | Mixer-S/16- SAM | 96.1 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 121 | ABNet-2G-R3 | 96.088 | – | Paper | Code | 2024 | linked, not harvested | report | ||||||
| 122 | PreActResNet18 (AMP) | 96.03 | – | Paper | Code | 2020 | 0 of 12 ran · 12 unverified | report | ||||||
| 123 | ConvMixer-256/8 | 96.03 | – | Paper | Code | 2022 | 8 of 8 ran · 0 unverified | report | ||||||
| 124 | Local Mixup Resnet18 | 95.97 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 125 | ABNet-2G-R2 | 95.900 | – | Paper | Code | 2024 | linked, not harvested | report | ||||||
| 126 | ResNet-50x1-ACG (ImageNet-21K) | 95.78 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 127 | ResNet18 (FSGDM) | 95.66 | – | Paper | Code | 2024 | 1 of 2 ran · 1 unverified | report | ||||||
| 128 | ACN | 95.6 | – | Paper | Code | 2014 | 0 of 6 ran · 6 unverified | report | ||||||
| 129 | Evolution ensemble | 95.6 | – | Paper | Code | 2017 | 1 of 1 ran · 0 unverified | report | ||||||
| 130 | ResNet-18 | 95.55 | – | Paper | Code | 2022 | 0 of 10 ran · 10 unverified | report | ||||||
| 131 | ABNet-2G-R1 | 95.536 | – | Paper | Code | 2024 | linked, not harvested | report | ||||||
| 132 | SimpleNetv1 | 95.51 | – | Paper | Code | 2016 | 3 of 11 ran · 8 unverified | report | ||||||
| 133 | Mobile Net_Sam | 95.50 | – | Paper | Code | 2018 | 85 of 111 ran · 26 unverified | report | ||||||
| 134 | IM-Loss (ResNet-19) | 95.49 | – | Paper | – | 2022 | no code linked | report | ||||||
| 135 | ResNet-1001 | 95.4 | – | Paper | Code | 2016 | 3 of 25 ran · 22 unverified | report | ||||||
| 136 | ResNet32 with reSGHMC | 95.35 | – | Paper | Code | 2020 | 2 of 2 ran · 0 unverified | report | ||||||
| 137 | ResNet-18+MM+FRL | 95.33 | – | Paper | – | 2020 | no code linked | report | ||||||
| 138 | PSN (Modified PLIF Net) | 95.32 | – | – | – | not matched | report | |||||||
| 139 | CCT-6/3x1 | 95.29 | – | Paper | Code | 2021 | 3 of 6 ran · 3 unverified | report | ||||||
| 140 | MomentumNet | 95.18 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 141 | Context-Aware Pipeline | 95.16 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 142 | SRM-ResNet-56 | 95.05 | 95.05 | – | Paper | Code | 2019 | 3 of 3 ran · 0 unverified | report | |||||
| 143 | MixMatch | 95.05 | – | Paper | Code | 2019 | 39 of 63 ran · 24 unverified | report | ||||||
| 144 | WRN-22-8 (Sparse Momentum) | 95.04 | – | Paper | Code | 2019 | 0 of 1 ran · 1 unverified | report | ||||||
| 145 | LP-BNN (ours) + cutout | 95.02 | – | Paper | Code | 2020 | 1 of 3 ran · 2 unverified | report | ||||||
| 146 | kEffNet-B0 V2 32ch + H Flip | 94.95 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 147 | Prodpoly | 94.9 | – | Paper | Code | 2020 | linked, not harvested | report | ||||||
| 148 | ResNet-9 | 94.79 | ✓ | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 149 | Stochastic Depth | 94.77 | ✓ | Paper | Code | 2016 | 8 of 9 ran · 1 unverified | report | ||||||
| 150 | VGG-19 with GradInit | 94.71 | – | Paper | Code | 2021 | 7 of 13 ran · 6 unverified | report | ||||||
| 151 | ResNet20 with reSGHMC | 94.62 | – | Paper | Code | 2020 | 2 of 2 ran · 0 unverified | report | ||||||
| 152 | PDO-eConv (p6m,0.37M) | 94.62 | – | Paper | Code | 2020 | 0 of 7 ran · 7 unverified | report | ||||||
| 153 | Evolution | 94.6 | – | Paper | Code | 2017 | 1 of 1 ran · 0 unverified | report | ||||||
| 154 | RL+NT | 94.6 | – | Paper | Code | 2017 | linked, not harvested | report | ||||||
| 155 | Convolutional Performer for Vision (CPV) | 94.46 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 156 | PreResNet-110 | 94.4367 | – | Paper | Code | 2023 | linked, not harvested | report | ||||||
| 157 | ResNet+ELU | 94.4 | – | Paper | Code | 2016 | linked, not harvested | report | ||||||
| 158 | Deep Complex | 94.4 | – | Paper | Code | 2017 | 3 of 6 ran · 3 unverified | report | ||||||
| 159 | PDO-eConv (p6,0.36M) | 94.35 | – | Paper | Code | 2020 | 0 of 7 ran · 7 unverified | report | ||||||
| 160 | Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods | 94.29 | – | Paper | Code | 2020 | linked, not harvested | report | ||||||
| 161 | Fitnet4-LSUV | 94.2 | – | Paper | Code | 2015 | 0 of 19 ran · 19 unverified | report | ||||||
| 162 | R-ExplaiNet-26 | 94.15 | 0.89 M | – | Paper | Code | 2024 | linked, not harvested | report | |||||
| 163 | ABNet-2G-R0 | 94.118 | – | Paper | Code | 2024 | linked, not harvested | report | ||||||
| 164 | ResNet 9 + Mish | 94.05 | – | Paper | Code | 2019 | 3 of 12 ran · 9 unverified | report | ||||||
| 165 | Tree+Max-Avg pooling | 94.0 | – | Paper | Code | 2015 | 1 of 12 ran · 11 unverified | report | ||||||
| 166 | Beta-Rank | 93.97 | – | Paper | Code | 2023 | linked, not harvested | report | ||||||
| 167 | ResNet-110 (SAP) | 93.861 | – | Paper | – | 2024 | no code linked | report | ||||||
| 168 | SA quadratic embedding | 93.8 | – | Paper | Code | 2019 | 4 of 16 ran · 12 unverified | report | ||||||
| 169 | kEffNet-B0 32ch | 93.75 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 170 | OTTT | 93.73 | – | Paper | Code | 2022 | 3 of 3 ran · 0 unverified | report | ||||||
| 171 | SSCNN | 93.7 | – | Paper | Code | 2014 | 0 of 2 ran · 2 unverified | report | ||||||
| 172 | NNCLR | 93.7 | – | Paper | Code | 2021 | 4 of 5 ran · 1 unverified | report | ||||||
| 173 | Tuned CNN | 93.6 | – | Paper | Code | 2015 | 1 of 1 ran · 0 unverified | report | ||||||
| 174 | Exponential Linear Units | 93.5 | – | Paper | Code | 2015 | 3 of 7 ran · 4 unverified | report | ||||||
| 175 | BNM NiN | 93.3 | – | Paper | Code | 2015 | 3 of 3 ran · 0 unverified | report | ||||||
| 176 | Universum Prescription | 93.3 | – | Paper | – | 2015 | no code linked | report | ||||||
| 177 | CMsC | 93.1 | – | Paper | – | 2015 | no code linked | report | ||||||
| 178 | DGPPF-ResNet18 | 92.90 | – | Paper | Code | 2024 | linked, not harvested | report | ||||||
| 179 | kMobileNet V3 Large 16ch | 92.74 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 180 | NiN+APL | 92.5 | – | Paper | Code | 2014 | linked, not harvested | report | ||||||
| 181 | VDN | 92.4 | – | Paper | Code | 2015 | linked, not harvested | report | ||||||
| 182 | ResNet | 92.3 | – | Paper | Code | 2021 | 0 of 9 ran · 9 unverified | report | ||||||
| 183 | SWWAE | 92.2 | – | Paper | Code | 2015 | linked, not harvested | report | ||||||
| 184 | FlexTCN-7 | 92.2 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 185 | ReActNet-18 | 92.08 | – | Paper | Code | 2021 | 4 of 11 ran · 7 unverified | report | ||||||
| 186 | ResNet v2-20 (Mish activation) | 92.02 | – | Paper | Code | 2019 | 3 of 12 ran · 9 unverified | report | ||||||
| 187 | Context-Aware DNN tree | 92.01 | – | Paper | – | 2020 | no code linked | report | ||||||
| 188 | DSN | 91.8 | – | Paper | Code | 2014 | 0 of 21 ran · 21 unverified | report | ||||||
| 189 | BinaryConnect | 91.7 | – | Paper | Code | 2015 | 3 of 3 ran · 0 unverified | report | ||||||
| 190 | CLS-GAN | 91.7 | – | Paper | Code | 2017 | linked, not harvested | report | ||||||
| 191 | MIM | 91.5 | – | Paper | – | 2015 | no code linked | report | ||||||
| 192 | Spectral Representations for Convolutional Neural Networks | 91.4 | – | Paper | – | 2015 | no code linked | report | ||||||
| 193 | DLME (ResNet-18, linear) | 91.3 | – | Paper | Code | 2022 | 1 of 1 ran · 0 unverified | report | ||||||
| 194 | RMDL (30 RDLs) | 91.21 | – | Paper | Code | 2018 | linked, not harvested | report | ||||||
| 195 | Network in Network | 91.2 | – | Paper | Code | 2013 | 1 of 7 ran · 6 unverified | report | ||||||
| 196 | ResNet-26 (Trainable Activations) | 91.1 | – | Paper | Code | 2023 | linked, not harvested | report | ||||||
| 197 | ResNet-32 (Trainable Activations) | 90.9 | – | Paper | Code | 2023 | linked, not harvested | report | ||||||
| 198 | kDenseNet-BC L100 12ch | 90.83 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 199 | Deep Networks with Internal Selective Attention through Feedback Connections | 90.8 | – | Paper | – | 2014 | no code linked | report | ||||||
| 200 | Maxout Network (k=2) | 90.65 | – | Paper | Code | 2013 | 0 of 3 ran · 3 unverified | report | ||||||
| 201 | ResNet-18 | 90.65 | ✓ | Paper | – | 2019 | no code linked | report | ||||||
| 202 | DNN+Probabilistic Maxout | 90.6 | ✓ | Paper | – | 2013 | no code linked | report | ||||||
| 203 | GP EI | 90.5 | – | Paper | Code | 2012 | linked, not harvested | report | ||||||
| 204 | ResNet-44 (Trainable Activations) | 90.5 | – | Paper | Code | 2023 | linked, not harvested | report | ||||||
| 205 | ResNet-20 (Trainable Activations) | 90.4 | – | Paper | Code | 2023 | linked, not harvested | report | ||||||
| 206 | SEER (RegNet10B) | 90 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 207 | kMobileNet 16ch | 89.81 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 208 | APAC | 89.7 | – | Paper | – | 2015 | no code linked | report | ||||||
| 209 | ensemble of 7 models | 89.4 | – | Paper | Code | 2017 | 18 of 118 ran · 100 unverified | report | ||||||
| 210 | DCNN+GFE | 89.1 | – | Paper | – | 2017 | no code linked | report | ||||||
| 211 | DCNN | 89 | – | Paper | Code | 2012 | linked, not harvested | report | ||||||
| 212 | ResNet-14 (Trainable Activations) | 89.0 | – | Paper | Code | 2023 | linked, not harvested | report | ||||||
| 213 | MCDNN | 88.8 | – | Paper | Code | 2012 | linked, not harvested | report | ||||||
| 214 | RReLU | 88.8 | – | Paper | Code | 2015 | linked, not harvested | report | ||||||
| 215 | ResNet-56 (Trainable Activations) | 88.8 | – | Paper | Code | 2023 | linked, not harvested | report | ||||||
| 216 | F-DENSER++ | 88.73 | – | Paper | – | 2019 | no code linked | report | ||||||
| 217 | Diffusion Classifier (zero-shot) | 88.5 | – | Paper | Code | 2023 | 2 of 2 ran · 0 unverified | report | ||||||
| 218 | ReNet | 87.7 | ✓ | Paper | Code | 2015 | linked, not harvested | report | ||||||
| 219 | OnDev-LCT-8/3 | 87.65 | 87.65 | 0.95M | – | Paper | – | 2024 | no code linked | report | ||||
| 220 | OnDev-LCT-4/3 | 87.03 | 87.03 | 0.55M | – | Paper | – | 2024 | no code linked | report | ||||
| 221 | TripleNet-B | 87.03 | – | Paper | Code | 2022 | 1 of 1 ran · 0 unverified | report | ||||||
| 222 | An Analysis of Unsupervised Pre-training in Light of Recent Advances | 86.7 | – | Paper | Code | 2014 | linked, not harvested | report | ||||||
| 223 | ThreshNet95 | 86.69 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 224 | OnDev-LCT-8/1 | 86.64 | 86.64 | 0.91M | – | Paper | – | 2024 | no code linked | report | ||||
| 225 | ShortNet1-53 | 86.64 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 226 | OnDev-LCT-4/1 | 86.61 | 86.61 | 0.51M | – | Paper | – | 2024 | no code linked | report | ||||
| 227 | CNN+ Wilson-Cowan model RNN | 86.59 | – | Paper | Code | 2024 | linked, not harvested | report | ||||||
| 228 | ResNet-8 (Trainable Activations) | 86.5 | – | Paper | Code | 2023 | linked, not harvested | report | ||||||
| 229 | ThresholdNet | 86.34 | – | Paper | – | 2021 | no code linked | report | ||||||
| 230 | OnDev-LCT-2/1 | 86.27 | 86.27 | 0.31M | – | Paper | – | 2024 | no code linked | report | ||||
| 231 | OnDev-LCT-2/3 | 86.04 | 86.04 | 0.35M | – | Paper | – | 2024 | no code linked | report | ||||
| 232 | OnDev-LCT-1/3 | 85.73 | 85.73 | 0.25M | – | Paper | – | 2024 | no code linked | report | ||||
| 233 | cvpr_class | 85.28 | – | Paper | Code | 2021 | 0 of 3 ran · 3 unverified | report | ||||||
| 234 | WaveMix | 85.21 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 235 | Stochastic Pooling | 84.9 | – | Paper | Code | 2013 | linked, not harvested | report | ||||||
| 236 | OnDev-LCT-1/1 | 84.55 | 84.55 | 0.21M | – | Paper | – | 2024 | no code linked | report | ||||
| 237 | Improving neural networks by preventing co-adaptation of feature detectors | 84.4 | – | Paper | Code | 2012 | linked, not harvested | report | ||||||
| 238 | CCN | 83.36 | ✓ | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 239 | CvN | 83.26 | ✓ | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 240 | UL-Hopfield (ULH) | 83.1 | – | Paper | – | 2018 | no code linked | report | ||||||
| 241 | DCGAN | 82.8 | ✓ | Paper | Code | 2015 | 113 of 219 ran · 106 unverified | report | ||||||
| 242 | TM Composites Toolbox | 82.8 | ✓ | Paper | Code | 2024 | linked, not harvested | report | ||||||
| 243 | CKN | 82.2 | – | Paper | – | 2014 | no code linked | report | ||||||
| 244 | The Analog Activation Function | 82.06 | 545100 | 82.06 | 0.5551 | – | Paper | Code | 2025 | linked, not harvested | report | |||
| 245 | Discriminative Unsupervised Feature Learning with Convolutional Neural Networks | 82 | – | Paper | Code | 2014 | linked, not harvested | report | ||||||
| 246 | Sign-symmetry | 80.98 | ✓ | Paper | Code | 2015 | linked, not harvested | report | ||||||
| 247 | pFedBreD_ns_mg | 80.63 | – | Paper | – | 2022 | no code linked | report | ||||||
| 248 | 1 Layer K-means | 80.6 | – | Paper | Code | 2015 | 113 of 219 ran · 106 unverified | report | ||||||
| 249 | APVT | 80.45 | – | Paper | – | 2022 | no code linked | report | ||||||
| 250 | Learning with Recursive Perceptual Representations | 79.7 | – | Paper | – | 2012 | no code linked | report | ||||||
| 251 | LeViP | 79.50 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 252 | Convolutional Deep Belief Network | 78.9 | – | – | – | not matched | report | |||||||
| 253 | PCANet | 78.7 | – | Paper | Code | 2014 | 0 of 3 ran · 3 unverified | report | ||||||
| 254 | Hybrid ViT+RoPE | 76.9 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 255 | FLSCNN | 75.9 | – | Paper | – | 2015 | no code linked | report | ||||||
| 256 | Hybrid Vision Nystromformer (ViN) | 75.26 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 257 | CTM Drop Clause | 75.1 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 258 | Hybrid PiN | 74 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 259 | SmoothNetV1 | 73.5 | – | Paper | Code | 2022 | linked, not harvested | report | ||||||
| 260 | SNN | 68.3 | – | Paper | Code | 2023 | linked, not harvested | report | ||||||
| 261 | Vision Nystromformer (ViN) | 65.06 | – | Paper | Code | 2021 | linked, not harvested | report | ||||||
| 262 | ANODE | 60.6 | – | Paper | Code | 2019 | 2 of 9 ran · 7 unverified | report | ||||||
| 263 | efficient adaptive ensembling | 99.612 | ✓ | Paper | – | 2022 | no code linked | report | ||||||
| 264 | DGMMC-S | 98.8 | – | Paper | Code | 2024 | linked, not harvested | report | ||||||
| 265 | SAG-ViT | 95.74 | – | Paper | Code | 2024 | linked, not harvested | report |
All 265 rows shown. 263 link to a paper page on this site; 43 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 of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded 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). 122 rows have a graph line, from 86 distinct papers; 95 rows (70 papers) have at least one sample that ran. Counting each paper once: Syntology ran 1,110 of 2,159 samples; 1,049 unverified. Separately, 672 of those 2,159 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. Read from the graph 2026-09-24. Per-sample status is on the paper page.
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