Browse › Computer Vision › Multi-Label Classification › CheXpert
CheXpert Benchmark (Multi-Label Classification)
Syntology Since the archive (Syntology): none placed; 1 newer paper judged to report on this board so far.
Multi-Label Classification is the supervised learning problem where an instance may be associated with multiple labels. This is an extension of single-label classification (i.e., multi-class, or binary) where each instance is only associated with a single class label.
The archive carries no text for this table; the description above is the archive's text for the task Multi-Label Classification. archive 2025-07-28
Over time archive 2025-07-28
Direction inferred from the metric name, not from the archive: AVERAGE AUC ON 14 LABEL (higher is better). Not inferred (points only, no best-so-far line): NUM RADS BELOW CURVE. Points are placed at the row's paper date, not an evaluation date; 13 of 226 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 | CFT (ensemble) Macao Polytechnic University | 0.933 | – | Paper | Code | 2023 | linked, not harvested | report | |
| 2 | DeepAUC-v1 | 0.930 | 2.800 | – | Paper | Code | 2020 | linked, not harvested | report |
| 3 | Hierarchical-Learning-V1 (ensemble) | 0.930 | 2.600 | – | Paper | Code | 2019 | linked, not harvested | report |
| 4 | YWW(ensemble) | 0.929 | 2.800 | – | – | – | not matched | report | |
| 5 | Conditional-Training-LSR | 0.929 | 2.600 | – | – | – | not matched | report | |
| 6 | Hierarchical-Learning-V4 (ensemble) | 0.929 | 2.600 | – | Paper | Code | 2019 | linked, not harvested | report |
| 7 | Conditional-Training-LSR-V1 | 0.929 | 2.600 | – | – | – | not matched | report | |
| 8 | Hierarchical-Learning-V0 (ensemble) | 0.929 | 2.600 | – | – | – | not matched | report | |
| 9 | Multi-Stage-Learning-CNN-V3 (ensemble) | 0.928 | 2.600 | – | – | – | not matched | report | |
| 10 | DeepCNNsGM(ensemble) | 0.928 | 2.600 | – | – | – | not matched | report | |
| 11 | inisis | 0.927 | 3.000 | – | – | – | not matched | report | |
| 12 | DeepCNNs(ensemble) | 0.927 | 2.600 | – | – | – | not matched | report | |
| 13 | SenseXDR | 0.927 | 2.600 | – | – | – | not matched | report | |
| 14 | ihil (ensemble) | 0.927 | 2.600 | – | – | – | not matched | report | |
| 15 | JF aboy ensemble_V2 JF HEALTHCARE https://github.com/deadpoppy/CheXpert-Challeng | 0.926 | 3.000 | – | – | – | not matched | report | |
| 16 | DRNet (ensemble) | 0.926 | 2.600 | – | – | – | not matched | report | |
| 17 | yw | 0.926 | 2.600 | – | – | – | not matched | report | |
| 18 | Anatomy-XNet-V1 | 0.926 | 2.600 | – | Paper | – | 2021 | no code linked | report |
| 19 | hoanganh_VB_ensemble3 | 0.925 | 2.400 | – | – | – | not matched | report | |
| 20 | alimebkovk | 0.925 | 2.400 | – | – | – | not matched | report | |
| 21 | uest | 0.924 | 2.600 | – | – | – | not matched | report | |
| 22 | Hoang_VB_ensemble31_v | 0.924 | 2.400 | – | – | – | not matched | report | |
| 23 | tedtt | 0.924 | 2.400 | – | – | – | not matched | report | |
| 24 | as-hust-v3 | 0.924 | 2.400 | – | – | – | not matched | report | |
| 25 | hoanganh_VB_VN | 0.924 | 2.400 | – | – | – | not matched | report | |
| 26 | Hierarchical-CNN-Ensemble-V1 (ensemble) | 0.924 | 2.400 | – | – | – | not matched | report | |
| 27 | DE_APR ensemble ltt | 0.923 | 2.600 | – | – | – | not matched | report | |
| 28 | DE_APR_N ensemble ltt | 0.923 | 2.600 | – | – | – | not matched | report | |
| 29 | Multi-Stage-Learning-CNN-V2 (ensemble) | 0.923 | 2.600 | – | – | – | not matched | report | |
| 30 | Weighted-CNN(ensemble) | 0.923 | 2.600 | – | – | – | not matched | report | |
| 31 | hoanganhcnu_ensemble27_v | 0.923 | 2.400 | – | – | – | not matched | report | |
| 32 | YJ&&YWW :https://github.com/inisis/chexper | 0.923 | 2.400 | – | – | – | not matched | report | |
| 33 | as-hust-v1 | 0.923 | 2.400 | – | – | – | not matched | report | |
| 34 | Maxium (ensemble) | 0.923 | 2.400 | – | – | – | not matched | report | |
| 35 | as-hust-v2 | 0.922 | 2.800 | – | – | – | not matched | report | |
| 36 | Average-CNN(ensemble) | 0.922 | 2.400 | – | – | – | not matched | report | |
| 37 | MaxAUC | 0.922 | 2.400 | – | – | – | not matched | report | |
| 38 | zjr(ensembel) | 0.921 | 2.600 | – | – | – | not matched | report | |
| 39 | SuperCNNv3 | 0.921 | 2.400 | – | – | – | not matched | report | |
| 40 | hyc | 0.921 | 2.400 | – | – | – | not matched | report | |
| 41 | hoangnguyenkcv1 | 0.921 | 2.400 | – | – | – | not matched | report | |
| 42 | {"submit_id": "0x3c7b0af1b5784c159daf259c58543aa3", "predict_id": "0x67b23473183f4f43afa3b37edbc5d7fe", "submitter_id": "0x30db016ad564455ba055eb7f7f4402ac" | 0.920 | 2.600 | – | – | – | not matched | report | |
| 43 | HOANG_VB_VN_2 | 0.920 | 2.400 | – | – | – | not matched | report | |
| 44 | BDNB | 0.919 | 2.600 | – | – | – | not matched | report | |
| 45 | JF Coolver ensemble | 0.919 | 2.600 | – | – | – | not matched | report | |
| 46 | thang ensemble colo | 0.919 | 2.400 | – | – | – | not matched | report | |
| 47 | hoangnn9 ensemble VBV | 0.919 | 2.400 | – | – | – | not matched | report | |
| 48 | JF aboy ensemble_V1 JF HEALTHCARE https://github.com/deadpoppy/CheXpert-Challeng | 0.919 | 2.400 | – | – | – | not matched | report | |
| 49 | {"submit_id": "0x33aeb0f2525e482a886196c273bdf1ba", "predict_id": "0xff2f60907da8440d98ff17f0af749535", "submitter_id": "0x0b382a226d4548c9b441f19b1907fe0f" | 0.919 | 2.200 | – | – | – | not matched | report | |
| 50 | brian-baseline-v2 | 0.919 | 2.200 | – | – | – | not matched | report | |
| 51 | DE_JUN4_RS_EN ensemble LTT | 0.918 | 2.600 | – | – | – | not matched | report | |
| 52 | Mehdi_You (ensemble) | 0.918 | 2.600 | – | – | – | not matched | report | |
| 53 | A Good Model (single model) Macao Polytechnic University | 0.918 | 2.600 | – | Paper | Code | 2023 | linked, not harvested | report |
| 54 | A Good Model (single model) | 0.918 | 2.600 | – | – | – | not matched | report | |
| 55 | Anatomy-XNet (ensemble) | 0.917 | 2.600 | – | Paper | – | 2021 | no code linked | report |
| 56 | Ensemble_v2 | 0.917 | 2.400 | – | – | – | not matched | report | |
| 57 | Deep-CNNs-V1 | 0.917 | 2.200 | – | – | – | not matched | report | |
| 58 | vdn6 ensemble ltt | 0.917 | 2.200 | – | – | – | not matched | report | |
| 59 | Overfit ensemble OTH-A | 0.917 | 2.200 | – | – | – | not matched | report | |
| 60 | thangbk(ensemble) | 0.917 | 2.000 | – | – | – | not matched | report | |
| 61 | desmond | 0.916 | 2.600 | – | – | – | not matched | report | |
| 62 | DE_JUN1_RS_EN ensemble LTT | 0.916 | 2.600 | – | – | – | not matched | report | |
| 63 | DE_JUN3_RS_EN ensemble LTT | 0.916 | 2.400 | – | – | – | not matched | report | |
| 64 | {"submit_id": "0x57dc2989f0474ca095d0841df09cfb18", "predict_id": "0xd43bcf7d4c9b467894db2b274b18794e", "submitter_id": "0x30db016ad564455ba055eb7f7f4402ac" | 0.916 | 2.400 | – | – | – | not matched | report | |
| 65 | ATT-AW-v1 | 0.916 | 2.400 | – | – | – | not matched | report | |
| 66 | {"submit_id": "0xeb9c9e79ed9e4410a2a37d62322f4585", "predict_id": "0x735b718280b14e83895decbc31641f87", "submitter_id": "0x30db016ad564455ba055eb7f7f4402ac" | 0.916 | 2.200 | – | – | – | not matched | report | |
| 67 | Multi-Stage-Learning-CNN-V0 | 0.916 | 2.200 | – | – | – | not matched | report | |
| 68 | TGNB | 0.915 | 2.600 | – | – | – | not matched | report | |
| 69 | ensemble SN | 0.915 | 2.400 | – | – | – | not matched | report | |
| 70 | zhangjingyan | 0.915 | 2.400 | – | – | – | not matched | report | |
| 71 | Deadpoppy Ensemble | 0.915 | 2.200 | – | – | – | not matched | report | |
| 72 | hoangnguyenkcv-ensemble28 | 0.915 | 2.200 | – | – | – | not matched | report | |
| 73 | DE_JUN2_RS_EN ensemble LTT | 0.914 | 2.600 | – | – | – | not matched | report | |
| 74 | GRNB | 0.914 | 2.400 | – | – | – | not matched | report | |
| 75 | Deep-CNNs (ensemble) | 0.914 | 2.000 | – | – | – | not matched | report | |
| 76 | Sky-Model | 0.913 | 2.200 | – | – | – | not matched | report | |
| 77 | JF Deadpoppy | 0.913 | 2.200 | – | – | – | not matched | report | |
| 78 | YWW-YJ:https://github.com/inisis/chexper | 0.913 | 2.000 | – | – | – | not matched | report | |
| 79 | zjy | 0.912 | 2.200 | – | – | – | not matched | report | |
| 80 | WL_Baseline (ensemble) | 0.912 | 2.000 | – | – | – | not matched | report | |
| 81 | KCV-CNN-ensemble-CN | 0.911 | 2.200 | – | – | – | not matched | report | |
| 82 | songta | 0.911 | 2.200 | – | – | – | not matched | report | |
| 83 | bhtrun | 0.911 | 2.200 | – | – | – | not matched | report | |
| 84 | anatomy_xnet_v1 (single model) | 0.911 | 2.200 | – | – | – | not matched | report | |
| 85 | DS_APR_N single model ltt | 0.911 | 2.000 | – | – | – | not matched | report | |
| 86 | DS_APR single model LTT | 0.911 | 2.000 | – | – | – | not matched | report | |
| 87 | brian-baseline | 0.911 | 2.000 | – | – | – | not matched | report | |
| 88 | ensemble SNU | 0.910 | 2.200 | – | – | – | not matched | report | |
| 89 | HinaNetV2 (ensemble) | 0.909 | 2.200 | – | – | – | not matched | report | |
| 90 | KD-Prune10 (Single model) | 0.909 | 2.000 | – | – | – | not matched | report | |
| 91 | G_Mans_ensembl | 0.909 | 1.800 | – | – | – | not matched | report | |
| 92 | Masks and Manuscripts | 0.909 | – | Paper | – | 2024 | no code linked | report | |
| 93 | guran_ri | 0.908 | 2.000 | – | – | – | not matched | report | |
| 94 | vdnnn (ensemble) | 0.908 | 1.800 | – | – | – | not matched | report | |
| 95 | BAAZT | 0.908 | 1.800 | – | – | – | not matched | report | |
| 96 | Stanford Baseline (ensemble) | 0.907 | 1.800 | – | Paper | Code | 2019 | 0 ran · 1 unverified | report |
| 97 | vbn (single model) | 0.907 | 1.600 | – | – | – | not matched | report | |
| 98 | muti_base (ensemble) | 0.907 | 1.600 | – | – | – | not matched | report | |
| 99 | Z_Ensemble_V | 0.907 | 1.400 | – | – | – | not matched | report | |
| 100 | ForwardModelEnsembleCorrected (ensemble) | 0.906 | 1.600 | – | – | – | not matched | report | |
| 101 | LBC-v2 (ensemble) | 0.906 | 1.600 | – | – | – | not matched | report | |
| 102 | LBC-v2 | 0.906 | 1.600 | – | – | – | not matched | report | |
| 103 | LBC-v2 (ensemble) | 0.906 | 1.600 | – | Paper | Code | 2022 | linked, not harvested | report |
| 104 | Multi-CNN | 0.905 | 2.000 | – | – | – | not matched | report | |
| 105 | hy | 0.905 | 1.800 | – | – | – | not matched | report | |
| 106 | ForwardMECorrectedFull (ensemble) | 0.905 | 1.600 | – | – | – | not matched | report | |
| 107 | JustAnotherDensenet | 0.904 | 1.200 | – | – | – | not matched | report | |
| 108 | Orlando (single model) | 0.903 | 1.600 | – | – | – | not matched | report | |
| 109 | Max (single model) | 0.902 | 2.000 | – | – | – | not matched | report | |
| 110 | DeepLungsEnsemble | 0.902 | 1.800 | – | – | – | not matched | report | |
| 111 | Ensemble_v1 | 0.901 | 1.600 | – | – | – | not matched | report | |
| 112 | Nakajima_ayas | 0.901 | 1.400 | – | – | – | not matched | report | |
| 113 | MLC11 NotDense (single-model) | 0.900 | 1.600 | – | – | – | not matched | report | |
| 114 | vn_2 single_model ltt | 0.900 | 1.200 | – | – | – | not matched | report | |
| 115 | AVG_MAX(ensemble) | 0.899 | 2.000 | – | – | – | not matched | report | |
| 116 | Z_Ensemble_ | 0.899 | 1.800 | – | – | – | not matched | report | |
| 117 | llllldz | 0.899 | 1.600 | – | – | – | not matched | report | |
| 118 | DiseaseNet Samg2003 single model, UIUC, http://sambhavgupta.com | 0.899 | 1.600 | – | – | – | not matched | report | |
| 119 | DiseaseNet Samg2003 single model, DPS RKP, http://sambhavgupta.co | 0.899 | 1.600 | – | – | – | not matched | report | |
| 120 | LBC-v0 | 0.899 | 1.400 | – | – | – | not matched | report | |
| 121 | LBC-v0 (ensemble) | 0.899 | 1.400 | – | – | – | not matched | report | |
| 122 | LBC-v0 (ensemble) | 0.899 | 1.400 | – | Paper | Code | 2022 | linked, not harvested | report |
| 123 | BUA | 0.898 | 1.800 | – | – | – | not matched | report | |
| 124 | G_Mans_v2 (single model): LibAUC + coat_mini | 0.898 | 1.400 | – | – | – | not matched | report | |
| 125 | ljc226 | 0.898 | 1.200 | – | – | – | not matched | report | |
| 126 | ForwardModelEnsemble (ensemble) | 0.897 | 1.600 | – | – | – | not matched | report | |
| 127 | NewTrickTest (ensemble) | 0.897 | 1.600 | – | – | – | not matched | report | |
| 128 | AccidentNet v1 (single model) | 0.897 | 1.200 | – | – | – | not matched | report | |
| 129 | ylz-v01 | 0.896 | 1.600 | – | – | – | not matched | report | |
| 130 | ldz | 0.896 | 1.400 | – | – | – | not matched | report | |
| 131 | Densenet | 0.896 | 1.400 | – | – | – | not matched | report | |
| 132 | Stellarium-CheXpert-Local (single model) | 0.896 | 1.400 | – | – | – | not matched | report | |
| 133 | Stellarium-CheXpert-Local | 0.896 | 1.400 | – | – | – | not matched | report | |
| 134 | Stellarium-CheXpert-Local | 0.896 | 1.400 | – | Paper | Code | 2022 | linked, not harvested | report |
| 135 | Deadpoppy Single | 0.895 | 1.800 | – | – | – | not matched | report | |
| 136 | adoudo | 0.895 | 1.600 | – | – | – | not matched | report | |
| 137 | {koala-large} (single model) | 0.895 | 1.400 | – | – | – | not matched | report | |
| 138 | MVD121 | 0.895 | 1.200 | – | – | – | not matched | report | |
| 139 | hust(single model) | 0.895 | 1.000 | – | – | – | not matched | report | |
| 140 | MM1 | 0.894 | 1.600 | – | – | – | not matched | report | |
| 141 | hycN | 0.894 | 1.600 | – | – | – | not matched | report | |
| 142 | zhujier | 0.894 | 1.600 | – | – | – | not matched | report | |
| 143 | U-Random-Ind (single) | 0.894 | 1.000 | – | – | – | not matched | report | |
| 144 | HybridModelEnsemble (ensemble) | 0.892 | 1.600 | – | – | – | not matched | report | |
| 145 | MVD121-320 | 0.891 | 1.200 | – | – | – | not matched | report | |
| 146 | ylz-v02 | 0.891 | 1.000 | – | – | – | not matched | report | |
| 147 | pause | 0.890 | 1.000 | – | – | – | not matched | report | |
| 148 | Overfit ensemble OT | 0.890 | 1.000 | – | – | – | not matched | report | |
| 149 | Haruka_Hamasak | 0.890 | 0.800 | – | – | – | not matched | report | |
| 150 | DenseNet169 at 320x320 (single model) | 0.889 | 1.400 | – | – | – | not matched | report | |
| 151 | LR-baseline (ensemble) | 0.889 | 1.400 | – | – | – | not matched | report | |
| 152 | DataAugFTW (single model) | 0.888 | 1.000 | – | – | – | not matched | report | |
| 153 | {koala} (single model) | 0.888 | 1.000 | – | – | – | not matched | report | |
| 154 | Xception (single model) | 0.887 | 1.200 | – | – | – | not matched | report | |
| 155 | Stellarium (single model) | 0.887 | 1.200 | – | – | – | not matched | report | |
| 156 | Stellarium | 0.887 | 1.200 | – | – | – | not matched | report | |
| 157 | pm_rn50_0.15pp | 0.887 | 1.200 | – | – | – | not matched | report | |
| 158 | baseline3 | 0.886 | 1.200 | – | – | – | not matched | report | |
| 159 | PrateekMunja | 0.886 | 1.000 | – | – | – | not matched | report | |
| 160 | MVR50 | 0.886 | 0.800 | – | – | – | not matched | report | |
| 161 | MNet-Fix (Single Model) | 0.884 | 1.600 | – | – | – | not matched | report | |
| 162 | Coolver XH | 0.884 | 0.800 | – | – | – | not matched | report | |
| 163 | Naive Densenet | 0.883 | 1.200 | – | – | – | not matched | report | |
| 164 | mhealth_buet (single model) | 0.883 | 0.600 | – | – | – | not matched | report | |
| 165 | Aoitori (single model) | 0.882 | 0.800 | – | – | – | not matched | report | |
| 166 | {chexpert-classifier}(single model) | 0.882 | 0.600 | – | – | – | not matched | report | |
| 167 | DearBrave (single model) | 0.882 | 0.400 | – | – | – | not matched | report | |
| 168 | AccidentNet V2 (single model) | 0.881 | 1.000 | – | – | – | not matched | report | |
| 169 | {densenet} (single model) | 0.880 | 1.200 | – | – | – | not matched | report | |
| 170 | Yoake (single model) | 0.879 | 0.600 | – | – | – | not matched | report | |
| 171 | MLC11 Baseline (single-model) | 0.878 | 0.600 | – | – | – | not matched | report | |
| 172 | DenseNet | 0.876 | 1.200 | – | – | – | not matched | report | |
| 173 | HCL1 (single model) | 0.876 | 1.000 | – | – | – | not matched | report | |
| 174 | MLGCN (single model) | 0.875 | 1.200 | – | – | – | not matched | report | |
| 175 | GCN_densenet121-single mode | 0.875 | 1.000 | – | – | – | not matched | report | |
| 176 | GreenTeaCalpis (single model) | 0.873 | 0.800 | – | – | – | not matched | report | |
| 177 | Multi-CNN (ensemble) | 0.873 | 0.400 | – | – | – | not matched | report | |
| 178 | BASELINE ResNet50 | 0.871 | 0.600 | – | – | – | not matched | report | |
| 179 | baseline1 (single model) | 0.868 | 0.800 | – | – | – | not matched | report | |
| 180 | Baseline DenseNet161 | 0.868 | 0.600 | – | – | – | not matched | report | |
| 181 | DSENet | 0.865 | 0.600 | – | – | – | not matched | report | |
| 182 | Densenet-Basic Single NUS | 0.863 | 0.800 | – | – | – | not matched | report | |
| 183 | KD_Mobilenet (single model) | 0.862 | 0.800 | – | – | – | not matched | report | |
| 184 | GoDense (single model) | 0.861 | 1.000 | – | – | – | not matched | report | |
| 185 | inceptionv3_single_NN | 0.861 | 0.400 | – | – | – | not matched | report | |
| 186 | MLKD (Single model) | 0.860 | 0.800 | – | – | – | not matched | report | |
| 187 | BASELINE Acorn | 0.860 | 0.600 | – | – | – | not matched | report | |
| 188 | ErrorNet (single model) | 0.859 | 0.600 | – | – | – | not matched | report | |
| 189 | SleepNet (single model) | 0.859 | 0.600 | – | – | – | not matched | report | |
| 190 | baseline2 | 0.858 | 1.000 | – | – | – | not matched | report | |
| 191 | UMLS_CLIP (single model) | 0.858 | 0.000 | – | – | – | not matched | report | |
| 192 | haw02 (single model) | 0.854 | 0.800 | – | – | – | not matched | report | |
| 193 | CombinedTrainDenseNet121 (single model) | 0.853 | 0.000 | – | – | – | not matched | report | |
| 194 | rayOfLightSingle (Single Model) | 0.851 | 0.400 | – | – | – | not matched | report | |
| 195 | Model_Team_34 (single model) | 0.850 | 0.600 | – | – | – | not matched | report | |
| 196 | Test model habbe | 0.850 | 0.400 | – | – | – | not matched | report | |
| 197 | model2_DenseNet121 | 0.848 | 0.600 | – | – | – | not matched | report | |
| 198 | Baseline | 0.848 | 0.200 | – | – | – | not matched | report | |
| 199 | HinaNet (single model) | 0.844 | 0.400 | – | – | – | not matched | report | |
| 200 | singlehead_models (single model combined) | 0.842 | 0.200 | – | – | – | not matched | report | |
| 201 | mwowra-conditional (single) | 0.840 | 0.400 | – | – | – | not matched | report | |
| 202 | multihead_model (one model for all pathologies) | 0.838 | 0.400 | – | – | – | not matched | report | |
| 203 | mobilenet (single model) | 0.837 | 0.200 | – | – | – | not matched | report | |
| 204 | Grp12BigCNN | 0.835 | 0.000 | – | – | – | not matched | report | |
| 205 | MLC9_Densenet (single model) | 0.834 | 0.400 | – | – | – | not matched | report | |
| 206 | Grp12v2USup2OSamp (ensemble) | 0.830 | 0.200 | – | – | – | not matched | report | |
| 207 | DNET121-single | 0.822 | 0.000 | – | – | – | not matched | report | |
| 208 | DensNet121 | 0.805 | – | Paper | Code | 2020 | linked, not harvested | report | |
| 209 | G_Mans_v1 (single model): | 0.797 | 0.600 | – | – | – | not matched | report | |
| 210 | 12ASLv2(single) | 0.769 | 0.000 | – | – | – | not matched | report | |
| 211 | DenseNet121 (single model) | 0.760 | 0.000 | – | – | – | not matched | report | |
| 212 | 12ASLv1(single) | 0.736 | 0.000 | – | – | – | not matched | report | |
| 213 | haw-baseline (single model) | 0.732 | 0.600 | – | – | – | not matched | report | |
| 214 | rayOfLight (ensemble) | 0.727 | 0.000 | – | – | – | not matched | report | |
| 215 | BASELINE DenseNet121 | 0.724 | 0.000 | – | – | – | not matched | report | |
| 216 | Chest-x-ray classification using | 0.618 | 0.200 | – | – | – | not matched | report | |
| 217 | BME_Final_v2 | 0.615 | 0.000 | – | – | – | not matched | report | |
| 218 | {densenet121}{single model | 0.606 | 0.000 | – | – | – | not matched | report | |
| 219 | autobot | 0.606 | 0.000 | – | – | – | not matched | report | |
| 220 | MLC02_DenseNet121 | 0.575 | 0.000 | – | – | – | not matched | report | |
| 221 | efficiantB5 (single model) | 0.531 | 0.000 | – | – | – | not matched | report | |
| 222 | apalepu1 | 0.524 | 0.000 | – | – | – | not matched | report | |
| 223 | Erdem (single) | 0.500 | 0.000 | – | – | – | not matched | report | |
| 224 | Adalab Standard (Single Model) | 0.481 | 0.000 | – | – | – | not matched | report | |
| 225 | Adalab Standard (single model) | 0.481 | 0.000 | – | – | – | not matched | report | |
| 226 | zeroshot_medclip_baseline (ensemble) | 0.479 | 0.000 | – | – | – | not matched | report |
All 226 rows shown. 13 link to a paper page on this site; 0 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). 1 rows have a graph line, from 1 distinct papers. Rows whose paper has a sample that ran: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument). Papers: 0 with a sample that ran: 0 with a run with no instrument failure, 0 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 1 rows with a graph line, 0 have an archive-official repository: on 0 a sample from it ran (0 with a run with no instrument failure), on 0 the samples that ran came from community repositories only, and on 0 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 samples: 0 ran · 1 unverified. Separately, 1 of those 1 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), 6 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 1,595 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 1 proposed a result, which gave no cell that passed the extractor's own checks; none await a verdict and none 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 |
|---|---|---|---|
| Federated LoRA Adaptation of BiomedCLIP Across Four International Chest X-Ray Cohorts arXiv:2609.02101 | 2 Sep 2026 | repository linked, no samples harvested | refused by a rule: the table's column header does not name the leaderboard's metric |
Syntology 1 newer paper 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 1 counted above as giving no cell that passed the extractor's own checks is the 1 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