Browse › Graphs › Graph Property Prediction › ogbg-molpcba

Graph Property Prediction archive 2025-07-28

ogbg-molpcba Benchmark (Graph Property Prediction)

36 rows 29 with code listed 4 metrics Dataset page

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: Test AP (higher is better), Validation AP (higher is better), Number of params (lower is better). Not inferred (points only, no best-so-far line): Ext. data. Points are placed at the row's paper date; 30 of 36 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 HyperFusino 0.3204 ± 0.0001No0.3353 ± 0.000210887085 – – – not matched report
2 HyperFusion 0.3204 ± 0.0001No0.3353 ± 0.000210887085 – – – not matched report
3 HIG(pre-trained on PCQM4M) 0.3167 ± 0.0034Yes0.3252 ± 0.0043119529665 – – – not matched report
4 TGT-Ag+TGT-At-DP 0.3167 ± 0.0031Yes47000000 ✓ Paper Code 2024 10 of 13 ran · 3 unverified report
5 Graphormer 0.3140 ± 0.00320.3227 ± 0.0024119529664 – Paper Code 2021 linked, not harvested report
6 Graphormer (pre-trained on PCQM4M) 0.3140 ± 0.0032Yes0.3227 ± 0.0024119529664 – Paper Code 2021 linked, not harvested report
7 GatedGCN-HSG 0.3129±0.0020 – Paper Code 2024 4 of 10 ran · 6 unverified report
8 PDF 0.3031 ± 0.0026No0.3115 ± 0.00203842048 – Paper Code 2023 0 of 4 ran · 4 unverified report
9 PAS 0.3012 ± 0.0039No0.3151 ± 0.00475560960 – – – not matched report
10 Nested GIN+virtual node (ensemble) 0.3007 ± 0.0037No0.3059 ± 0.005644187480 – Paper Code 2021 1 of 2 ran · 1 unverified report
11 Nested GIN+virtual node (ens) 0.3007 ± 0.00370.3059 ± 0.0056 – Paper Code 2021 1 of 2 ran · 1 unverified report
12 GINE+bot 0.2994 ± 0.0019No0.3094 ± 0.00235511680 – – – not matched report
13 CRaWl 0.2986 ± 0.0025No0.3075 ± 0.00206115728 – Paper Code 2021 linked, not harvested report
14 GatedGCN+ 0.2981 ± 0.0024No0.3011 ± 0.00376016860 – Paper Code 2025 4 of 12 ran · 8 unverified report
15 GINE+ w/ APPNP 0.2979 ± 0.0030No0.3126 ± 0.00236147029 – Paper Code 2020 linked, not harvested report
16 EGT 0.2961 ± 0.0024 – Paper Code 2021 0 of 4 ran · 4 unverified report
17 PHC-GNN 0.2947 ± 0.0026No0.3068 ± 0.00251690328 – Paper Code 2021 linked, not harvested report
18 GIN-AK 0.2930 ± 0.0044No0.3047 ± 0.00073081029 – Paper Code 2021 4 of 18 ran · 14 unverified report
19 GINE+ w/ virtual nodes 0.2917 ± 0.0015No0.3065 ± 0.00306147029 – Paper Code 2020 linked, not harvested report
20 GPS 0.2907No0.3015 ± 0.00389744496 – Paper Code 2022 3 of 21 ran · 18 unverified report
21 DGN 0.2885 ± 0.0030No0.2970 ± 0.00216732696 – Paper Code 2020 6 of 14 ran · 8 unverified report
22 RandomGIN-vn+FLAG 0.2881 ± 0.0028No0.3035 ± 0.00475572026 – Paper – 2021 no code linked report
23 DeeperGCN+virtual node+FLAG 0.2842 ± 0.0043No0.2952 ± 0.00295550208 – Paper Code 2020 3 of 15 ran · 12 unverified report
24 PNA 0.2838 ± 0.0035No0.2926 ± 0.00266550839 – Paper Code 2020 33 of 55 ran · 22 unverified report
25 GIN+virtual node+FLAG 0.2834 ± 0.0038No0.2912 ± 0.00263374533 – Paper Code 2020 3 of 15 ran · 12 unverified report
26 Nested GIN+virtual node 0.2832 ± 0.00410.2915 ± 0.0035 – Paper Code 2021 1 of 2 ran · 1 unverified report
27 DeeperGCN+virtual node 0.2781 ± 0.0038No0.2920 ± 0.00255550208 – Paper Code 2020 linked, not harvested report
28 GIN+virtual node 0.2703 ± 0.0023No0.2798 ± 0.00253374533 – Paper Code 2018 3 of 10 ran · 7 unverified report
29 GCN+virtual node+FLAG 0.2483 ± 0.0037No0.2556 ± 0.00402017028 – Paper Code 2020 3 of 15 ran · 12 unverified report
30 GCN+virtual node 0.2424 ± 0.0034No0.2495 ± 0.00422017028 – Paper Code 2016 31 of 58 ran · 27 unverified report
31 GIN+FLAG 0.2395 ± 0.0040No0.2451 ± 0.00421923433 – Paper Code 2020 3 of 15 ran · 12 unverified report
32 ChebNet 0.2306 ± 0.0016No0.2372 ± 0.00181475003 – Paper Code 2016 2 of 6 ran · 4 unverified report
33 GIN 0.2266 ± 0.0028No0.2305 ± 0.00271923433 – Paper Code 2018 3 of 10 ran · 7 unverified report
34 GCN+FLAG 0.2116 ± 0.0017No0.2150 ± 0.0022565928 – Paper Code 2020 3 of 15 ran · 12 unverified report
35 MorganFP+Rand. Forest 0.2054 ± 0.0004No0.2226 ± 0.000229440000 – – – not matched report
36 GCN 0.2020 ± 0.0024No0.2059 ± 0.0033565928 – Paper Code 2016 31 of 58 ran · 27 unverified report

All 36 rows shown. 30 link to a paper page on this site; 1 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). 22 rows have a graph line, from 14 distinct papers; 20 rows (12 papers) have at least one sample that ran. Counting each paper once: Syntology ran 104 of 242 samples; 138 unverified. Separately, 77 of those 242 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