The current 2026 edition and every prior OAEI Bio-ML campaign. Use the year tabs to switch editions.
Prior editions kept a different pair set and evaluation setup, so each is shown in its own structure;
the 2026 organiser baselines live on the baselines page.
First OAEI Bio-ML edition (superseded LargeBio). Unsupervised (90% test maps) and semi-supervised (70% test maps): equivalence by P/R/F + local ranking, subsumption by local ranking. Source: krr-oxford.github.io.
Equivalence matching=
Unsupervised (90% Test Mappings)
Semi-supervised (70% Test Mappings)
System
Precision
Recall
F-score
MRR
Hits@1
Precision
Recall
F-score
MRR
Hits@1
LogMap
0.918
0.667
0.773
0.559
0.364
0.896
0.661
0.761
0.559
0.363
LogMap-Lite
0.981
0.578
0.727
0.976
0.575
0.723
AMD
0.885
0.768
0.823
0.858
0.770
0.811
BERTMap
0.912
0.829
0.868
0.967
0.953
0.823
0.887
0.854
0.968
0.955
BERTMap-Lite
0.912
0.776
0.838
0.904
0.884
0.889
0.771
0.826
0.903
0.883
Matcha-DL
0.955
0.801
0.871
0.810
0.804
Matcha
0.906
0.756
0.825
0.883
0.754
0.813
ATMatcher
0.964
0.603
0.742
0.954
0.604
0.740
LSMatch
0.719
0.565
0.633
0.665
0.565
0.611
Subsumption matching< >
Unsupervised (90% Test Mappings)
Semi-supervised (70% Test Mappings)
System
MRR
Hits@1
Hits@5
Hits@10
MRR
Hits@1
Hits@5
Hits@10
Word2Vec+RF
0.306
0.206
0.390
0.510
0.363
0.263
0.448
0.566
OWL2Vec*+RF
0.388
0.285
0.485
0.604
0.422
0.315
0.524
0.647
BERTSubs (IC)
0.601
0.460
0.777
0.877
0.618
0.496
0.758
0.862
Equivalence matching=
Unsupervised (90% Test Mappings)
Semi-supervised (70% Test Mappings)
System
Precision
Recall
F-score
MRR
Hits@1
Precision
Recall
F-score
MRR
Hits@1
LogMap
0.827
0.498
0.622
0.803
0.742
0.788
0.501
0.612
0.805
0.744
LogMap-Lite
0.935
0.259
0.405
0.919
0.261
0.407
AMD
0.664
0.565
0.611
0.601
0.567
0.583
BERTMap
0.730
0.572
0.641
0.873
0.817
0.762
0.548
0.637
0.877
0.823
BERTMap-Lite
0.819
0.499
0.620
0.776
0.729
0.781
0.507
0.615
0.777
0.727
Matcha-DL
0.887
0.578
0.700
0.600
0.583
Matcha
0.743
0.508
0.604
0.694
0.511
0.589
ATMatcher
0.940
0.247
0.391
0.925
0.251
0.395
LSMatch
0.650
0.221
0.329
0.594
0.223
0.325
Subsumption matching< >
Unsupervised (90% Test Mappings)
Semi-supervised (70% Test Mappings)
System
MRR
Hits@1
Hits@5
Hits@10
MRR
Hits@1
Hits@5
Hits@10
Word2Vec+RF
0.191
0.106
0.223
0.362
0.193
0.110
0.233
0.315
OWL2Vec*+RF
0.270
0.160
0.362
0.521
0.284
0.151
0.411
0.534
BERTSubs (IC)
0.299
0.108
0.473
0.613
0.295
0.139
0.472
0.667
Equivalence matching=
Unsupervised (90% Test Mappings)
Semi-supervised (70% Test Mappings)
System
Precision
Recall
F-score
MRR
Hits@1
Precision
Recall
F-score
MRR
Hits@1
LogMap
0.702
0.581
0.636
0.545
0.330
0.646
0.580
0.611
0.542
0.328
LogMap-Lite
0.967
0.543
0.695
0.958
0.543
0.693
AMD
0.890
0.704
0.786
0.861
0.709
0.778
BERTMap
0.997
0.639
0.773
0.954
0.930
0.811
0.708
0.756
0.967
0.950
BERTMap-Lite
0.976
0.660
0.787
0.895
0.869
0.970
0.665
0.789
0.897
0.871
Matcha-DL
0.998
0.756
0.856
0.790
0.782
Matcha
0.875
0.594
0.707
0.845
0.592
0.696
ATMatcher
0.264
0.226
0.244
0.216
0.223
0.219
LSMatch
0.809
0.072
0.132
0.762
0.070
0.128
Subsumption matching< >
Unsupervised (90% Test Mappings)
Semi-supervised (70% Test Mappings)
System
MRR
Hits@1
Hits@5
Hits@10
MRR
Hits@1
Hits@5
Hits@10
Word2Vec+RF
0.558
0.415
0.731
0.850
0.629
0.503
0.792
0.886
OWL2Vec*+RF
0.668
0.540
0.836
0.911
0.743
0.626
0.900
0.944
BERTSubs (IC)
0.589
0.422
0.816
0.939
0.622
0.490
0.788
0.878
Equivalence matching=
Unsupervised (90% Test Mappings)
Semi-supervised (70% Test Mappings)
System
Precision
Recall
F-score
MRR
Hits@1
Precision
Recall
F-score
MRR
Hits@1
LogMap
0.823
0.547
0.657
0.824
0.747
0.783
0.547
0.644
0.821
0.743
LogMap-Lite
0.947
0.520
0.671
0.932
0.519
0.667
AMD
0.836
0.534
0.652
0.792
0.528
0.633
BERTMap
0.655
0.777
0.711
0.960
0.939
0.575
0.784
0.664
0.965
0.947
BERTMap-Lite
0.815
0.709
0.759
0.900
0.876
0.775
0.713
0.743
0.900
0.876
Matcha-DL
0.956
0.615
0.748
0.654
0.640
Matcha
0.754
0.564
0.645
0.704
0.564
0.626
ATMatcher
0.866
0.284
0.428
0.835
0.286
0.426
LSMatch
0.902
0.238
0.377
0.877
0.238
0.374
Subsumption matching< >
Unsupervised (90% Test Mappings)
Semi-supervised (70% Test Mappings)
System
MRR
Hits@1
Hits@5
Hits@10
MRR
Hits@1
Hits@5
Hits@10
Word2Vec+RF
0.512
0.368
0.694
0.834
0.577
0.433
0.773
0.880
OWL2Vec*+RF
0.603
0.461
0.782
0.860
0.666
0.547
0.827
0.880
BERTSubs (IC)
0.530
0.333
0.786
0.948
0.638
0.463
0.859
0.953
Equivalence matching=
Unsupervised (90% Test Mappings)
Semi-supervised (70% Test Mappings)
System
Precision
Recall
F-score
MRR
Hits@1
Precision
Recall
F-score
MRR
Hits@1
LogMap
0.915
0.612
0.733
0.820
0.695
0.893
0.609
0.724
0.821
0.699
LogMap-Lite
0.995
0.598
0.747
0.994
0.594
0.743
AMD
0.962
0.745
0.840
0.952
0.746
0.836
BERTMap
0.966
0.606
0.745
0.919
0.876
0.941
0.724
0.818
0.963
0.941
BERTMap-Lite
0.979
0.432
0.600
0.836
0.760
0.973
0.429
0.595
0.835
0.758
Matcha-DL
0.999
0.593
0.744
0.612
0.597
Matcha
0.941
0.613
0.742
0.924
0.607
0.733
ATMatcher
0.937
0.566
0.706
0.920
0.563
0.698
LSMatch
0.982
0.551
0.706
0.976
0.548
0.702
Subsumption matching< >
Unsupervised (90% Test Mappings)
Semi-supervised (70% Test Mappings)
System
MRR
Hits@1
Hits@5
Hits@10
MRR
Hits@1
Hits@5
Hits@10
Word2Vec+RF
0.488
0.335
0.687
0.852
0.526
0.402
0.663
0.834
OWL2Vec*+RF
0.524
0.364
0.738
0.870
0.579
0.446
0.747
0.893
BERTSubs (IC)
0.504
0.321
0.762
0.920
0.476
0.281
0.715
0.900
Published OAEI Bio-ML 2022 results, transcribed from the campaign result pages. Footnote marks
(∗ † ‡) and the “Use Train(ing) Maps” flag are those of the original tables. Blank cells were not
reported. Authoritative copy: krr-oxford.github.io.
Unsupervised (no train maps) and semi-supervised (optional 30% train maps). Subsumption is local-ranking; "Use Training Maps" (✔/✘) marks whether the 30% train maps were used. Source: krr-oxford.github.io.
Equivalence matching=
Unsupervised (No Train Maps)
Semi-supervised (Optional 30% Train Maps)
System
Precision
Recall
F-score
MRR
Hits@1
Use Train Maps
Precision
Recall
F-score
MRR
Hits@1
AMD∗
0.885
0.691
0.777
✔
0.858
0.770
0.811
BERTMap‡
0.888
0.878
0.883
0.959
0.937
✔
0.831
0.883
0.856
0.960
0.938
BERTMapLt‡
0.919
0.772
0.839
0.890
0.861
✘
0.888
0.770
0.825
0.890
0.861
LogMap†
0.934
0.668
0.779
✘
0.908
0.664
0.767
LogMapBio†
0.860
0.962
0.908
✘
0.811
0.959
0.879
LogMapLt†
0.983
0.575
0.725
✘
0.976
0.575
0.723
Matcha†
0.882
0.756
0.814
✘
0.839
0.750
0.792
Matcha-DL∗
0.847
0.586
0.693
0.870
0.844
✔
0.847
0.834
0.841
0.870
0.844
OLaLa∗
0.913
0.864
0.888
✘
0.880
0.861
0.870
SORBETMtch†∗
0.920
0.907
0.913
✔
0.925
0.882
0.903
Subsumption matching< >
System
Use Training Maps
MRR
Hits@1
Hits@5
Hits@10
BERTSubs (IC)‡
✔
0.535
0.342
0.796
0.938
BERTSubs (IC)‡
✘
0.442
0.240
0.710
0.916
OWL2Vec* + RF
✔
0.626
0.509
0.761
0.864
OWL2Vec* + RF‡
✘
0.617
0.503
0.755
0.858
OWL2Vec* + RF (del)
✔
0.429
0.323
0.519
0.646
OWL2Vec* + RF (del)
✘
0.368
0.282
0.433
0.524
Word2Vec + RF
✔
0.537
0.397
0.702
0.819
SORBETMtch∗
✔
0.802
0.695
0.941
0.977
Word2Vec + RF‡
✘
0.520
0.378
0.690
0.806
Word2Vec + RF (del)
✔
0.361
0.246
0.472
0.599
Word2Vec + RF (del)‡
✘
0.330
0.229
0.419
0.532
Equivalence matching=
Unsupervised (No Train Maps)
Semi-supervised (Optional 30% Train Maps)
System
Precision
Recall
F-score
MRR
Hits@1
Use Train Maps
Precision
Recall
F-score
MRR
Hits@1
AMD∗
0.664
0.508
0.576
✔
0.601
0.567
0.583
BERTMap‡
0.734
0.576
0.646
0.880
0.830
✔
0.645
0.592
0.617
0.891
0.841
BERTMapLt‡
0.834
0.497
0.623
0.766
0.716
✘
0.782
0.507
0.615
0.766
0.716
LogMap†
0.876
0.448
0.593
✘
0.834
0.456
0.589
LogMapBio†
0.866
0.609
0.715
✘
0.821
0.614
0.703
LogMapLt†
0.940
0.252
0.397
✘
0.919
0.261
0.407
Matcha†
0.781
0.509
0.617
✘
0.718
0.519
0.602
Matcha-DL∗
0.745
0.513
0.607
0.811
0.780
✔
0.745
0.732
0.738
0.811
0.780
OLaLa∗
0.735
0.582
0.649
✘
0.655
0.570
0.610
SORBETMtch†∗
0.693
0.635
0.663
✔
0.568
0.652
0.607
Subsumption matching< >
System
Use Training Maps
MRR
Hits@1
Hits@5
Hits@10
BERTSubs (IC)‡
✔
0.433
0.278
0.597
0.833
BERTSubs (IC)‡
✘
0.395
0.208
0.625
0.778
OWL2Vec* + RF
✔
0.506
0.333
0.722
0.819
OWL2Vec* + RF‡
✘
0.504
0.333
0.714
0.811
Word2Vec + RF
✔
0.416
0.208
0.681
0.806
SORBETMtch∗
✔
0.272
0.181
0.347
0.431
Word2Vec + RF‡
✘
0.406
0.167
0.764
0.792
Word2Vec + RF (del)
✔
0.409
0.205
0.671
0.803
Word2Vec + RF (del)‡
✘
0.401
0.194
0.681
0.782
Equivalence matching=
Unsupervised (No Train Maps)
Semi-supervised (Optional 30% Train Maps)
System
Precision
Recall
F-score
MRR
Hits@1
Use Train Maps
Precision
Recall
F-score
MRR
Hits@1
AMD∗
0.890
0.633
0.740
✔
0.861
0.709
0.778
BERTMap‡
0.979
0.662
0.790
0.944
0.920
✔
0.970
0.669
0.792
0.965
0.947
BERTMapLt‡
0.979
0.655
0.785
0.892
0.865
✘
0.970
0.662
0.787
0.892
0.865
LogMap†
0.744
0.407
0.526
✘
0.673
0.411
0.511
LogMapBio†
0.827
0.577
0.680
✘
0.770
0.577
0.660
LogMapLt†
0.970
0.542
0.696
✘
0.958
0.542
0.693
Matcha†
0.887
0.502
0.641
✘
0.846
0.502
0.630
Matcha-DL∗
0.960
0.602
0.740
0.918
0.908
✔
0.959
0.825
0.887
0.918
0.908
OLaLa∗
0.270
0.348
0.304
✘
0.202
0.339
0.253
SORBETMtch†∗
0.618
0.749
0.677
✔
0.794
0.704
0.746
Subsumption matching< >
System
Use Training Maps
MRR
Hits@1
Hits@5
Hits@10
BERTSubs (IC)‡
✔
0.596
0.466
0.768
0.908
BERTSubs (IC)‡
✘
0.479
0.305
0.692
0.878
OWL2Vec* + RF
✔
0.655
0.510
0.839
0.922
OWL2Vec* + RF‡
✘
0.465
0.293
0.684
0.818
OWL2Vec* + RF (del)
✔
0.630
0.488
0.806
0.899
OWL2Vec* + RF (del)
✘
0.378
0.228
0.562
0.706
Word2Vec + RF
✔
0.588
0.441
0.771
0.884
SORBETMtch∗
✔
0.516
0.311
0.821
0.941
Word2Vec + RF‡
✘
0.356
0.210
0.509
0.694
Word2Vec + RF (del)
✔
0.560
0.432
0.764
0.878
Word2Vec + RF (del)‡
✘
0.305
0.164
0.443
0.639
Equivalence matching=
Unsupervised (No Train Maps)
Semi-supervised (Optional 30% Train Maps)
System
Precision
Recall
F-score
MRR
Hits@1
Use Train Maps
Precision
Recall
F-score
MRR
Hits@1
AMD∗
0.836
0.481
0.610
✔
0.792
0.528
0.633
BERTMap‡
0.557
0.762
0.643
0.954
0.928
✔
0.562
0.771
0.650
0.962
0.938
BERTMapLt‡
0.831
0.687
0.752
0.891
0.859
✘
0.775
0.688
0.729
0.891
0.859
LogMap†
0.870
0.586
0.701
✘
0.823
0.583
0.683
LogMapBio†
0.748
0.795
0.771
✘
0.675
0.793
0.729
LogMapLt†
0.951
0.517
0.670
✘
0.931
0.514
0.662
Matcha†
0.838
0.551
0.665
✘
0.782
0.545
0.642
Matcha-DL∗
0.811
0.514
0.629
0.829
0.806
✔
0.806
0.714
0.757
0.829
0.806
OLaLa∗
0.540
0.546
0.543
✘
0.451
0.545
0.493
SORBETMtch†∗
0.626
0.642
0.634
✔
0.731
0.605
0.662
Subsumption matching< >
System
Use Training Maps
MRR
Hits@1
Hits@5
Hits@10
BERTSubs (IC)‡
✔
0.661
0.483
0.893
0.980
BERTSubs (IC)‡
✘
0.559
0.356
0.832
0.940
OWL2Vec* + RF
✔
0.689
0.510
0.919
0.993
OWL2Vec* + RF‡
✘
0.673
0.503
0.933
0.980
Word2Vec + RF
✔
0.662
0.483
0.899
0.946
SORBETMtch∗
✔
0.685
0.557
0.859
0.899
Word2Vec + RF‡
✘
0.597
0.409
0.866
0.966
Word2Vec + RF (del)
✔
0.584
0.416
0.799
0.906
Word2Vec + RF (del)
✘
0.532
0.369
0.745
0.805
Equivalence matching=
Unsupervised (No Train Maps)
Semi-supervised (Optional 30% Train Maps)
System
Precision
Recall
F-score
MRR
Hits@1
Use Train Maps
Precision
Recall
F-score
MRR
Hits@1
AMD∗
0.962
0.670
0.790
✔
0.952
0.746
0.836
BERTMap‡
0.971
0.585
0.730
0.969
0.951
✔
0.898
0.715
0.796
0.971
0.953
BERTMapLt‡
0.981
0.574
0.724
0.849
0.773
✘
0.973
0.569
0.718
0.849
0.773
LogMap†
0.966
0.607
0.746
✘
0.952
0.603
0.738
LogMapBio†
0.928
0.611
0.737
✘
0.899
0.606
0.724
LogMapLt†
0.996
0.599
0.748
✘
0.994
0.594
0.743
Matcha†
0.987
0.607
0.752
✘
0.982
0.601
0.746
Matcha-DL∗
0.904
0.616
0.733
0.931
0.917
✔
0.903
0.872
0.888
0.931
0.917
SORBETMtch†∗
0.973
0.607
0.748
✔
0.876
0.604
0.715
Subsumption matching< >
System
Use Training Maps
MRR
Hits@1
Hits@5
Hits@10
BERTSubs (IC)
✔
0.436
0.235
0.712
0.908
BERTSubs (IC)
✘
0.378
0.171
0.655
0.877
OWL2Vec* + RF
✔
0.460
0.251
0.753
0.926
OWL2Vec* + RF
✘
0.448
0.255
0.699
0.886
OWL2Vec* + RF (del)
✔
0.437
0.243
0.712
0.888
OWL2Vec* + RF (del)
✘
0.314
0.177
0.433
0.612
Word2Vec + RF
✔
0.405
0.205
0.683
0.867
SORBETMtch∗
✔
0.760
0.659
0.880
0.912
Word2Vec + RF
✘
0.355
0.179
0.551
0.793
Word2Vec + RF (del)
✔
0.386
0.197
0.620
0.831
Word2Vec + RF (del)
✘
0.276
0.144
0.369
0.563
Published OAEI Bio-ML 2023 results, transcribed from the campaign result pages. Footnote marks
(∗ † ‡) and the “Use Train(ing) Maps” flag are those of the original tables. Blank cells were not
reported. Authoritative copy: krr-oxford.github.io.
Unsupervised (no train maps) and semi-supervised (optional 30% train maps). Subsumption is local-ranking; "Use Training Maps" (✔/✘) marks whether the 30% train maps were used. Source: krr-oxford.github.io.
Equivalence matching=
Unsupervised (No Train Maps)
Semi-supervised (Optional 30% Train Maps)
System
Precision
Recall
F-score
MRR
Hits@1
Use Train Maps
Precision
Recall
F-score
MRR
Hits@1
BERTMap‡
0.888
0.878
0.883
0.959
0.937
✔
0.831
0.883
0.856
0.960
0.938
BERTMapLt‡
0.919
0.772
0.839
0.890
0.861
✘
0.888
0.770
0.825
0.890
0.861
BioGITOM∗
✔
0.944
0.884
0.913
BioSTransMatch∗
0.657
0.833
0.735
0.900
0.865
✔
0.698
0.741
0.719
0.906
0.872
HybridOM∗
0.924
0.913
0.918
0.952
0.928
✘
0.895
0.913
0.904
0.952
0.928
LogMap†
0.934
0.668
0.779
✘
0.908
0.664
0.767
LogMapBio†
0.860
0.962
0.908
✘
0.811
0.959
0.879
LogMapLt†
0.983
0.575
0.725
✘
0.976
0.575
0.723
Matcha†
0.882
0.756
0.814
0.902
0.873
✘
0.839
0.750
0.792
0.902
0.873
Subsumption matching< >
System
Use Training Maps
MRR
Hits@1
Hits@5
Hits@10
BERTSubs (IC)‡
✔
0.535
0.342
0.796
0.938
BERTSubs (IC)‡
✘
0.442
0.240
0.710
0.916
OWL2Vec* + RF
✔
0.626
0.509
0.761
0.864
OWL2Vec* + RF‡
✘
0.617
0.503
0.755
0.858
OWL2Vec* + RF (del)
✔
0.429
0.323
0.519
0.646
OWL2Vec* + RF (del)
✘
0.368
0.282
0.433
0.524
Word2Vec + RF
✔
0.537
0.397
0.702
0.819
SORBETMtch∗
✔
0.802
0.695
0.941
0.977
Word2Vec + RF‡
✘
0.520
0.378
0.690
0.806
Word2Vec + RF (del)
✔
0.361
0.246
0.472
0.599
Word2Vec + RF (del)‡
✘
0.330
0.229
0.419
0.532
Equivalence matching=
Unsupervised (No Train Maps)
Semi-supervised (Optional 30% Train Maps)
System
Precision
Recall
F-score
MRR
Hits@1
Use Train Maps
Precision
Recall
F-score
MRR
Hits@1
BERTMap‡
0.734
0.576
0.646
0.880
0.830
✔
0.645
0.592
0.617
0.891
0.841
BERTMapLt‡
0.834
0.497
0.623
0.766
0.716
✘
0.782
0.507
0.615
0.766
0.716
BioGITOM∗
✔
0.951
0.773
0.853
BioSTransMatch∗
0.312
0.586
0.407
0.741
0.683
✔
0.973
0.278
0.432
0.737
0.672
HybridOM∗
0.690
0.679
0.685
0.849
0.792
✘
0.611
0.683
0.645
0.849
0.792
LogMap†
0.876
0.448
0.593
✘
0.834
0.456
0.589
LogMapBio†
0.866
0.609
0.715
✘
0.821
0.614
0.703
LogMapLt†
0.940
0.252
0.397
✘
0.919
0.261
0.407
Matcha†
0.781
0.509
0.617
0.815
0.782
✘
0.718
0.519
0.602
0.815
0.782
Subsumption matching< >
System
Use Training Maps
MRR
Hits@1
Hits@5
Hits@10
BERTSubs (IC)‡
✔
0.433
0.278
0.597
0.833
BERTSubs (IC)‡
✘
0.395
0.208
0.625
0.778
OWL2Vec* + RF
✔
0.506
0.333
0.722
0.819
OWL2Vec* + RF‡
✘
0.504
0.333
0.714
0.811
Word2Vec + RF
✔
0.416
0.208
0.681
0.806
SORBETMtch∗
✔
0.272
0.181
0.347
0.431
Word2Vec + RF‡
✘
0.406
0.167
0.764
0.792
Word2Vec + RF (del)
✔
0.409
0.205
0.671
0.803
Word2Vec + RF (del)‡
✘
0.401
0.194
0.681
0.782
Equivalence matching=
Unsupervised (No Train Maps)
Semi-supervised (Optional 30% Train Maps)
System
Precision
Recall
F-score
MRR
Hits@1
Use Train Maps
Precision
Recall
F-score
MRR
Hits@1
BERTMap‡
0.979
0.662
0.790
0.944
0.920
✔
0.970
0.669
0.792
0.965
0.947
BERTMapLt‡
0.979
0.655
0.785
0.892
0.865
✘
0.970
0.662
0.787
0.892
0.865
BioGITOM∗
✔
0.962
0.886
0.923
BioSTransMatch∗
0.128
0.384
0.192
0.633
0.513
✔
0.357
0.661
0.464
0.855
0.798
HybridOM∗
0.870
0.722
0.790
0.907
0.861
✘
0.825
0.725
0.772
0.907
0.861
LogMap†
0.744
0.407
0.526
✘
0.673
0.411
0.511
LogMapBio†
0.827
0.577
0.680
✘
0.770
0.577
0.660
LogMapLt†
0.970
0.542
0.696
✘
0.958
0.542
0.693
Matcha†
0.887
0.502
0.641
0.950
0.935
✘
0.846
0.502
0.630
0.950
0.935
Subsumption matching< >
System
Use Training Maps
MRR
Hits@1
Hits@5
Hits@10
BERTSubs (IC)‡
✔
0.596
0.466
0.768
0.908
BERTSubs (IC)‡
✘
0.479
0.305
0.692
0.878
OWL2Vec* + RF
✔
0.655
0.510
0.839
0.922
OWL2Vec* + RF‡
✘
0.465
0.293
0.684
0.818
OWL2Vec* + RF (del)
✔
0.630
0.488
0.806
0.899
OWL2Vec* + RF (del)
✘
0.378
0.228
0.562
0.706
Word2Vec + RF
✔
0.588
0.441
0.771
0.884
SORBETMtch∗
✔
0.516
0.311
0.821
0.941
Word2Vec + RF‡
✘
0.356
0.210
0.509
0.694
Word2Vec + RF (del)
✔
0.560
0.432
0.764
0.878
Word2Vec + RF (del)‡
✘
0.305
0.164
0.443
0.639
Equivalence matching=
Unsupervised (No Train Maps)
Semi-supervised (Optional 30% Train Maps)
System
Precision
Recall
F-score
MRR
Hits@1
Use Train Maps
Precision
Recall
F-score
MRR
Hits@1
BERTMap‡
0.557
0.762
0.643
0.954
0.928
✔
0.562
0.771
0.650
0.962
0.938
BERTMapLt‡
0.831
0.687
0.752
0.891
0.859
✘
0.775
0.688
0.729
0.891
0.859
BioSTransMatch∗
0.289
0.663
0.402
0.846
0.789
✔
0.700
0.607
0.650
0.855
0.795
HybridOM∗
0.807
0.710
0.755
0.911
0.870
✘
0.747
0.718
0.732
0.911
0.870
LogMap†
0.870
0.586
0.701
✘
0.823
0.583
0.683
LogMapBio†
0.748
0.795
0.771
✘
0.675
0.793
0.729
LogMapLt†
0.951
0.517
0.670
✘
0.931
0.514
0.662
Matcha†
0.838
0.551
0.665
0.889
0.936
✘
0.782
0.545
0.642
0.889
0.936
Subsumption matching< >
System
Use Training Maps
MRR
Hits@1
Hits@5
Hits@10
BERTSubs (IC)‡
✔
0.661
0.483
0.893
0.980
BERTSubs (IC)‡
✘
0.559
0.356
0.832
0.940
OWL2Vec* + RF
✔
0.689
0.510
0.919
0.993
OWL2Vec* + RF‡
✘
0.673
0.503
0.933
0.980
Word2Vec + RF
✔
0.662
0.483
0.899
0.946
SORBETMtch∗
✔
0.685
0.557
0.859
0.899
Word2Vec + RF‡
✘
0.597
0.409
0.866
0.966
Word2Vec + RF (del)
✔
0.584
0.416
0.799
0.906
Word2Vec + RF (del)
✘
0.532
0.369
0.745
0.805
Equivalence matching=
Unsupervised (No Train Maps)
Semi-supervised (Optional 30% Train Maps)
System
Precision
Recall
F-score
MRR
Hits@1
Use Train Maps
Precision
Recall
F-score
MRR
Hits@1
BERTMap‡
0.971
0.585
0.730
0.969
0.951
✔
0.898
0.715
0.796
0.971
0.953
BERTMapLt‡
0.981
0.574
0.724
0.849
0.773
✘
0.973
0.569
0.718
0.849
0.773
BioGITOM∗
✔
0.983
0.713
0.827
BioSTransMatch∗
0.584
0.844
0.690
0.943
0.918
✔
0.845
0.860
0.852
0.957
0.943
HybridOM∗
0.916
0.889
0.902
0.964
0.936
✘
0.884
0.886
0.885
0.964
0.936
LogMap†
0.966
0.607
0.746
✘
0.952
0.603
0.738
LogMapBio†
0.928
0.611
0.737
✘
0.899
0.606
0.724
LogMapLt†
0.996
0.599
0.748
✘
0.994
0.594
0.743
Matcha†
0.987
0.607
0.752
0.936
0.921
✘
0.982
0.601
0.746
0.936
0.921
Subsumption matching< >
System
Use Training Maps
MRR
Hits@1
Hits@5
Hits@10
BERTSubs (IC)
✔
0.436
0.235
0.712
0.908
BERTSubs (IC)
✘
0.378
0.171
0.655
0.877
OWL2Vec* + RF
✔
0.460
0.251
0.753
0.926
OWL2Vec* + RF
✘
0.448
0.255
0.699
0.886
OWL2Vec* + RF (del)
✔
0.437
0.243
0.712
0.888
OWL2Vec* + RF (del)
✘
0.314
0.177
0.433
0.612
Word2Vec + RF
✔
0.405
0.205
0.683
0.867
SORBETMtch∗
✔
0.760
0.659
0.880
0.912
Word2Vec + RF
✘
0.355
0.179
0.551
0.793
Word2Vec + RF (del)
✔
0.386
0.197
0.620
0.831
Word2Vec + RF (del)
✘
0.276
0.144
0.369
0.563
Published OAEI Bio-ML 2024 results, transcribed from the campaign result pages. Footnote marks
(∗ † ‡) and the “Use Train(ing) Maps” flag are those of the original tables. Blank cells were not
reported. Authoritative copy: krr-oxford.github.io.
Unsupervised (no train maps) and semi-supervised (optional 30% train maps). Equivalence matching only this edition. Source: liseda-lab.github.io.
Equivalence matching=
Unsupervised (No Train Maps)
Semi-supervised (Optional 30% Train Maps)
System
Precision
Recall
F-score
MRR
Hits@1
Use Train Maps
Precision
Recall
F-score
MRR
Hits@1
Agent-OM∗
0.922
0.637
0.753
✘
0.892
0.635
0.742
BERTMap∗
0.888
0.878
0.883
0.959
0.937
✔
0.831
0.883
0.856
0.960
0.938
BERTMapLt∗
0.919
0.772
0.839
0.890
0.861
✘
0.888
0.770
0.825
0.890
0.861
BioGITOM∗
0.924
0.638
0.755
0.913
0.891
✔
0.924
0.911
0.918
0.932
0.891
BioSTransMatch∗
0.554
0.786
0.649
0.856
0.812
✔
0.465
0.787
0.585
0.856
0.812
LogMap∗
0.843
0.893
0.867
✘
0.885
0.895
0.890
LogMapBio†
0.860
0.962
0.908
✘
0.811
0.959
0.879
LogMap-LLM∗
0.932
0.883
0.907
✘
0.905
0.879
0.892
LogMapLt†
0.983
0.575
0.725
✘
0.976
0.575
0.723
Logmap+OWL2Vec4OA∗
0.873
0.834
✘
0.873
0.834
Matcha∗
0.882
0.756
0.814
0.902
0.873
✘
0.839
0.750
0.792
0.902
0.873
OWL2Vec4OA∗
0.879
0.841
✘
0.879
0.841
Equivalence matching=
Unsupervised (No Train Maps)
Semi-supervised (Optional 30% Train Maps)
System
Precision
Recall
F-score
MRR
Hits@1
Use Train Maps
Precision
Recall
F-score
MRR
Hits@1
Agent-OM∗
0.718
0.253
0.375
✘
0.649
0.259
0.369
BERTMap∗
0.734
0.576
0.646
0.880
0.830
✔
0.645
0.592
0.617
0.891
0.841
BERTMapLt∗
0.834
0.497
0.623
0.766
0.716
✘
0.782
0.507
0.615
0.766
0.716
BioGITOM∗
0.845
0.515
0.640
0.834
0.768
✔
0.845
0.736
0.787
0.834
0.768
BioSTransMatch∗
0.218
0.526
0.309
0.693
0.620
✔
0.164
0.529
0.251
0.693
0.620
LogMap∗
0.834
0.456
0.589
✘
0.876
0.448
0.593
LogMapBio†
0.866
0.609
0.715
✘
0.821
0.614
0.703
LogMap-LLM∗
0.916
0.476
0.626
✘
0.886
0.484
0.626
LogMapLt†
0.940
0.252
0.397
✘
0.919
0.261
0.407
Logmap+OWL2Vec4OA∗
0.692
0.618
✘
0.692
0.618
Matcha∗
0.781
0.509
0.617
0.815
0.782
✘
0.718
0.519
0.602
0.815
0.782
OWL2Vec4OA∗
0.707
0.635
✘
0.707
0.635
Equivalence matching=
Unsupervised (No Train Maps)
Semi-supervised (Optional 30% Train Maps)
System
Precision
Recall
F-score
MRR
Hits@1
Use Train Maps
Precision
Recall
F-score
MRR
Hits@1
BERTMap∗
0.979
0.662
0.790
0.944
0.920
✔
0.970
0.669
0.792
0.965
0.947
BERTMapLt∗
0.979
0.655
0.785
0.892
0.865
✘
0.970
0.662
0.787
0.892
0.865
BioGITOM∗
0.831
0.529
0.646
0.909
0.854
✔
0.829
0.748
0.787
0.909
0.854
BioSTransMatch∗
0.164
0.522
0.250
0.633
0.724
✔
0.121
0.522
0.196
0.633
0.724
LogMap∗
0.760
0.569
0.651
✘
0.818
0.564
0.667
LogMapBio†
0.827
0.577
0.680
✘
0.770
0.577
0.660
LogMap-LLM∗
0.869
0.561
0.682
✘
0.842
0.566
0.671
LogMapLt†
0.970
0.542
0.696
✘
0.958
0.542
0.693
Matcha∗
0.887
0.502
0.641
0.950
0.935
✘
0.846
0.502
0.630
0.950
0.935
Equivalence matching=
Unsupervised (No Train Maps)
Semi-supervised (Optional 30% Train Maps)
System
Precision
Recall
F-score
MRR
Hits@1
Use Train Maps
Precision
Recall
F-score
MRR
Hits@1
Agent-OM∗
0.552
0.130
0.211
✘
0.466
0.132
0.206
BERTMap∗
0.557
0.762
0.643
0.954
0.928
✔
0.562
0.771
0.650
0.962
0.938
BERTMapLt∗
0.831
0.687
0.752
0.891
0.859
✘
0.775
0.688
0.729
0.891
0.859
BioGITOM∗
0.777
0.512
0.617
0.929
0.884
✔
0.774
0.719
0.745
0.929
0.884
BioSTransMatch∗
0.199
0.568
0.295
0.779
0.698
✔
0.149
0.572
0.237
0.779
0.698
LogMap∗
0.763
0.772
0.736
✘
0.773
0.775
0.774
LogMapBio†
0.748
0.795
0.771
✘
0.675
0.793
0.729
LogMap-LLM∗
0.821
0.747
0.782
✘
0.762
0.746
0.754
LogMapLt†
0.951
0.517
0.670
✘
0.931
0.514
0.662
Logmap+OWL2Vec4OA∗
0.808
0.739
✘
0.808
0.739
Matcha∗
0.838
0.551
0.665
0.889
0.936
✘
0.782
0.545
0.642
0.889
0.936
OWL2Vec4OA∗
0.828
0.770
✘
0.828
0.770
Equivalence matching=
Unsupervised (No Train Maps)
Semi-supervised (Optional 30% Train Maps)
System
Precision
Recall
F-score
MRR
Hits@1
Use Train Maps
Precision
Recall
F-score
MRR
Hits@1
Agent-OM∗
0.789
0.311
0.446
✘
0.719
0.305
0.428
BERTMap∗
0.971
0.585
0.730
0.969
0.951
✔
0.898
0.715
0.796
0.971
0.953
BERTMapLt∗
0.981
0.574
0.724
0.849
0.773
✘
0.973
0.569
0.718
0.849
0.773
BioGITOM∗
0.793
0.548
0.648
0.913
0.855
✔
0.793
0.779
0.786
0.913
0.855
BioSTransMatch∗
0.303
0.746
0.431
0.908
0.877
✔
0.223
0.745
0.355
0.908
0.877
LogMap∗
0.932
0.620
0.745
✘
0.952
0.625
0.755
LogMapBio†
0.928
0.611
0.737
✘
0.899
0.606
0.724
LogMap-LLM∗
0.979
0.621
0.760
✘
0.970
0.616
0.753
LogMapLt†
0.996
0.599
0.748
✘
0.994
0.594
0.743
Logmap+OWL2Vec4OA∗
0.852
0.777
✘
0.852
0.777
Matcha∗
0.987
0.607
0.752
0.936
0.921
✘
0.982
0.601
0.746
0.936
0.921
OWL2Vec4OA∗
0.864
0.796
✘
0.864
0.796
Published OAEI Bio-ML 2025 results, transcribed from the campaign result pages. Footnote marks
(∗ † ‡) and the “Use Train(ing) Maps” flag are those of the original tables. Blank cells were not
reported. Authoritative copy: liseda-lab.github.io.
No participant submissions yet
The 2026 competition and leaderboards open on 12 July 2026; evaluation closes on
1 September 2026 and the competition ends on 6 September 2026. Submitted systems and their scores
appear here — updated automatically from the live CodaBench leaderboards — once the window opens.
Meanwhile, see the organiser baselines.
Work through the quickstart: download the data from the Hugging
Face dataset, produce one alignment RDF per pair (global) and/or one ranking submission per pair (local
and typed), validate with the scoring-kit scripts, and submit via CodaBench.