Configuration

dyMEAN-FixFR

Protein model evaluated by the ProteinBench authors under their harness.

Overview

Protein model evaluated by the ProteinBench authors under their harness.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

Release 2026-09-17-134cd1815de8 · 11 evaluations · 11 metric rows. Different protocols are not a single leaderboard. Where several source tables report the same metric, the published comparisons above offer a pooled view that names what it does not hold constant.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
dyMEAN-FixFR on ProteinBench AB-ACCURACY-RMSD: Accuracy RMSD Configuration: dyMEAN-FixFRTask: ProteinBench AB-ACCURACY-RMSD: Accuracy RMSDDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
2.37 ± 0.03 rmsd Unit: score · Direction: lower	Uncertainty: type: standard deviation; value: 0.03 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(dyMEAN-FixFR), column(Accuracy RMSD ↓) Source checking is not independent reproduction.
dyMEAN-FixFR on ProteinBench AB-ACCURACY-TM-SCORE: Accuracy TM-score Configuration: dyMEAN-FixFRTask: ProteinBench AB-ACCURACY-TM-SCORE: Accuracy TM-scoreDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
0.35 ± 0.01 tm-score Unit: score · Direction: higher	Uncertainty: type: standard deviation; value: 0.01 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(dyMEAN-FixFR), column(Accuracy TM-score ↑) Source checking is not independent reproduction.
dyMEAN-FixFR on ProteinBench AB-FUNCTIONALITY-BINDING-ENERGY: Functionality Binding Energy Configuration: dyMEAN-FixFRTask: ProteinBench AB-FUNCTIONALITY-BINDING-ENERGY: Functionality Binding EnergyDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
612.75 ± 56.03 binding-energy Unit: score · Direction: lower	Uncertainty: type: standard deviation; value: 56.03 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(dyMEAN-FixFR), column(Functionality Binding Energy ↓) Source checking is not independent reproduction.
dyMEAN-FixFR on ProteinBench AB-RATIONALITY-CLASHES-INNER: Rationality Clashes-inner Configuration: dyMEAN-FixFRTask: ProteinBench AB-RATIONALITY-CLASHES-INNER: Rationality Clashes-innerDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
8.88 ± 0.55 clashes-inner Unit: score · Direction: lower	Uncertainty: type: standard deviation; value: 0.55 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(dyMEAN-FixFR), column(Rationality Clashes-inner ↓) Source checking is not independent reproduction.
dyMEAN-FixFR on ProteinBench AB-RATIONALITY-CLASHES-OUTER: Rationality Clashes-outer Configuration: dyMEAN-FixFRTask: ProteinBench AB-RATIONALITY-CLASHES-OUTER: Rationality Clashes-outerDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
0.48 ± 0.12 clashes-outer Unit: score · Direction: lower	Uncertainty: type: standard deviation; value: 0.12 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(dyMEAN-FixFR), column(Rationality Clashes-outer ↓) Source checking is not independent reproduction.
dyMEAN-FixFR on ProteinBench AB-RATIONALITY-CN-SCORE: Rationality CN-score Configuration: dyMEAN-FixFRTask: ProteinBench AB-RATIONALITY-CN-SCORE: Rationality CN-scoreDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
1.14 ± 1.71 cn-score Unit: score · Direction: higher	Uncertainty: type: standard deviation; value: 1.71 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(dyMEAN-FixFR), column(Rationality CN-score ↑) Source checking is not independent reproduction.
dyMEAN-FixFR on ProteinBench AB-RATIONALITY-SCRMSD: Rationality scRMSD Configuration: dyMEAN-FixFRTask: ProteinBench AB-RATIONALITY-SCRMSD: Rationality scRMSDDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
2 .48 ± 0.24 scrmsd Unit: score · Direction: lower	Uncertainty: type: standard deviation; value: 0.24 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(dyMEAN-FixFR), column(Rationality scRMSD ↓) Source checking is not independent reproduction.
dyMEAN-FixFR on ProteinBench AB-RATIONALITY-SEQNAT: Rationality SeqNat Configuration: dyMEAN-FixFRTask: ProteinBench AB-RATIONALITY-SEQNAT: Rationality SeqNatDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
-1.82 ± 0.10 seqnat Unit: score · Direction: higher	Uncertainty: type: standard deviation; value: 0.10 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(dyMEAN-FixFR), column(Rationality SeqNat ↑) Source checking is not independent reproduction.
dyMEAN-FixFR on ProteinBench AB-RATIONALITY-TOTAL-ENERGY: Rationality Total Energy Configuration: dyMEAN-FixFRTask: ProteinBench AB-RATIONALITY-TOTAL-ENERGY: Rationality Total EnergyDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
1239.29 ± 113.84 total-energy Unit: score · Direction: lower	Uncertainty: type: standard deviation; value: 113.84 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(dyMEAN-FixFR), column(Rationality Total Energy ↓) Source checking is not independent reproduction.
dyMEAN-FixFR on ProteinBench AB-SPECIFICITY-SEQSIM-INNER: Specificity SeqSim-inner Configuration: dyMEAN-FixFRTask: ProteinBench AB-SPECIFICITY-SEQSIM-INNER: Specificity SeqSim-innerDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
0.96 seqsim-inner Unit: score · Direction: higher	Uncertainty: Not reported Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(dyMEAN-FixFR), column(Specificity SeqSim-inner ↑) Source checking is not independent reproduction.
dyMEAN-FixFR on ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outer Configuration: dyMEAN-FixFRTask: ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outerDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
0.60 seqsim-outer Unit: score · Direction: lower	Uncertainty: Not reported Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(dyMEAN-FixFR), column(Specificity SeqSim-outer ↓) Source checking is not independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

0 evidence rows matching the loaded filters