Configuration

HelixFold 3 — FoldBench published inference

5 seeds × 5 samples, 10 recycles; highest model ranking score. Paper-specific input/code adjustments; H800 80GB inference.

9 evaluations · 35 results

Overview

5 seeds × 5 samples, 10 recycles; highest model ranking score. Paper-specific input/code adjustments; H800 80GB inference.

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

Evaluations and results

9 evaluations · 35 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench antibody-antigen published full-set assessment Dataset: FoldBench antibody-antigen published targets	9.97 irmsd angstrom · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench antibody antigen helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, antibody-antigen block, iRMSD row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench antibody-antigen published full-set assessment Dataset: FoldBench antibody-antigen published targets	0.84 lddt fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench antibody antigen helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, antibody-antigen block, LDDT row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench antibody-antigen published full-set assessment Dataset: FoldBench antibody-antigen published targets	33 lrmsd angstrom · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench antibody antigen helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, antibody-antigen block, lRMSD row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench antibody-antigen published full-set assessment Dataset: FoldBench antibody-antigen published targets	28.4% success-rate percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench antibody antigen helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, antibody-antigen block, Success rate row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench dna-monomer published full-set assessment Dataset: FoldBench dna-monomer published targets	0.38 gdt-ts fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench dna monomer helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, dna-monomer block, GDT-TS row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench dna-monomer published full-set assessment Dataset: FoldBench dna-monomer published targets	0.29 lddt fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench dna monomer helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, dna-monomer block, LDDT row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench dna-monomer published full-set assessment Dataset: FoldBench dna-monomer published targets	10.7 rmsd angstrom · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench dna monomer helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, dna-monomer block, RMSD row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench dna-monomer published full-set assessment Dataset: FoldBench dna-monomer published targets	0.19 tm-score fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench dna monomer helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, dna-monomer block, TM-score row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-dna published full-set assessment Dataset: FoldBench protein-dna published targets	7.67 irmsd angstrom · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein dna helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-dna block, iRMSD row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-dna published full-set assessment Dataset: FoldBench protein-dna published targets	0.71 lddt fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein dna helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-dna block, LDDT row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-dna published full-set assessment Dataset: FoldBench protein-dna published targets	17.1 lrmsd angstrom · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein dna helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-dna block, lRMSD row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-dna published full-set assessment Dataset: FoldBench protein-dna published targets	50% success-rate percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein dna helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-dna block, Success rate row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-ligand published full-set assessment Dataset: FoldBench protein-ligand published targets	0.89 lddt-lp fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein ligand helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-ligand block, LDDT-LP row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-ligand published full-set assessment Dataset: FoldBench protein-ligand published targets	0.69 lddt-pli fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein ligand helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-ligand block, LDDT-PLI row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-ligand published full-set assessment Dataset: FoldBench protein-ligand published targets	51.8% success-rate percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein ligand helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-ligand block, Success rate row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-monomer published full-set assessment Dataset: FoldBench protein-monomer published targets	0.91 gdt-ts fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein monomer helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-monomer block, GDT-TS row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-monomer published full-set assessment Dataset: FoldBench protein-monomer published targets	0.86 lddt fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein monomer helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-monomer block, LDDT row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-monomer published full-set assessment Dataset: FoldBench protein-monomer published targets	2.03 rmsd angstrom · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein monomer helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-monomer block, RMSD row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-monomer published full-set assessment Dataset: FoldBench protein-monomer published targets	0.94 tm-score fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein monomer helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-monomer block, TM-score row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-peptide published full-set assessment Dataset: FoldBench protein-peptide published targets	3.72 irmsd angstrom · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein peptide helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-peptide block, iRMSD row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-peptide published full-set assessment Dataset: FoldBench protein-peptide published targets	0.83 lddt fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein peptide helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-peptide block, LDDT row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-peptide published full-set assessment Dataset: FoldBench protein-peptide published targets	9.79 lrmsd angstrom · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein peptide helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-peptide block, lRMSD row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-peptide published full-set assessment Dataset: FoldBench protein-peptide published targets	89.5% success-rate percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein peptide helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-peptide block, Success rate row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-protein published full-set assessment Dataset: FoldBench protein-protein published targets	7.14 irmsd angstrom · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein protein helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-protein block, iRMSD row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inference	Protocol: FoldBench protein-protein published full-set assessment Dataset: FoldBench protein-protein published targets	0.78 lddt fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source foldbench protein protein helixfold3 Not reported Aggregation: source table mean FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-protein block, LDDT row, HelixFold 3 column; Table 1 assessable count

Source checking is not independent reproduction. Release 2026-09-30-e37e3ab1284d.

Use this model

How it works, versions and access

Strengths, limitations and unresolved questions

Evidence

Source checking verifies the cited claim or transcription. It does not establish 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

Claims, original sources and review scope · Release 2026-09-30-e37e3ab1284d
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

View linked audit checks and correction history

Release 2026-09-30-e37e3ab1284d · Record review: source checked

2 source records and release history

Benchmarking all-atom biomolecular structure prediction with FoldBench · Original source · 10.1038/s41467-025-67127-3
FoldBench supplementary target coverage and performance · Original source · Supplementary Information to 10.1038/s41467-025-67127-3

Download this release

Technical metadata and extraction receipts

Stable ID: ucc-research-config-foldbench-helixfold3

review: method: automated_source_review; actor: Codex research coverage worker; reviewed at: 2026-09-30T21:43:56Z; note: Primary-source table transcription and scope review; no independent reproduction or human scientific review.
code commit: 705c2974a833cdc3a4420f4e3379da596091c97f
samples: 25
recycles: 10
selection: highest model ranking score
missing metadata: weights sha256: not extracted

Related records

variant of: HelixFold 3
configuration: foldbench antibody antigen helixfold3
configuration: foldbench dna monomer helixfold3
configuration: foldbench protein dna helixfold3
configuration: foldbench protein ligand helixfold3
configuration: foldbench protein monomer helixfold3
configuration: foldbench protein peptide helixfold3
configuration: foldbench protein protein helixfold3
configuration: foldbench protein rna helixfold3
configuration: foldbench rna monomer helixfold3

Suggest a correction