Configuration

FoldFlow1(base)

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

20 evaluations · 20 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: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-100-DIVERSITY-MAX-CLUST: length 100, Diversity Max Clust. Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.83 max-clust score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-100-DIVERSITY-MAX-CLUST: length 100, Diversity Max Clust. Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 100, Diversity Max Clust.↑)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-100-DIVERSITY-PAIRWISE-TM: length 100, Diversity pairwise TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.48 ± 0.07 pairwise-tm score · lower Uncertainty: type: standard_deviation; value: 0.07 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-100-DIVERSITY-PAIRWISE-TM: length 100, Diversity pairwise TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 100, Diversity pairwise TM ↓)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-100-NOVELTY-MAX-TM: length 100, Novelty Max TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.62 ± 0.01 max-tm score · lower Uncertainty: type: standard_deviation; value: 0.01 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-100-NOVELTY-MAX-TM: length 100, Novelty Max TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 100, Novelty Max TM ↓)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-100-QUALITY-SCRMSD: length 100, Quality scRMSD Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	1.70 ± 1.95 scrmsd score · lower Uncertainty: type: standard_deviation; value: 1.95 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-100-QUALITY-SCRMSD: length 100, Quality scRMSD Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 100, Quality scRMSD ↓)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-100-QUALITY-SCTM: length 100, Quality scTM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.81 ± 0.15 sctm score · higher Uncertainty: type: standard_deviation; value: 0.15 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-100-QUALITY-SCTM: length 100, Quality scTM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 100, Quality scTM ↑)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-300-DIVERSITY-MAX-CLUST: length 300, Diversity Max Clust. Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.98 max-clust score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-300-DIVERSITY-MAX-CLUST: length 300, Diversity Max Clust. Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 300, Diversity Max Clust. ↑)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-300-DIVERSITY-PAIRWISE-TM: length 300, Diversity pairwise TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.39 ± 0.05 pairwise-tm score · lower Uncertainty: type: standard_deviation; value: 0.05 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-300-DIVERSITY-PAIRWISE-TM: length 300, Diversity pairwise TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 300, Diversity pairwise TM ↓)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-300-NOVELTY-MAX-TM: length 300, Novelty Max TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.54 ± 0.01 max-tm score · lower Uncertainty: type: standard_deviation; value: 0.01 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-300-NOVELTY-MAX-TM: length 300, Novelty Max TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 300, Novelty Max TM ↓)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-300-QUALITY-SCRMSD: length 300, Quality scRMSD Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	9.56 ± 2.42 scrmsd score · lower Uncertainty: type: standard_deviation; value: 2.42 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-300-QUALITY-SCRMSD: length 300, Quality scRMSD Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 300, Quality scRMSD ↓)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-300-QUALITY-SCTM: length 300, Quality scTM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.43 ± 0.09 sctm score · higher Uncertainty: type: standard_deviation; value: 0.09 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-300-QUALITY-SCTM: length 300, Quality scTM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 300, Quality scTM ↑)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-50-DIVERSITY-MAX-CLUST: length 50, Diversity Max Clust. Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.76 max-clust score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-50-DIVERSITY-MAX-CLUST: length 50, Diversity Max Clust. Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 50, Diversity Max Clust. ↑)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-50-DIVERSITY-PAIRWISE-TM: length 50, Diversity pairwise TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.53 ± 0.08 pairwise-tm score · lower Uncertainty: type: standard_deviation; value: 0.08 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-50-DIVERSITY-PAIRWISE-TM: length 50, Diversity pairwise TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 50, Diversity pairwise TM ↓)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-50-NOVELTY-MAX-TM: length 50, Novelty Max TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.66 ± 0.02 max-tm score · lower Uncertainty: type: standard_deviation; value: 0.02 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-50-NOVELTY-MAX-TM: length 50, Novelty Max TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 50, Novelty Max TM ↓)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-50-QUALITY-SCRMSD: length 50, Quality scRMSD Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	1.19 ± 1.27 scrmsd score · lower Uncertainty: type: standard_deviation; value: 1.27 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-50-QUALITY-SCRMSD: length 50, Quality scRMSD Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 50, Quality scRMSD ↓)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-50-QUALITY-SCTM: length 50, Quality scTM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.79 ± 0.14 sctm score · higher Uncertainty: type: standard_deviation; value: 0.14 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-50-QUALITY-SCTM: length 50, Quality scTM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 50, Quality scTM ↑)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-500-DIVERSITY-MAX-CLUST: length 500, Diversity Max Clust. Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	1 max-clust score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-500-DIVERSITY-MAX-CLUST: length 500, Diversity Max Clust. Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 500, Diversity Max Clust.↑)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-500-DIVERSITY-PAIRWISE-TM: length 500, Diversity pairwise TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.39 ± 0.05 pairwise-tm score · lower Uncertainty: type: standard_deviation; value: 0.05 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-500-DIVERSITY-PAIRWISE-TM: length 500, Diversity pairwise TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 500, Diversity pairwise TM ↓)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-500-NOVELTY-MAX-TM: length 500, Novelty Max TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.52 ± 0.01 max-tm score · lower Uncertainty: type: standard_deviation; value: 0.01 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-500-NOVELTY-MAX-TM: length 500, Novelty Max TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 500, Novelty Max TM ↓)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-500-QUALITY-SCRMSD: length 500, Quality scRMSD Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	13.20 ± 2.29 scrmsd score · lower Uncertainty: type: standard_deviation; value: 2.29 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-500-QUALITY-SCRMSD: length 500, Quality scRMSD Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 500, Quality scRMSD ↓)
Configuration: FoldFlow1(base)	Task: ProteinBench BB-LENGTH-500-QUALITY-SCTM: length 500, Quality scTM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.35 ± 0.05 sctm score · higher Uncertainty: type: standard_deviation; value: 0.05 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source FoldFlow1(base) on ProteinBench BB-LENGTH-500-QUALITY-SCTM: length 500, Quality scTM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(FoldFlow1(base)), column(length 500, Quality scTM ↑)

Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.

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