Configuration

Native Seqs

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 · 12 evaluations · 12 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
Native Seqs on ProteinBench SEQ-LENGTH-100-DIVERSITY-MAX-CLUST: length 100, Diversity Max Clust. Configuration: Native SeqsTask: ProteinBench SEQ-LENGTH-100-DIVERSITY-MAX-CLUST: length 100, Diversity Max Clust.Dataset subset: Generated sequences at fixed lengths (ProteinBench split) Unconditional sequence generation at a fixed length. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked
0.75 max-clust Unit: score · Direction: higher	Uncertainty: Not reported Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 4, row(Native Seqs), column(length 100, Diversity Max Clust. ↑) Source checking is not independent reproduction.
Native Seqs on ProteinBench SEQ-LENGTH-100-DIVERSITY-PAIRWISE-TM: length 100, Diversity pairwise TM Configuration: Native SeqsTask: ProteinBench SEQ-LENGTH-100-DIVERSITY-PAIRWISE-TM: length 100, Diversity pairwise TMDataset subset: Generated sequences at fixed lengths (ProteinBench split) Unconditional sequence generation at a fixed length. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked
0.55 ± 0.19 pairwise-tm Unit: score · Direction: lower	Uncertainty: type: standard deviation; value: 0.19 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 4, row(Native Seqs), column(length 100, Diversity pairwise TM ↓) Source checking is not independent reproduction.
Native Seqs on ProteinBench SEQ-LENGTH-100-QUALITY-PLDDT: length 100, Quality pLDDT Configuration: Native SeqsTask: ProteinBench SEQ-LENGTH-100-QUALITY-PLDDT: length 100, Quality pLDDTDataset subset: Generated sequences at fixed lengths (ProteinBench split) Unconditional sequence generation at a fixed length. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked
68.46 ± 16.50 plddt Unit: score · Direction: higher	Uncertainty: type: standard deviation; value: 16.50 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 4, row(Native Seqs), column(length 100, Quality pLDDT ↑) Source checking is not independent reproduction.
Native Seqs on ProteinBench SEQ-LENGTH-200-DIVERSITY-MAX-CLUST: length 200, Diversity Max Clust. Configuration: Native SeqsTask: ProteinBench SEQ-LENGTH-200-DIVERSITY-MAX-CLUST: length 200, Diversity Max Clust.Dataset subset: Generated sequences at fixed lengths (ProteinBench split) Unconditional sequence generation at a fixed length. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked
0.78 max-clust Unit: score · Direction: higher	Uncertainty: Not reported Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 4, row(Native Seqs), column(length 200, Diversity Max Clust. ↑) Source checking is not independent reproduction.
Native Seqs on ProteinBench SEQ-LENGTH-200-DIVERSITY-PAIRWISE-TM: length 200, Diversity pairwise TM Configuration: Native SeqsTask: ProteinBench SEQ-LENGTH-200-DIVERSITY-PAIRWISE-TM: length 200, Diversity pairwise TMDataset subset: Generated sequences at fixed lengths (ProteinBench split) Unconditional sequence generation at a fixed length. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked
0.49 ± 0.10 pairwise-tm Unit: score · Direction: lower	Uncertainty: type: standard deviation; value: 0.10 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 4, row(Native Seqs), column(length 200, Diversity pairwise TM ↓) Source checking is not independent reproduction.
Native Seqs on ProteinBench SEQ-LENGTH-200-QUALITY-PLDDT: length 200, Quality pLDDT Configuration: Native SeqsTask: ProteinBench SEQ-LENGTH-200-QUALITY-PLDDT: length 200, Quality pLDDTDataset subset: Generated sequences at fixed lengths (ProteinBench split) Unconditional sequence generation at a fixed length. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked
61.91 ± 11.62 plddt Unit: score · Direction: higher	Uncertainty: type: standard deviation; value: 11.62 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 4, row(Native Seqs), column(length 200, Quality pLDDT↑) Source checking is not independent reproduction.
Native Seqs on ProteinBench SEQ-LENGTH-300-DIVERSITY-MAX-CLUST: length 300, Diversity Max Clust. Configuration: Native SeqsTask: ProteinBench SEQ-LENGTH-300-DIVERSITY-MAX-CLUST: length 300, Diversity Max Clust.Dataset subset: Generated sequences at fixed lengths (ProteinBench split) Unconditional sequence generation at a fixed length. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked
0.85 max-clust Unit: score · Direction: higher	Uncertainty: Not reported Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 4, row(Native Seqs), column(length 300, Diversity Max Clust. ↑) Source checking is not independent reproduction.
Native Seqs on ProteinBench SEQ-LENGTH-300-DIVERSITY-PAIRWISE-TM: length 300, Diversity pairwise TM Configuration: Native SeqsTask: ProteinBench SEQ-LENGTH-300-DIVERSITY-PAIRWISE-TM: length 300, Diversity pairwise TMDataset subset: Generated sequences at fixed lengths (ProteinBench split) Unconditional sequence generation at a fixed length. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked
0.51 ± 0.13 pairwise-tm Unit: score · Direction: lower	Uncertainty: type: standard deviation; value: 0.13 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 4, row(Native Seqs), column(length 300, Diversity pairwise TM ↓) Source checking is not independent reproduction.
Native Seqs on ProteinBench SEQ-LENGTH-300-QUALITY-PLDDT: length 300, Quality pLDDT Configuration: Native SeqsTask: ProteinBench SEQ-LENGTH-300-QUALITY-PLDDT: length 300, Quality pLDDTDataset subset: Generated sequences at fixed lengths (ProteinBench split) Unconditional sequence generation at a fixed length. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked
61.49 ± 14.47 plddt Unit: score · Direction: higher	Uncertainty: type: standard deviation; value: 14.47 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 4, row(Native Seqs), column(length 300, Quality pLDDT ↑) Source checking is not independent reproduction.
Native Seqs on ProteinBench SEQ-LENGTH-500-DIVERSITY-MAX-CLUST: length 500, Diversity Max Clust. Configuration: Native SeqsTask: ProteinBench SEQ-LENGTH-500-DIVERSITY-MAX-CLUST: length 500, Diversity Max Clust.Dataset subset: Generated sequences at fixed lengths (ProteinBench split) Unconditional sequence generation at a fixed length. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked
0.78 max-clust Unit: score · Direction: higher	Uncertainty: Not reported Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 4, row(Native Seqs), column(length 500, Diversity Max Clust. ↑) Source checking is not independent reproduction.
Native Seqs on ProteinBench SEQ-LENGTH-500-DIVERSITY-PAIRWISE-TM: length 500, Diversity pairwise TM Configuration: Native SeqsTask: ProteinBench SEQ-LENGTH-500-DIVERSITY-PAIRWISE-TM: length 500, Diversity pairwise TMDataset subset: Generated sequences at fixed lengths (ProteinBench split) Unconditional sequence generation at a fixed length. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked
0.51 ± 0.11 pairwise-tm Unit: score · Direction: lower	Uncertainty: type: standard deviation; value: 0.11 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 4, row(Native Seqs), column(length 500, Diversity pairwise TM ↓) Source checking is not independent reproduction.
Native Seqs on ProteinBench SEQ-LENGTH-500-QUALITY-PLDDT: length 500, Quality pLDDT Configuration: Native SeqsTask: ProteinBench SEQ-LENGTH-500-QUALITY-PLDDT: length 500, Quality pLDDTDataset subset: Generated sequences at fixed lengths (ProteinBench split) Unconditional sequence generation at a fixed length. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked
62.95 ± 12.60 plddt Unit: score · Direction: higher	Uncertainty: type: standard deviation; value: 12.60 Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 4, row(Native Seqs), column(length 500, Quality pLDDT↑) 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