rewire.it
Task

PFMBench SEC-STRUCT: Secondary structure

Secondary structure. Scored with Accuracy on Secondary structure. Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.

12 evaluations · 12 metric rows

Overview

Secondary structure. Scored with Accuracy on Secondary structure. Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.

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

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

Benchmarks

These source-backed links do not make different protocols or scores interchangeable.

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Run instructions

No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.

Published comparisons

Explore the results reported under one evaluation protocol. Each figure keeps its source, dataset and metric together; it is not a ranking across studies. The pooled view gathers every source table that reports the same metric and names what it does not hold constant.

PFMBench SEC-STRUCT: Secondary structure

accuracy (fraction) · Higher values are better for this metric.

Every method PFMBench reports on Secondary structure, scored with Accuracy on Secondary structure.

Evaluation protocol · Secondary structure (PFMBench split)

  1. ESM-2 · Configuration · Author-reported evaluation0.76375
  2. VenusPLM · Configuration · Author-reported evaluation0.71637
  3. ESM-C · Configuration · Author-reported evaluation0.76777
  4. ProtGPT2 · Configuration · Author-reported evaluation0.49371
  5. PGLM · Configuration · Author-reported evaluation0.72842
  6. ProtT5 · Configuration · Author-reported evaluation0.77978
  7. DPLM · Configuration · Author-reported evaluation0.75695
  8. SaProt · Configuration · Author-reported evaluation0.82389
  9. ProstT5 · Configuration · Author-reported evaluation0 .81397
  10. ProtST · Configuration · Author-reported evaluation0.68468
  11. ESM3 · Configuration · Author-reported evaluation0.81264
  12. ProTrek · Configuration · Author-reported evaluation0.77363

Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.

pfmbench primary benchmark evidence · Table 1, row(Secondary structure)
Values, uncertainty and evidence
accuracy: original source values
Tested entityPrinted valueUncertaintyEvidence
ESM-2 · Configuration0.76375 fractionNot reportedAuthor-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-2 [ 35 ]), column(Sec. Str.)
VenusPLM · Configuration0.71637 fractionNot reportedAuthor-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(VenusPLM [ 59 ]), column(Sec. Str.)
ESM-C · Configuration0.76777 fractionNot reportedAuthor-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-C), column(Sec. Str.)
ProtGPT2 · Configuration0.49371 fractionNot reportedAuthor-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtGPT2 [ 12 ]), column(Sec. Str.)
PGLM · Configuration0.72842 fractionNot reportedAuthor-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(PGLM [ 5 ]), column(Sec. Str.)
ProtT5 · Configuration0.77978 fractionNot reportedAuthor-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtT5 [ 11 ]), column(Sec. Str.)
DPLM · Configuration0.75695 fractionNot reportedAuthor-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(DPLM [ 68 ]), column(Sec. Str.)
SaProt · Configuration0.82389 fractionNot reportedAuthor-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(SaProt [ 55 ]), column(Sec. Str.)
ProstT5 · Configuration0 .81397 fractionNot reportedAuthor-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProstT5 [ 21 ]), column(Sec. Str.)
ProtST · Configuration0.68468 fractionNot reportedAuthor-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtST [ 71 ]), column(Sec. Str.)
ESM3 · Configuration0.81264 fractionNot reportedAuthor-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM3 [ 18 ]), column(Sec. Str.)
ProTrek · Configuration0.77363 fractionNot reportedAuthor-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProTrek [ 56 ]), column(Sec. Str.)
Scope and limitations
  • Author-reported numbers, source checked but not independently reproduced.
  • The metric differs by task, taken from Table 1, so these figures cannot be averaged into one score.
  • Table 3 scores come from adapter fine-tuning; the ProteinGym figure is zero-shot and is not comparable to them.

Source transcription and grouping reviewed by automated source review on 2026-09-18. These experiments were not independently reproduced by rewire.

Tested entities 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.

Results grouped by the exact reported evaluation
Metric and findingCoverage and uncertaintyEvidence
DPLM on PFMBench SEC-STRUCT: Secondary structure

Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.

Author-reported evaluation · Evaluation metadata: source checked

0.75695 accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedpfmbench primary benchmark evidence · Table 3, row(DPLM [ 68 ]), column(Sec. Str.)

Source checking is not independent reproduction.

ESM-2 on PFMBench SEC-STRUCT: Secondary structure

Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.

Author-reported evaluation · Evaluation metadata: source checked

0.76375 accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-2 [ 35 ]), column(Sec. Str.)

Source checking is not independent reproduction.

ESM-C on PFMBench SEC-STRUCT: Secondary structure

Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.

Author-reported evaluation · Evaluation metadata: source checked

0.76777 accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-C), column(Sec. Str.)

Source checking is not independent reproduction.

ESM3 on PFMBench SEC-STRUCT: Secondary structure

Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.

Author-reported evaluation · Evaluation metadata: source checked

0.81264 accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedpfmbench primary benchmark evidence · Table 3, row(ESM3 [ 18 ]), column(Sec. Str.)

Source checking is not independent reproduction.

PGLM on PFMBench SEC-STRUCT: Secondary structure

Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.

Author-reported evaluation · Evaluation metadata: source checked

0.72842 accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedpfmbench primary benchmark evidence · Table 3, row(PGLM [ 5 ]), column(Sec. Str.)

Source checking is not independent reproduction.

ProstT5 on PFMBench SEC-STRUCT: Secondary structure

Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.

Author-reported evaluation · Evaluation metadata: source checked

0 .81397 accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedpfmbench primary benchmark evidence · Table 3, row(ProstT5 [ 21 ]), column(Sec. Str.)

Source checking is not independent reproduction.

ProtGPT2 on PFMBench SEC-STRUCT: Secondary structure

Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.

Author-reported evaluation · Evaluation metadata: source checked

0.49371 accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedpfmbench primary benchmark evidence · Table 3, row(ProtGPT2 [ 12 ]), column(Sec. Str.)

Source checking is not independent reproduction.

ProTrek on PFMBench SEC-STRUCT: Secondary structure

Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.

Author-reported evaluation · Evaluation metadata: source checked

0.77363 accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedpfmbench primary benchmark evidence · Table 3, row(ProTrek [ 56 ]), column(Sec. Str.)

Source checking is not independent reproduction.

ProtST on PFMBench SEC-STRUCT: Secondary structure

Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.

Author-reported evaluation · Evaluation metadata: source checked

0.68468 accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedpfmbench primary benchmark evidence · Table 3, row(ProtST [ 71 ]), column(Sec. Str.)

Source checking is not independent reproduction.

ProtT5 on PFMBench SEC-STRUCT: Secondary structure

Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.

Author-reported evaluation · Evaluation metadata: source checked

0.77978 accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedpfmbench primary benchmark evidence · Table 3, row(ProtT5 [ 11 ]), column(Sec. Str.)

Source checking is not independent reproduction.

SaProt on PFMBench SEC-STRUCT: Secondary structure

Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.

Author-reported evaluation · Evaluation metadata: source checked

0.82389 accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedpfmbench primary benchmark evidence · Table 3, row(SaProt [ 55 ]), column(Sec. Str.)

Source checking is not independent reproduction.

VenusPLM on PFMBench SEC-STRUCT: Secondary structure

Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.

Author-reported evaluation · Evaluation metadata: source checked

0.71637 accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedpfmbench primary benchmark evidence · Table 3, row(VenusPLM [ 59 ]), column(Sec. Str.)

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-134cd1815de8
Property and statementOriginal source and locationReview and provenance
Relationship: part of

discovery-benchmark-pfmbench

Individual claims
pfmbench primary benchmark evidence

Original source ↗

Table 1, row(Secondary structure)

Version: 2506.14796v1
Retrieved: 2026-09-16T21:06:29.716004+00:00

source checked

automated source review · 2026-09-18

Audit details

Primary-source transcription with no human sign-off and no independent reproduction.

Field: links:part_of:discovery-benchmark-pfmbench

Claim: pfmbench-association-sec-struct

Source artifact SHA-256: 59c7bbb888e8e91f33c1e2cabfde062c32381d6ca727d23b6655c977aabf97a2

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Sources and history

Release 2026-09-17-134cd1815de8 · Record review: source checked

1 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: pfmbench-task-sec-struct

areas
proteins-complexes
tasks
Secondary structure
metric
Accuracy
metric direction
higher
dataset
Secondary structure
protocol
Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.
source locator
Table 1, row(Secondary structure)
comparison panels
id: pfmbench-panel-sec-struct; title: PFMBench SEC-STRUCT: Secondary structure; protocol id: pfmbench-task-sec-struct; dataset id: pfmbench-dataset-secondary-structure; metric: accuracy; unit: fraction; direction: higher; result ids: pfmbench-result-esm-2-sec-struct-accuracy; pfmbench-result-venusplm-sec-struct-accuracy; pfmbench-result-esm-c-sec-struct-accuracy; pfmbench-result-protgpt2-sec-struct-accuracy; pfmbench-result-pglm-sec-struct-accuracy; pfmbench-result-prott5-sec-struct-accuracy; pfmbench-result-dplm-sec-struct-accuracy; pfmbench-result-saprot-sec-struct-accuracy; pfmbench-result-prostt5-sec-struct-accuracy; pfmbench-result-protst-sec-struct-accuracy; pfmbench-result-esm3-sec-struct-accuracy; pfmbench-result-protrek-sec-struct-accuracy; source ids: expansion-p3-pfmbench; source locator: Table 1, row(Secondary structure); context: Every method PFMBench reports on Secondary structure, scored with Accuracy on Secondary structure.; caveats: Author-reported numbers, source checked but not independently reproduced.; The metric differs by task, taken from Table 1, so these figures cannot be averaged into one score.; Table 3 scores come from adapter fine-tuning; the ProteinGym figure is zero-shot and is not comparable to them.; review: method: automated_source_review; date: 2026-09-18
Related records

Suggest a correction