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.
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.
- DPLM on PFMBench SEC-STRUCT: Secondary structure
- ESM-2 on PFMBench SEC-STRUCT: Secondary structure
- ESM-C on PFMBench SEC-STRUCT: Secondary structure
- ESM3 on PFMBench SEC-STRUCT: Secondary structure
- PGLM on PFMBench SEC-STRUCT: Secondary structure
- ProstT5 on PFMBench SEC-STRUCT: Secondary structure
- ProtGPT2 on PFMBench SEC-STRUCT: Secondary structure
- ProTrek on PFMBench SEC-STRUCT: Secondary structure
- ProtST on PFMBench SEC-STRUCT: Secondary structure
- ProtT5 on PFMBench SEC-STRUCT: Secondary structure
- SaProt on PFMBench SEC-STRUCT: Secondary structure
- VenusPLM on PFMBench SEC-STRUCT: Secondary structure
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.
- ESM-2 · Configuration · Author-reported evaluation0.76375
- VenusPLM · Configuration · Author-reported evaluation0.71637
- ESM-C · Configuration · Author-reported evaluation0.76777
- ProtGPT2 · Configuration · Author-reported evaluation0.49371
- PGLM · Configuration · Author-reported evaluation0.72842
- ProtT5 · Configuration · Author-reported evaluation0.77978
- DPLM · Configuration · Author-reported evaluation0.75695
- SaProt · Configuration · Author-reported evaluation0.82389
- ProstT5 · Configuration · Author-reported evaluation0 .81397
- ProtST · Configuration · Author-reported evaluation0.68468
- ESM3 · Configuration · Author-reported evaluation0.81264
- 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
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| ESM-2 · Configuration | 0.76375 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-2 [ 35 ]), column(Sec. Str.) |
| VenusPLM · Configuration | 0.71637 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(VenusPLM [ 59 ]), column(Sec. Str.) |
| ESM-C · Configuration | 0.76777 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-C), column(Sec. Str.) |
| ProtGPT2 · Configuration | 0.49371 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtGPT2 [ 12 ]), column(Sec. Str.) |
| PGLM · Configuration | 0.72842 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(PGLM [ 5 ]), column(Sec. Str.) |
| ProtT5 · Configuration | 0.77978 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtT5 [ 11 ]), column(Sec. Str.) |
| DPLM · Configuration | 0.75695 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(DPLM [ 68 ]), column(Sec. Str.) |
| SaProt · Configuration | 0.82389 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(SaProt [ 55 ]), column(Sec. Str.) |
| ProstT5 · Configuration | 0 .81397 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProstT5 [ 21 ]), column(Sec. Str.) |
| ProtST · Configuration | 0.68468 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtST [ 71 ]), column(Sec. Str.) |
| ESM3 · Configuration | 0.81264 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM3 [ 18 ]), column(Sec. Str.) |
| ProTrek · Configuration | 0.77363 fraction | Not reported | Author-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.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| DPLM on PFMBench SEC-STRUCT: Secondary structure Configuration: DPLMTask: PFMBench SEC-STRUCT: Secondary structureDataset subset: Secondary structure (PFMBench split) 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 Configuration: ESM-2Task: PFMBench SEC-STRUCT: Secondary structureDataset subset: Secondary structure (PFMBench split) 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 Configuration: ESM-CTask: PFMBench SEC-STRUCT: Secondary structureDataset subset: Secondary structure (PFMBench split) 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 Configuration: ESM3Task: PFMBench SEC-STRUCT: Secondary structureDataset subset: Secondary structure (PFMBench split) 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 Configuration: PGLMTask: PFMBench SEC-STRUCT: Secondary structureDataset subset: Secondary structure (PFMBench split) 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 Configuration: ProstT5Task: PFMBench SEC-STRUCT: Secondary structureDataset subset: Secondary structure (PFMBench split) 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 Configuration: ProtGPT2Task: PFMBench SEC-STRUCT: Secondary structureDataset subset: Secondary structure (PFMBench split) 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 Configuration: ProTrekTask: PFMBench SEC-STRUCT: Secondary structureDataset subset: Secondary structure (PFMBench split) 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 Configuration: ProtSTTask: PFMBench SEC-STRUCT: Secondary structureDataset subset: Secondary structure (PFMBench split) 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 Configuration: ProtT5Task: PFMBench SEC-STRUCT: Secondary structureDataset subset: Secondary structure (PFMBench split) 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 Configuration: SaProtTask: PFMBench SEC-STRUCT: Secondary structureDataset subset: Secondary structure (PFMBench split) 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 Configuration: VenusPLMTask: PFMBench SEC-STRUCT: Secondary structureDataset subset: Secondary structure (PFMBench split) 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
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Relationship: part of discovery-benchmark-pfmbench Individual claims | pfmbench primary benchmark evidence Table 1, row(Secondary structure) Version: 2506.14796v1 | source checked automated source review · 2026-09-18 Audit detailsPrimary-source transcription with no human sign-off and no independent reproduction. Field: Claim: pfmbench-association-sec-struct Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
Release 2026-09-17-134cd1815de8 · Record review: source checked
1 source records and release history
- pfmbench primary benchmark evidence · Original source · 2506.14796v1
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
- part of: PFMBench
- subject: PFMBench SEC-STRUCT: part of discovery-benchmark-pfmbench
- benchmark: DPLM on PFMBench SEC-STRUCT: Secondary structure
- benchmark: ESM-2 on PFMBench SEC-STRUCT: Secondary structure
- benchmark: ESM-C on PFMBench SEC-STRUCT: Secondary structure
- benchmark: ESM3 on PFMBench SEC-STRUCT: Secondary structure
- benchmark: PGLM on PFMBench SEC-STRUCT: Secondary structure
- benchmark: ProstT5 on PFMBench SEC-STRUCT: Secondary structure
- benchmark: ProtGPT2 on PFMBench SEC-STRUCT: Secondary structure
- benchmark: ProTrek on PFMBench SEC-STRUCT: Secondary structure
- benchmark: ProtST on PFMBench SEC-STRUCT: Secondary structure
- benchmark: ProtT5 on PFMBench SEC-STRUCT: Secondary structure
- benchmark: SaProt on PFMBench SEC-STRUCT: Secondary structure
- benchmark: VenusPLM on PFMBench SEC-STRUCT: Secondary structure