PFMBench MAT-PROD: Material production
Material production. Scored with Accuracy on Material production. Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.
Overview
Material production. Scored with Accuracy on Material production. 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 MAT-PROD: Material production
- ESM-2 on PFMBench MAT-PROD: Material production
- ESM-C on PFMBench MAT-PROD: Material production
- ESM3 on PFMBench MAT-PROD: Material production
- PGLM on PFMBench MAT-PROD: Material production
- ProstT5 on PFMBench MAT-PROD: Material production
- ProtGPT2 on PFMBench MAT-PROD: Material production
- ProTrek on PFMBench MAT-PROD: Material production
- ProtST on PFMBench MAT-PROD: Material production
- ProtT5 on PFMBench MAT-PROD: Material production
- SaProt on PFMBench MAT-PROD: Material production
- VenusPLM on PFMBench MAT-PROD: Material production
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 MAT-PROD: Material production
accuracy (fraction) · Higher values are better for this metric.
Every method PFMBench reports on Material production, scored with Accuracy on Material production.
- ESM-2 · Configuration · Author-reported evaluation0.81189
- VenusPLM · Configuration · Author-reported evaluation0.82018
- ESM-C · Configuration · Author-reported evaluation0.81009
- ProtGPT2 · Configuration · Author-reported evaluation0.76757
- PGLM · Configuration · Author-reported evaluation0.79495
- ProtT5 · Configuration · Author-reported evaluation0.80072
- DPLM · Configuration · Author-reported evaluation0.80144
- SaProt · Configuration · Author-reported evaluation0.81081
- ProstT5 · Configuration · Author-reported evaluation0 .81622
- ProtST · Configuration · Author-reported evaluation0.69261
- ESM3 · Configuration · Author-reported evaluation0.77514
- ProTrek · Configuration · Author-reported evaluation0.81477
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(Material production)Values, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| ESM-2 · Configuration | 0.81189 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-2 [ 35 ]), column(Mat.Pro.) |
| VenusPLM · Configuration | 0.82018 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(VenusPLM [ 59 ]), column(Mat.Pro.) |
| ESM-C · Configuration | 0.81009 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-C), column(Mat.Pro.) |
| ProtGPT2 · Configuration | 0.76757 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtGPT2 [ 12 ]), column(Mat.Pro.) |
| PGLM · Configuration | 0.79495 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(PGLM [ 5 ]), column(Mat.Pro.) |
| ProtT5 · Configuration | 0.80072 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtT5 [ 11 ]), column(Mat.Pro.) |
| DPLM · Configuration | 0.80144 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(DPLM [ 68 ]), column(Mat.Pro.) |
| SaProt · Configuration | 0.81081 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(SaProt [ 55 ]), column(Mat.Pro.) |
| ProstT5 · Configuration | 0 .81622 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProstT5 [ 21 ]), column(Mat.Pro.) |
| ProtST · Configuration | 0.69261 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtST [ 71 ]), column(Mat.Pro.) |
| ESM3 · Configuration | 0.77514 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM3 [ 18 ]), column(Mat.Pro.) |
| ProTrek · Configuration | 0.81477 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProTrek [ 56 ]), column(Mat.Pro.) |
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 MAT-PROD: Material production Configuration: DPLMTask: PFMBench MAT-PROD: Material productionDataset subset: Material production (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 | ||
| 0.80144 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(Mat.Pro.) Source checking is not independent reproduction. |
| ESM-2 on PFMBench MAT-PROD: Material production Configuration: ESM-2Task: PFMBench MAT-PROD: Material productionDataset subset: Material production (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 | ||
| 0.81189 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(Mat.Pro.) Source checking is not independent reproduction. |
| ESM-C on PFMBench MAT-PROD: Material production Configuration: ESM-CTask: PFMBench MAT-PROD: Material productionDataset subset: Material production (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 | ||
| 0.81009 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(Mat.Pro.) Source checking is not independent reproduction. |
| ESM3 on PFMBench MAT-PROD: Material production Configuration: ESM3Task: PFMBench MAT-PROD: Material productionDataset subset: Material production (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 | ||
| 0.77514 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(Mat.Pro.) Source checking is not independent reproduction. |
| PGLM on PFMBench MAT-PROD: Material production Configuration: PGLMTask: PFMBench MAT-PROD: Material productionDataset subset: Material production (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 | ||
| 0.79495 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(Mat.Pro.) Source checking is not independent reproduction. |
| ProstT5 on PFMBench MAT-PROD: Material production Configuration: ProstT5Task: PFMBench MAT-PROD: Material productionDataset subset: Material production (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 .81622 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(Mat.Pro.) Source checking is not independent reproduction. |
| ProtGPT2 on PFMBench MAT-PROD: Material production Configuration: ProtGPT2Task: PFMBench MAT-PROD: Material productionDataset subset: Material production (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 | ||
| 0.76757 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(Mat.Pro.) Source checking is not independent reproduction. |
| ProTrek on PFMBench MAT-PROD: Material production Configuration: ProTrekTask: PFMBench MAT-PROD: Material productionDataset subset: Material production (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 | ||
| 0.81477 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(Mat.Pro.) Source checking is not independent reproduction. |
| ProtST on PFMBench MAT-PROD: Material production Configuration: ProtSTTask: PFMBench MAT-PROD: Material productionDataset subset: Material production (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 | ||
| 0.69261 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(Mat.Pro.) Source checking is not independent reproduction. |
| ProtT5 on PFMBench MAT-PROD: Material production Configuration: ProtT5Task: PFMBench MAT-PROD: Material productionDataset subset: Material production (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 | ||
| 0.80072 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(Mat.Pro.) Source checking is not independent reproduction. |
| SaProt on PFMBench MAT-PROD: Material production Configuration: SaProtTask: PFMBench MAT-PROD: Material productionDataset subset: Material production (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 | ||
| 0.81081 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(Mat.Pro.) Source checking is not independent reproduction. |
| VenusPLM on PFMBench MAT-PROD: Material production Configuration: VenusPLMTask: PFMBench MAT-PROD: Material productionDataset subset: Material production (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 | ||
| 0.82018 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(Mat.Pro.) 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(Material production) 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-mat-prod 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-mat-prod
- areas
- proteins-complexes
- tasks
- Material production
- metric
- Accuracy
- metric direction
- higher
- dataset
- Material production
- protocol
- Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.
- source locator
- Table 1, row(Material production)
- comparison panels
- id: pfmbench-panel-mat-prod; title: PFMBench MAT-PROD: Material production; protocol id: pfmbench-task-mat-prod; dataset id: pfmbench-dataset-material-production; metric: accuracy; unit: fraction; direction: higher; result ids: pfmbench-result-esm-2-mat-prod-accuracy; pfmbench-result-venusplm-mat-prod-accuracy; pfmbench-result-esm-c-mat-prod-accuracy; pfmbench-result-protgpt2-mat-prod-accuracy; pfmbench-result-pglm-mat-prod-accuracy; pfmbench-result-prott5-mat-prod-accuracy; pfmbench-result-dplm-mat-prod-accuracy; pfmbench-result-saprot-mat-prod-accuracy; pfmbench-result-prostt5-mat-prod-accuracy; pfmbench-result-protst-mat-prod-accuracy; pfmbench-result-esm3-mat-prod-accuracy; pfmbench-result-protrek-mat-prod-accuracy; source ids: expansion-p3-pfmbench; source locator: Table 1, row(Material production); context: Every method PFMBench reports on Material production, scored with Accuracy on Material production.; 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 MAT-PROD: part of discovery-benchmark-pfmbench
- benchmark: DPLM on PFMBench MAT-PROD: Material production
- benchmark: ESM-2 on PFMBench MAT-PROD: Material production
- benchmark: ESM-C on PFMBench MAT-PROD: Material production
- benchmark: ESM3 on PFMBench MAT-PROD: Material production
- benchmark: PGLM on PFMBench MAT-PROD: Material production
- benchmark: ProstT5 on PFMBench MAT-PROD: Material production
- benchmark: ProtGPT2 on PFMBench MAT-PROD: Material production
- benchmark: ProTrek on PFMBench MAT-PROD: Material production
- benchmark: ProtST on PFMBench MAT-PROD: Material production
- benchmark: ProtT5 on PFMBench MAT-PROD: Material production
- benchmark: SaProt on PFMBench MAT-PROD: Material production
- benchmark: VenusPLM on PFMBench MAT-PROD: Material production