PFMBench ANTI-RES: Antibiotic resistance
Antibiotic resistance. Scored with Accuracy on Antibiotic resistance. Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.
Overview
Antibiotic resistance. Scored with Accuracy on Antibiotic resistance. 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 ANTI-RES: Antibiotic resistance
- ESM-2 on PFMBench ANTI-RES: Antibiotic resistance
- ESM-C on PFMBench ANTI-RES: Antibiotic resistance
- ESM3 on PFMBench ANTI-RES: Antibiotic resistance
- PGLM on PFMBench ANTI-RES: Antibiotic resistance
- ProstT5 on PFMBench ANTI-RES: Antibiotic resistance
- ProtGPT2 on PFMBench ANTI-RES: Antibiotic resistance
- ProTrek on PFMBench ANTI-RES: Antibiotic resistance
- ProtST on PFMBench ANTI-RES: Antibiotic resistance
- ProtT5 on PFMBench ANTI-RES: Antibiotic resistance
- SaProt on PFMBench ANTI-RES: Antibiotic resistance
- VenusPLM on PFMBench ANTI-RES: Antibiotic resistance
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 ANTI-RES: Antibiotic resistance
accuracy (fraction) · Higher values are better for this metric.
Every method PFMBench reports on Antibiotic resistance, scored with Accuracy on Antibiotic resistance.
Evaluation protocol · Antibiotic resistance (PFMBench split)
- ESM-2 · Configuration · Author-reported evaluation0.63422
- VenusPLM · Configuration · Author-reported evaluation0.64602
- ESM-C · Configuration · Author-reported evaluation0.67257
- ProtGPT2 · Configuration · Author-reported evaluation0.68437
- PGLM · Configuration · Author-reported evaluation0.67257
- ProtT5 · Configuration · Author-reported evaluation0 .68732
- DPLM · Configuration · Author-reported evaluation0 .68732
- SaProt · Configuration · Author-reported evaluation0.65782
- ProstT5 · Configuration · Author-reported evaluation0.69027
- ProtST · Configuration · Author-reported evaluation0.63422
- ESM3 · Configuration · Author-reported evaluation0.58407
- ProTrek · Configuration · Author-reported evaluation0.59292
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(Antibiotic resistance)Values, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| ESM-2 · Configuration | 0.63422 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-2 [ 35 ]), column(Anti.Res.) |
| VenusPLM · Configuration | 0.64602 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(VenusPLM [ 59 ]), column(Anti.Res.) |
| ESM-C · Configuration | 0.67257 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-C), column(Anti.Res.) |
| ProtGPT2 · Configuration | 0.68437 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtGPT2 [ 12 ]), column(Anti.Res.) |
| PGLM · Configuration | 0.67257 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(PGLM [ 5 ]), column(Anti.Res.) |
| ProtT5 · Configuration | 0 .68732 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtT5 [ 11 ]), column(Anti.Res.) |
| DPLM · Configuration | 0 .68732 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(DPLM [ 68 ]), column(Anti.Res.) |
| SaProt · Configuration | 0.65782 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(SaProt [ 55 ]), column(Anti.Res.) |
| ProstT5 · Configuration | 0.69027 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProstT5 [ 21 ]), column(Anti.Res.) |
| ProtST · Configuration | 0.63422 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtST [ 71 ]), column(Anti.Res.) |
| ESM3 · Configuration | 0.58407 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM3 [ 18 ]), column(Anti.Res.) |
| ProTrek · Configuration | 0.59292 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProTrek [ 56 ]), column(Anti.Res.) |
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 ANTI-RES: Antibiotic resistance Configuration: DPLMTask: PFMBench ANTI-RES: Antibiotic resistanceDataset subset: Antibiotic resistance (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 .68732 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(Anti.Res.) Source checking is not independent reproduction. |
| ESM-2 on PFMBench ANTI-RES: Antibiotic resistance Configuration: ESM-2Task: PFMBench ANTI-RES: Antibiotic resistanceDataset subset: Antibiotic resistance (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 | ||
| 0.63422 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(Anti.Res.) Source checking is not independent reproduction. |
| ESM-C on PFMBench ANTI-RES: Antibiotic resistance Configuration: ESM-CTask: PFMBench ANTI-RES: Antibiotic resistanceDataset subset: Antibiotic resistance (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 | ||
| 0.67257 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(Anti.Res.) Source checking is not independent reproduction. |
| ESM3 on PFMBench ANTI-RES: Antibiotic resistance Configuration: ESM3Task: PFMBench ANTI-RES: Antibiotic resistanceDataset subset: Antibiotic resistance (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 | ||
| 0.58407 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(Anti.Res.) Source checking is not independent reproduction. |
| PGLM on PFMBench ANTI-RES: Antibiotic resistance Configuration: PGLMTask: PFMBench ANTI-RES: Antibiotic resistanceDataset subset: Antibiotic resistance (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 | ||
| 0.67257 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(Anti.Res.) Source checking is not independent reproduction. |
| ProstT5 on PFMBench ANTI-RES: Antibiotic resistance Configuration: ProstT5Task: PFMBench ANTI-RES: Antibiotic resistanceDataset subset: Antibiotic resistance (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 | ||
| 0.69027 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(Anti.Res.) Source checking is not independent reproduction. |
| ProtGPT2 on PFMBench ANTI-RES: Antibiotic resistance Configuration: ProtGPT2Task: PFMBench ANTI-RES: Antibiotic resistanceDataset subset: Antibiotic resistance (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 | ||
| 0.68437 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(Anti.Res.) Source checking is not independent reproduction. |
| ProTrek on PFMBench ANTI-RES: Antibiotic resistance Configuration: ProTrekTask: PFMBench ANTI-RES: Antibiotic resistanceDataset subset: Antibiotic resistance (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 | ||
| 0.59292 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(Anti.Res.) Source checking is not independent reproduction. |
| ProtST on PFMBench ANTI-RES: Antibiotic resistance Configuration: ProtSTTask: PFMBench ANTI-RES: Antibiotic resistanceDataset subset: Antibiotic resistance (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 | ||
| 0.63422 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(Anti.Res.) Source checking is not independent reproduction. |
| ProtT5 on PFMBench ANTI-RES: Antibiotic resistance Configuration: ProtT5Task: PFMBench ANTI-RES: Antibiotic resistanceDataset subset: Antibiotic resistance (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 .68732 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(Anti.Res.) Source checking is not independent reproduction. |
| SaProt on PFMBench ANTI-RES: Antibiotic resistance Configuration: SaProtTask: PFMBench ANTI-RES: Antibiotic resistanceDataset subset: Antibiotic resistance (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 | ||
| 0.65782 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(Anti.Res.) Source checking is not independent reproduction. |
| VenusPLM on PFMBench ANTI-RES: Antibiotic resistance Configuration: VenusPLMTask: PFMBench ANTI-RES: Antibiotic resistanceDataset subset: Antibiotic resistance (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 | ||
| 0.64602 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(Anti.Res.) 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(Antibiotic resistance) 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-anti-res 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-anti-res
- areas
- proteins-complexes
- tasks
- Antibiotic resistance
- metric
- Accuracy
- metric direction
- higher
- dataset
- Antibiotic resistance
- protocol
- Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.
- source locator
- Table 1, row(Antibiotic resistance)
- comparison panels
- id: pfmbench-panel-anti-res; title: PFMBench ANTI-RES: Antibiotic resistance; protocol id: pfmbench-task-anti-res; dataset id: pfmbench-dataset-antibiotic-resistance; metric: accuracy; unit: fraction; direction: higher; result ids: pfmbench-result-esm-2-anti-res-accuracy; pfmbench-result-venusplm-anti-res-accuracy; pfmbench-result-esm-c-anti-res-accuracy; pfmbench-result-protgpt2-anti-res-accuracy; pfmbench-result-pglm-anti-res-accuracy; pfmbench-result-prott5-anti-res-accuracy; pfmbench-result-dplm-anti-res-accuracy; pfmbench-result-saprot-anti-res-accuracy; pfmbench-result-prostt5-anti-res-accuracy; pfmbench-result-protst-anti-res-accuracy; pfmbench-result-esm3-anti-res-accuracy; pfmbench-result-protrek-anti-res-accuracy; source ids: expansion-p3-pfmbench; source locator: Table 1, row(Antibiotic resistance); context: Every method PFMBench reports on Antibiotic resistance, scored with Accuracy on Antibiotic resistance.; 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 ANTI-RES: part of discovery-benchmark-pfmbench
- benchmark: DPLM on PFMBench ANTI-RES: Antibiotic resistance
- benchmark: ESM-2 on PFMBench ANTI-RES: Antibiotic resistance
- benchmark: ESM-C on PFMBench ANTI-RES: Antibiotic resistance
- benchmark: ESM3 on PFMBench ANTI-RES: Antibiotic resistance
- benchmark: PGLM on PFMBench ANTI-RES: Antibiotic resistance
- benchmark: ProstT5 on PFMBench ANTI-RES: Antibiotic resistance
- benchmark: ProtGPT2 on PFMBench ANTI-RES: Antibiotic resistance
- benchmark: ProTrek on PFMBench ANTI-RES: Antibiotic resistance
- benchmark: ProtST on PFMBench ANTI-RES: Antibiotic resistance
- benchmark: ProtT5 on PFMBench ANTI-RES: Antibiotic resistance
- benchmark: SaProt on PFMBench ANTI-RES: Antibiotic resistance
- benchmark: VenusPLM on PFMBench ANTI-RES: Antibiotic resistance