ESM C 6B (HyPLM report)
Runs the public ESM C 6B checkpoint in BF16 through the esm package to produce embeddings, probe features and masked-language-model scores.
Overview
An explanatory profile has not yet been reviewed for this record.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Model Capabilities & Hardware Requirements
Deployment facts recorded for ESM C 6B (HyPLM report). Fields the record does not carry are marked not recorded.
Evaluated Checkpoint: Public ESM C 6B checkpoint; no revision printed
Evaluations and results
11 evaluations · 11 results. Different protocols are not a single leaderboard.
Sorted by Accuracy (Three-state (Q3) per-residue secondary-structure accuracy on the CB513 test set) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.
| Tested configuration | Protocol and dataset | Accuracy (Three-state (Q3) per-residue secondary-structure accuracy on the CB513 test set) | Log loss (Mean negative log-likelihood of masked residues in nats on the report's held-out UniRef panel, identical masks and crops for every model) | Log loss (Mean negative log-likelihood of masked residues in nats on the report's recent-PDB panel, identical masks and crops for every model) | Perplexity (Masked-residue perplexity on the held-out UniRef panel: the exponential of the mean negative log-likelihood of masked residues under the model itself, with identical masks and crops for every model) | Perplexity (Masked-residue perplexity on the recent PDB chains: the exponential of the mean negative log-likelihood of masked residues under the model itself, with identical masks and crops for every model) | Spearman (Spearman correlation averaged over the 217 substitution assays of ProteinGym v1.3 with the benchmark's official aggregation, from masked-marginal zero-shot scores; per-assay values rounded to three decimals before aggregation) | Spearman (Spearman correlation averaged over the ProteinGym v1.3 substitution assays of selection type 'Activity', from masked-marginal zero-shot scores; only the authors' own runs (dagger rows of Table 5) are recorded) | Spearman (Spearman correlation averaged over the ProteinGym v1.3 substitution assays of selection type 'Binding', from masked-marginal zero-shot scores; only the authors' own runs (dagger rows of Table 5) are recorded) | Spearman (Spearman correlation averaged over the ProteinGym v1.3 substitution assays of selection type 'Expression', from masked-marginal zero-shot scores; only the authors' own runs (dagger rows of Table 5) are recorded) | Spearman (Spearman correlation averaged over the ProteinGym v1.3 substitution assays of selection type 'Organismal fitness', from masked-marginal zero-shot scores; only the authors' own runs (dagger rows of Table 5) are recorded) | Spearman (Spearman correlation averaged over the ProteinGym v1.3 substitution assays of selection type 'Stability', from masked-marginal zero-shot scores; only the authors' own runs (dagger rows of Table 5) are recorded) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ESM C 6B (HyPLM report)Evaluation | Secondary structure (CB513) (HyPLM report), Secondary structure prediction (TAPE) | 0.884 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| ESM C 6B (HyPLM report)Evaluation | NLL, held-out UniRef panel (HyPLM report), Held-out UniRef panel (479 proteins, HyPLM report) | Not reported | 1.41 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| ESM C 6B (HyPLM report)Evaluation | NLL, recent PDB chains (HyPLM report), Recent PDB chains (887, HyPLM report) | Not reported | Not reported | 1.05 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| ESM C 6B (HyPLM report)Evaluation | Masked-residue perplexity, held-out UniRef panel (HyPLM report), Held-out UniRef panel (479 proteins, HyPLM report) | Not reported | Not reported | Not reported | 4.11 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| ESM C 6B (HyPLM report)Evaluation | Masked-residue perplexity, recent PDB chains (HyPLM report), Recent PDB chains (887, HyPLM report) | Not reported | Not reported | Not reported | Not reported | 2.87 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| ESM C 6B (HyPLM report)Evaluation | ProteinGym zero-shot, activity assays (HyPLM report), ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 0.428 | Not reported | Not reported | Not reported | Not reported |
| ESM C 6B (HyPLM report)Evaluation | ProteinGym zero-shot, binding assays (HyPLM report), ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 0.309 | Not reported | Not reported | Not reported |
| ESM C 6B (HyPLM report)Evaluation | ProteinGym zero-shot, expression assays (HyPLM report), ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 0.417 | Not reported | Not reported |
| ESM C 6B (HyPLM report)Evaluation | ProteinGym zero-shot, organismal fitness assays (HyPLM report), ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 0.374 | Not reported |
| ESM C 6B (HyPLM report)Evaluation | ProteinGym zero-shot, stability assays (HyPLM report), ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 0.518 |
| ESM C 6B (HyPLM report)Evaluation | ProteinGym zero-shot (HyPLM report), ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | Not reported | Not reported | Not reported | Not reported | Not reported | 0.409 | Not reported | Not reported | Not reported | Not reported | Not reported |
All 11 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: ESM C 6B (HyPLM report) | Protocol: NLL, held-out UniRef panel (HyPLM report) Dataset: Held-out UniRef panel (479 proteins, HyPLM report) | 1.41 Log loss (Mean negative log-likelihood of masked residues in nats on the report's held-out UniRef panel, identical masks and crops for every model) unitless · lower Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM C 6B on nll-held-out-uniref (HyPLM report) hyplm-flash-20261106-protocol-nll-held-out-uniref Aggregation: Not reported HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 3, row 'ESM C 6B', column 'Held-out UniRef proteins, NLL' (page 6 of 13) |
| Configuration: ESM C 6B (HyPLM report) | Protocol: NLL, recent PDB chains (HyPLM report) Dataset: Recent PDB chains (887, HyPLM report) | 1.05 Log loss (Mean negative log-likelihood of masked residues in nats on the report's recent-PDB panel, identical masks and crops for every model) unitless · lower Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM C 6B on nll-recent-pdb (HyPLM report) hyplm-flash-20261106-protocol-nll-recent-pdb Aggregation: Not reported HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 3, row 'ESM C 6B', column 'Recent PDB chains, NLL' (page 6 of 13) |
| Configuration: ESM C 6B (HyPLM report) | Protocol: Masked-residue perplexity, held-out UniRef panel (HyPLM report) Dataset: Held-out UniRef panel (479 proteins, HyPLM report) | 4.11 Perplexity (Masked-residue perplexity on the held-out UniRef panel: the exponential of the mean negative log-likelihood of masked residues under the model itself, with identical masks and crops for every model) unitless · lower Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM C 6B on ppl-held-out-uniref (HyPLM report) hyplm-flash-20261106-protocol-ppl-held-out-uniref Aggregation: Not reported HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 3, row 'ESM C 6B', column 'Held-out UniRef proteins, PPL' (page 6 of 13) |
| Configuration: ESM C 6B (HyPLM report) | Protocol: Masked-residue perplexity, recent PDB chains (HyPLM report) Dataset: Recent PDB chains (887, HyPLM report) | 2.87 Perplexity (Masked-residue perplexity on the recent PDB chains: the exponential of the mean negative log-likelihood of masked residues under the model itself, with identical masks and crops for every model) unitless · lower Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM C 6B on ppl-recent-pdb (HyPLM report) hyplm-flash-20261106-protocol-ppl-recent-pdb Aggregation: Not reported HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 3, row 'ESM C 6B', column 'Recent PDB chains, PPL' (page 6 of 13) |
| Configuration: ESM C 6B (HyPLM report) | Protocol: ProteinGym zero-shot, activity assays (HyPLM report) Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.428 Spearman (Spearman correlation averaged over the ProteinGym v1.3 substitution assays of selection type 'Activity', from masked-marginal zero-shot scores; only the authors' own runs (dagger rows of Table 5) are recorded) unitless · higher Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM C 6B on proteingym-activity (HyPLM report) hyplm-flash-20261106-protocol-proteingym-activity Aggregation: Not reported HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 5, row 'ESM C 6B†', column 'Activity' (page 11 of 13) |
| Configuration: ESM C 6B (HyPLM report) | Protocol: ProteinGym zero-shot, binding assays (HyPLM report) Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.309 Spearman (Spearman correlation averaged over the ProteinGym v1.3 substitution assays of selection type 'Binding', from masked-marginal zero-shot scores; only the authors' own runs (dagger rows of Table 5) are recorded) unitless · higher Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM C 6B on proteingym-binding (HyPLM report) hyplm-flash-20261106-protocol-proteingym-binding Aggregation: Not reported HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 5, row 'ESM C 6B†', column 'Binding' (page 11 of 13) |
| Configuration: ESM C 6B (HyPLM report) | Protocol: ProteinGym zero-shot, expression assays (HyPLM report) Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.417 Spearman (Spearman correlation averaged over the ProteinGym v1.3 substitution assays of selection type 'Expression', from masked-marginal zero-shot scores; only the authors' own runs (dagger rows of Table 5) are recorded) unitless · higher Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM C 6B on proteingym-expression (HyPLM report) hyplm-flash-20261106-protocol-proteingym-expression Aggregation: Not reported HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 5, row 'ESM C 6B†', column 'Expression' (page 11 of 13) |
| Configuration: ESM C 6B (HyPLM report) | Protocol: ProteinGym zero-shot, organismal fitness assays (HyPLM report) Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.374 Spearman (Spearman correlation averaged over the ProteinGym v1.3 substitution assays of selection type 'Organismal fitness', from masked-marginal zero-shot scores; only the authors' own runs (dagger rows of Table 5) are recorded) unitless · higher Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM C 6B on proteingym-organismal-fitness (HyPLM report) hyplm-flash-20261106-protocol-proteingym-organismal-fitness Aggregation: Not reported HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 5, row 'ESM C 6B†', column 'Organismal fitness' (page 11 of 13) |
| Configuration: ESM C 6B (HyPLM report) | Protocol: ProteinGym zero-shot, stability assays (HyPLM report) Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.518 Spearman (Spearman correlation averaged over the ProteinGym v1.3 substitution assays of selection type 'Stability', from masked-marginal zero-shot scores; only the authors' own runs (dagger rows of Table 5) are recorded) unitless · higher Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM C 6B on proteingym-stability (HyPLM report) hyplm-flash-20261106-protocol-proteingym-stability Aggregation: Not reported HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 5, row 'ESM C 6B†', column 'Stability' (page 11 of 13) |
| Configuration: ESM C 6B (HyPLM report) | Protocol: ProteinGym zero-shot (HyPLM report) Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.409 Spearman (Spearman correlation averaged over the 217 substitution assays of ProteinGym v1.3 with the benchmark's official aggregation, from masked-marginal zero-shot scores; per-assay values rounded to three decimals before aggregation) unitless · higher Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM C 6B on proteingym-zero-shot (HyPLM report) hyplm-flash-20261106-protocol-proteingym-zero-shot Aggregation: Not reported HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 5, row 'ESM C 6B†', column 'Average' (page 11 of 13) |
| Configuration: ESM C 6B (HyPLM report) | Protocol: Secondary structure (CB513) (HyPLM report) Dataset: Secondary structure prediction (TAPE) | 0.884 Accuracy (Three-state (Q3) per-residue secondary-structure accuracy on the CB513 test set) fraction · higher Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM C 6B on secondary-structure-cb513 (HyPLM report) hyplm-flash-20261106-protocol-secondary-structure-cb513 Aggregation: Not reported HyPLM Technical Report (Hyra Team, 2026-10-12) · Section 4.2, sentence 'exceeded only by ESM3-open (0.896) and ESM C 6B (0.884)' (page 4 of 13) |
Source checking is not independent reproduction. Release 2026-11-21-adc15377fab2.
Use this configuration
How it works, versions and access
Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.
Evidence
Source checking verifies the cited claim or transcription. It does not establish 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
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-11-21-adc15377fab2 · Record review: source checked
1 source record and release history
- HyPLM Technical Report (Hyra Team, 2026-10-12) · Original source · Dated 2026-10-12 on page 1; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (13 pages)
Technical metadata and record identifiers
Technical metadata for this record is tracked under stable ID hyplm-flash-20261106-config-esm-c-6b.
Source locator: Appendix A 'Models' and 'Deviations'; Section 4
Related records
- configuration of: ESMC
- system: ESM C 6B on nll-held-out-uniref (HyPLM report)
- system: ESM C 6B on nll-recent-pdb (HyPLM report)
- system: ESM C 6B on ppl-held-out-uniref (HyPLM report)
- system: ESM C 6B on ppl-recent-pdb (HyPLM report)
- system: ESM C 6B on proteingym-activity (HyPLM report)
- system: ESM C 6B on proteingym-binding (HyPLM report)
- system: ESM C 6B on proteingym-expression (HyPLM report)
- system: ESM C 6B on proteingym-organismal-fitness (HyPLM report)
- system: ESM C 6B on proteingym-stability (HyPLM report)
- system: ESM C 6B on proteingym-zero-shot (HyPLM report)
- system: ESM C 6B on secondary-structure-cb513 (HyPLM report)
How to cite
ESM C 6B (HyPLM report). Rewire biological model benchmark database, release 2026-11-21-adc15377fab2. https://benchmarks.rewirebio.io/database/configuration/hyplm-flash-20261106-config-esm-c-6b/
Release 2026-11-21-adc15377fab2. Rankings and values change between releases, so keep the release id in the citation. Cite the original publication as well for any value you reuse: each result links its source.
The compilation and annotations made by Rewire in this release are offered under CC BY 4.0; values and text taken from cited sources stay under the terms of those sources and are not covered by this licence. Data licence