Benchmark
Zero-shot RNA language model benchmark (Wang et al. 2026)
Standardised zero-shot evaluation of 21 RNA language models, with DNA language models as reference controls, on attention-based secondary structure prediction, embedding-based RNA classification and likelihood-based mutational fitness prediction.
Results are recorded on the linked protocols, tasks or configurations listed below. Their settings and evaluations are kept separate.
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.
Results on linked records
This benchmark has no results of its own in this release. 36 linked records have results. They are not assigned to the underlying benchmark: each record keeps its own settings and evaluations, and its scores are on its own page.
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, AUC (mean over assays) Protocol · part of this benchmark · 22 evaluations · 22 results
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, AUC (median over assays) Protocol · part of this benchmark · 22 evaluations · 22 results
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, MCC (mean over assays) Protocol · part of this benchmark · 22 evaluations · 22 results
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, MCC (median over assays) Protocol · part of this benchmark · 22 evaluations · 22 results
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, SR (mean over assays) Protocol · part of this benchmark · 22 evaluations · 22 results
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, SR (median over assays) Protocol · part of this benchmark · 22 evaluations · 22 results
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, AUC (mean over assays) Protocol · part of this benchmark · 35 evaluations · 35 results
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, AUC (median over assays) Protocol · part of this benchmark · 35 evaluations · 35 results
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Protocol · part of this benchmark · 35 evaluations · 35 results
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (median over assays) Protocol · part of this benchmark · 35 evaluations · 35 results
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, SR (mean over assays) Protocol · part of this benchmark · 35 evaluations · 35 results
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, SR (median over assays) Protocol · part of this benchmark · 35 evaluations · 35 results
- Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, F1 score (mean over structures) Protocol · part of this benchmark · 32 evaluations · 32 results
- Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, F1 score (median over structures) Protocol · part of this benchmark · 32 evaluations · 32 results
- Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, MCC (mean over structures) Protocol · part of this benchmark · 32 evaluations · 32 results
- Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, MCC (median over structures) Protocol · part of this benchmark · 32 evaluations · 32 results
- Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, F1 score (mean over structures) Protocol · part of this benchmark · 32 evaluations · 32 results
- Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, F1 score (median over structures) Protocol · part of this benchmark · 32 evaluations · 32 results
- Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, MCC (mean over structures) Protocol · part of this benchmark · 32 evaluations · 32 results
- Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, MCC (median over structures) Protocol · part of this benchmark · 32 evaluations · 32 results
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, 1 − OR (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 35 evaluations · 35 results
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, AUC (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 37 evaluations · 37 results
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 37 evaluations · 37 results
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, MCC (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 37 evaluations · 37 results
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, 1 − OR (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 35 evaluations · 35 results
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, AUC (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 37 evaluations · 37 results
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 37 evaluations · 37 results
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, MCC (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 37 evaluations · 37 results
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, 1 − OR (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 35 evaluations · 35 results
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, AUC (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 37 evaluations · 37 results
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, F1 (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 37 evaluations · 37 results
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, MCC (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 37 evaluations · 37 results
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, 1 − OR (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 35 evaluations · 35 results
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, AUC (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 37 evaluations · 37 results
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, F1 (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 37 evaluations · 37 results
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, MCC (mean over repeated random samplings of sequence pairs) Protocol · part of this benchmark · 37 evaluations · 37 results
Methods and evaluation design
Procedure, tasks and evaluated configurations
Baseline coverage
Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.
0 of 72 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.
Baseline status by linked protocol
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, AUC (mean over assays) · 0/2 roles measured
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, AUC (median over assays) · 0/2 roles measured
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, MCC (mean over assays) · 0/2 roles measured
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, MCC (median over assays) · 0/2 roles measured
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, SR (mean over assays) · 0/2 roles measured
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, SR (median over assays) · 0/2 roles measured
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, AUC (mean over assays) · 0/2 roles measured
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, AUC (median over assays) · 0/2 roles measured
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) · 0/2 roles measured
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (median over assays) · 0/2 roles measured
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, SR (mean over assays) · 0/2 roles measured
- Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, SR (median over assays) · 0/2 roles measured
- Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, F1 score (mean over structures) · 0/2 roles measured
- Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, F1 score (median over structures) · 0/2 roles measured
- Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, MCC (mean over structures) · 0/2 roles measured
- Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, MCC (median over structures) · 0/2 roles measured
- Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, F1 score (mean over structures) · 0/2 roles measured
- Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, F1 score (median over structures) · 0/2 roles measured
- Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, MCC (mean over structures) · 0/2 roles measured
- Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, MCC (median over structures) · 0/2 roles measured
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, 1 − OR (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, AUC (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, MCC (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, 1 − OR (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, AUC (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, MCC (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, 1 − OR (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, AUC (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, F1 (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
- Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, MCC (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, 1 − OR (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, AUC (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, F1 (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
- Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, MCC (mean over repeated random samplings of sequence pairs) · 0/2 roles measured
Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)
Coverage is derived from release 2026-10-22-1b7cf027e4f6. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.
Run instructions
No runnable recipe has been reviewed for this benchmark. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
Strengths, limitations and unresolved questions
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 2026-10-22-1b7cf027e4f6 · Record review: source checked
2 source records and release history
- Zero-shot benchmarking of RNA language models: Supplementary Information · Original source · bbag098_supplymentary_information_20260209.docx from the Europe PMC supplementary files archive for PMC12963973
- Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Original source · Briefings in Bioinformatics 2026, bbag098 (issue date 2026-03-01); PMC12963973 full-text XML
Technical metadata and extraction receipts
Stable ID: lit-rna-20261011-rnalm-zeroshot-benchmark-wang2026-zero-shot-rna-lm
- areas
- rna-transcriptomes
- contexts
- research
- entity level
- suite
- version
- Published 2026
- task
- Zero-shot RNA secondary structure, RNA classification and ncRNA fitness prediction
- scope note
- No fine-tuning. Secondary structure on TS (70 PDB structures) and TS-Hard (15) with a head-layer and threshold chosen on VL1 (40); classification of homologous versus non-homologous sequence pairs on RfamSample (561 Rfam families) and ArchiveII-Nr (1273 RNAs) from FFT or CLS embeddings; fitness on 31 RNAGym ncRNA deep mutational scanning assays (wild-type length <= 440 nt) with WT-LLR or PLL-D scores.
- source locator
- Main text Methods 'RNA secondary structure', 'RNA classification', 'RNA DMS assays'; Supplementary Tables 4-11
- limitations
- RNA-MSM is from the corresponding authors' group (Zhang et al.); the TS and VL1 sets come from the same group's earlier work (ref. 29).; Models are included per task only where their attention, embeddings or logits were available (Supplementary Table 3).
Related records
- part of: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, AUC (mean over assays)
- part of: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, AUC (median over assays)
- part of: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, MCC (mean over assays)
- part of: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, MCC (median over assays)
- part of: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, SR (mean over assays)
- part of: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, SR (median over assays)
- part of: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, AUC (mean over assays)
- part of: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, AUC (median over assays)
- part of: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays)
- part of: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (median over assays)
- part of: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, SR (mean over assays)
- part of: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, SR (median over assays)
- part of: Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, F1 score (mean over structures)
- part of: Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, F1 score (median over structures)
- part of: Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, MCC (mean over structures)
- part of: Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, MCC (median over structures)
- part of: Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, F1 score (mean over structures)
- part of: Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, F1 score (median over structures)
- part of: Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, MCC (mean over structures)
- part of: Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, MCC (median over structures)
- part of: Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, 1 − OR (mean over repeated random samplings of sequence pairs)
- part of: Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, AUC (mean over repeated random samplings of sequence pairs)
- part of: Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, F1 (mean over repeated random samplings of sequence pairs)
- part of: Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, MCC (mean over repeated random samplings of sequence pairs)
- part of: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, 1 − OR (mean over repeated random samplings of sequence pairs)
- part of: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, AUC (mean over repeated random samplings of sequence pairs)
- part of: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs)
- part of: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, MCC (mean over repeated random samplings of sequence pairs)
- part of: Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, 1 − OR (mean over repeated random samplings of sequence pairs)
- part of: Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, AUC (mean over repeated random samplings of sequence pairs)
- part of: Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, F1 (mean over repeated random samplings of sequence pairs)
- part of: Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, MCC (mean over repeated random samplings of sequence pairs)
- part of: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, 1 − OR (mean over repeated random samplings of sequence pairs)
- part of: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, AUC (mean over repeated random samplings of sequence pairs)
- part of: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, F1 (mean over repeated random samplings of sequence pairs)
- part of: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, MCC (mean over repeated random samplings of sequence pairs)