Protocol

Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays)

Zero-shot: pseudo-log-likelihood difference from token logits; MCC reported as mean over assays (Supplementary Table 11).

35 evaluations · 35 results

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.

35 recorded evaluations, 35 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

35 evaluations · 35 results. Different protocols are not a single leaderboard.

Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) · Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)

Sorted by MCC (PLL-D; mean over assays) (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	MCC (PLL-D; mean over assays)
EVO1.5 (8k_base) (zero-shot, Wang et al. 2026)Evaluation	0.132±0.088 (best in column)
RiNALMo (mega) (zero-shot, Wang et al. 2026)Evaluation	0.125±0.108
AIDO.RNA (650M) (zero-shot, Wang et al. 2026)Evaluation	0.122±0.107
AIDO.RNA (1.6B) (zero-shot, Wang et al. 2026)Evaluation	0.121±0.100
RiNALMo (giga) (zero-shot, Wang et al. 2026)Evaluation	0.116±0.108
DGRNA (zero-shot, Wang et al. 2026)Evaluation	0.111±0.083
Uni-RNA (L12) (zero-shot, Wang et al. 2026)Evaluation	0.111±0.100
Uni-RNA (L16) (zero-shot, Wang et al. 2026)Evaluation	0.107±0.105
Uni-RNA (L8) (zero-shot, Wang et al. 2026)Evaluation	0.107±0.084
GenerRNA (zero-shot, Wang et al. 2026)Evaluation	0.100±0.092
RiNALMo (micro) (zero-shot, Wang et al. 2026)Evaluation	0.098±0.098
RNA-FM (zero-shot, Wang et al. 2026)Evaluation	0.095±0.085
LAMAR (4k) (zero-shot, Wang et al. 2026)Evaluation	0.091±0.077
RFamLlama (Large) (zero-shot, Wang et al. 2026)Evaluation	0.090±0.060
LucaOne (D17.6M) (zero-shot, Wang et al. 2026)Evaluation	0.088±0.082
RFamLlama (Base) (zero-shot, Wang et al. 2026)Evaluation	0.087±0.064
PlantRNA-FM (zero-shot, Wang et al. 2026)Evaluation	0.083±0.075
NT (zero-shot, Wang et al. 2026)Evaluation	0.082±0.076
EVO1 (8k_base) (zero-shot, Wang et al. 2026)Evaluation	0.081±0.063
LAMAR (2k) (zero-shot, Wang et al. 2026)Evaluation	0.079±0.065
3UTRBERT (K4) (zero-shot, Wang et al. 2026)Evaluation	0.076±0.059
RNAErnie (zero-shot, Wang et al. 2026)Evaluation	0.076±0.069
LucaOne (G36.8M) (zero-shot, Wang et al. 2026)Evaluation	0.074±0.065
MP-RNA (zero-shot, Wang et al. 2026)Evaluation	0.072±0.068
SpliceBERT (zero-shot, Wang et al. 2026)Evaluation	0.071±0.059
UTR_LM (zero-shot, Wang et al. 2026)Evaluation	0.071±0.068
DNABERT-2 (zero-shot, Wang et al. 2026)Evaluation	0.069±0.052
RNABERT (zero-shot, Wang et al. 2026)Evaluation	0.065±0.063
3UTRBERT (K6) (zero-shot, Wang et al. 2026)Evaluation	0.064±0.050
DNABERT (k=6) (zero-shot, Wang et al. 2026)Evaluation	0.064±0.059
3UTRBERT (K5) (zero-shot, Wang et al. 2026)Evaluation	0.063±0.047
LucaOne (D36.0M) (zero-shot, Wang et al. 2026)Evaluation	0.062±0.052
ProtRNA (zero-shot, Wang et al. 2026)Evaluation	0.059±0.042
DNABERT (k=3) (zero-shot, Wang et al. 2026)Evaluation	0.054±0.038
3UTRBERT (K3) (zero-shot, Wang et al. 2026)Evaluation	0.053±0.055

All 35 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: 3UTRBERT (K3) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.053±0.055 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.055 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source 3UTRBERT (K3) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row '3UTRBERT (K3)', column 'MCC' (Mean ± Std)
Configuration: 3UTRBERT (K4) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.076±0.059 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.059 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source 3UTRBERT (K4) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row '3UTRBERT (K4)', column 'MCC' (Mean ± Std)
Configuration: 3UTRBERT (K5) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.063±0.047 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.047 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source 3UTRBERT (K5) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row '3UTRBERT (K5)', column 'MCC' (Mean ± Std)
Configuration: 3UTRBERT (K6) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.064±0.050 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.050 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source 3UTRBERT (K6) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row '3UTRBERT (K6)', column 'MCC' (Mean ± Std)
Configuration: AIDO.RNA (1.6B) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.121±0.100 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.100 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AIDO.RNA (1.6B) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'AIDO.RNA (1.6B)', column 'MCC' (Mean ± Std)
Configuration: AIDO.RNA (650M) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.122±0.107 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.107 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AIDO.RNA (650M) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'AIDO.RNA (650M)', column 'MCC' (Mean ± Std)
Configuration: DGRNA (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.111±0.083 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.083 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DGRNA zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'DGRNA', column 'MCC' (Mean ± Std)
Configuration: DNABERT-2 (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.069±0.052 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.052 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT-2 zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'DNABERT-2', column 'MCC' (Mean ± Std)
Configuration: DNABERT (k=3) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.054±0.038 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.038 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT (k=3) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'DNABERT (k=3)', column 'MCC' (Mean ± Std)
Configuration: DNABERT (k=6) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.064±0.059 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.059 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT (k=6) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'DNABERT (k=6)', column 'MCC' (Mean ± Std)
Configuration: EVO1.5 (8k_base) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.132±0.088 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.088 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source EVO1.5 (8k_base) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'EVO1.5 (8k_base)', column 'MCC' (Mean ± Std)
Configuration: EVO1 (8k_base) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.081±0.063 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.063 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source EVO1 (8k_base) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'EVO1 (8k_base)', column 'MCC' (Mean ± Std)
Configuration: GenerRNA (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.100±0.092 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.092 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GenerRNA zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'GenerRNA', column 'MCC' (Mean ± Std)
Configuration: LAMAR (2k) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.079±0.065 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.065 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LAMAR (2k) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'LAMAR (2k)', column 'MCC' (Mean ± Std)
Configuration: LAMAR (4k) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.091±0.077 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.077 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LAMAR (4k) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'LAMAR (4k)', column 'MCC' (Mean ± Std)
Configuration: LucaOne (D17.6M) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.088±0.082 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.082 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LucaOne (D17.6M) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'LucaOne (D17.6M)', column 'MCC' (Mean ± Std)
Configuration: LucaOne (D36.0M) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.062±0.052 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.052 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LucaOne (D36.0M) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'LucaOne (D36.0M)', column 'MCC' (Mean ± Std)
Configuration: LucaOne (G36.8M) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.074±0.065 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.065 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LucaOne (G36.8M) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'LucaOne (G36.8M)', column 'MCC' (Mean ± Std)
Configuration: MP-RNA (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.072±0.068 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.068 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MP-RNA zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'MP-RNA', column 'MCC' (Mean ± Std)
Configuration: NT (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.082±0.076 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.076 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'NT', column 'MCC' (Mean ± Std)
Configuration: PlantRNA-FM (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.083±0.075 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.075 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PlantRNA-FM zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'PlantRNA-FM', column 'MCC' (Mean ± Std)
Configuration: ProtRNA (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.059±0.042 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.042 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ProtRNA zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'ProtRNA', column 'MCC' (Mean ± Std)
Configuration: RFamLlama (Base) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.087±0.064 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.064 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source RFamLlama (Base) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'RFamLlama (Base)', column 'MCC' (Mean ± Std)
Configuration: RFamLlama (Large) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.090±0.060 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.060 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source RFamLlama (Large) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'RFamLlama (Large)', column 'MCC' (Mean ± Std)
Configuration: RiNALMo (giga) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) Dataset: RNAGym ncRNA DMS assays (31 assays) (Wang et al. 2026)	0.116±0.108 MCC (PLL-D; mean over assays) unitless · higher Uncertainty: SD 0.108 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source RiNALMo (giga) zero-shot fitness on RNAGym ncRNA DMS assays (31 assays) (PLL-D, MCC, mean) lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 11, row 'RiNALMo (giga)', column 'MCC' (Mean ± Std)

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

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 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

External evaluations: 35

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Protocol-valid seeded random ranking; no fitting on assay labels

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Established label-free reference with explicitly permitted sequence/MSA inputs

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

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 protocol. 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

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

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

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-rna-20261011-rnalm-zeroshot-protocol-t11-mcc-mean

areas: rna-transcriptomes
contexts: research
protocol: Zero-shot: pseudo-log-likelihood difference from token logits. Metric MCC, mean over assays.
version: Wang et al. 2026
metric: matthews-correlation-coefficient
metric direction: higher
unit: unitless
metric qualifier: PLL-D; mean over assays
source locator: Supplementary Table 11 caption and column 'MCC'; main text Methods
limitations: Zero-shot only; no fine-tuning or task head.; Binarisation for MCC, F1 and AUC in the fitness task is not described in the main text or supplement.

Related records

Suggest a correction