rewirebio.iobenchmarks
Contested result

Nucleotide Transformer and RNA-FM: NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction reverses the order

  • Low severity
  • Not yet reviewed
  • Ordering reversal
  • unknown

NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction ranks RNA-FM above Nucleotide Transformer in 22 of 25 comparisons; 2 of 2 other studies rank Nucleotide Transformer above RNA-FM.

An automatic lead, not a finding of error. The results below are shown as published, everywhere on the site, until a reviewer decides otherwise.

Which studies agree

4 papers rank Nucleotide Transformer above RNA-FM in 42 of their 81 comparisons and RNA-FM higher in 25; 14 are ties. NABench ranks RNA-FM above Nucleotide Transformer in 22 of its 27 comparisons and Nucleotide Transformer higher in 3; 2 are ties.

Papers grouped by which system they rank higher: Nucleotide Transformer or RNA-FMRank Nucleotide Transformer higher: Benchmarking pre-trained genomic…, mRNABench. Rank RNA-FM higher: NABench (disagrees). Mixed: Genome modelling and design across all…, RNAGym fitness leaderboard.Rank Nucleotide Transformer h…MixedRank RNA-FM higherBenchmarkingpre-trained genomic…Benchmarking pre-trained genomic language models for RNA sequence-related predictive applicationsmRNABenchmRNABench: A curated benchmark for mature mRNA property and function predictionGenome modelling anddesign across all…Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026)RNAGym fitnessleaderboardRNAGym fitness leaderboard (v0.1.1), leaderboard/fitness/README.mdNABenchNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction
  • Rank Nucleotide Transformer higher (2): Benchmarking pre-trained genomic…, mRNABench
  • Rank RNA-FM higher (1): NABench (disagrees)
  • Mixed (2): Genome modelling and design across all…, RNAGym fitness leaderboard

Each paper sits where at least two thirds of its comparisons point; Mixed means neither model reaches two thirds. The larger, outlined dot is the paper that disagrees.

Comparisons in which each paper scores Nucleotide Transformer or RNA-FM higherNABench (disagrees): Nucleotide Transformer higher in 3, RNA-FM higher in 22, 2 ties. Genome modelling and design across all…: Nucleotide Transformer higher in 24, RNA-FM higher in 23, 5 ties. Benchmarking pre-trained genomic…: Nucleotide Transformer higher in 7, RNA-FM higher in 0, 8 ties. mRNABench: Nucleotide Transformer higher in 9, RNA-FM higher in 0, 1 tie. RNAGym fitness leaderboard: Nucleotide Transformer higher in 2, RNA-FM higher in 2, 0 ties.Disagrees: NABenchNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction3 Nucleotide Transformer higher32 tie22 RNA-FM higher22Genome modelling and design across all…Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026)24 Nucleotide Transformer higher245 tie523 RNA-FM higher23Benchmarking pre-trained genomic…Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications7 Nucleotide Transformer higher78 tie8mRNABenchmRNABench: A curated benchmark for mature mRNA property and function prediction9 Nucleotide Transformer higher91 tie1RNAGym fitness leaderboardRNAGym fitness leaderboard (v0.1.1), leaderboard/fitness/README.md2 Nucleotide Transformer higher22 RNA-FM higher2
Nucleotide Transformer higherTieRNA-FM higherNumbers are counts of comparisons; the outlined bar is the paper that disagrees.
Comparisons in NABench (27)
ProtocolDatasetMetricNucleotide TransformerRNA-FMHigher
NABench FS-CORR-APTAMER: Fitness prediction on aptamer assays, few-shotNABench aptamer assays (NABench split)Spearman, unitless0.1660.248RNA-FM
NABench FS-CORR-ENHANCER: Fitness prediction on enhancer assays, few-shotNABench enhancer assays (NABench split)Spearman, unitless0.0530.009Nucleotide Transformer
NABench FS-CORR-MRNA: Fitness prediction on mRNA assays, few-shotNABench mRNA assays (NABench split)Spearman, unitless0.2560.318RNA-FM
NABench FS-CORR-PROMOTER: Fitness prediction on promoter assays, few-shotNABench promoter assays (NABench split)Spearman, unitless0.0710.159RNA-FM
NABench FS-CORR-RIBOZYME: Fitness prediction on ribozyme assays, few-shotNABench ribozyme assays (NABench split)Spearman, unitless0.1350.164RNA-FM
NABench RCV-CORR-APTAMER: Fitness prediction on aptamer assays, supervised, random cross validationNABench aptamer assays (NABench split)Spearman, unitless0.360.53RNA-FM
NABench RCV-CORR-ENHANCER: Fitness prediction on enhancer assays, supervised, random cross validationNABench enhancer assays (NABench split)Spearman, unitless0.210.256RNA-FM
NABench RCV-CORR-MRNA: Fitness prediction on mRNA assays, supervised, random cross validationNABench mRNA assays (NABench split)Spearman, unitless0.560.597RNA-FM
NABench RCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, random cross validationNABench promoter assays (NABench split)Spearman, unitless0.6360.582Nucleotide Transformer
NABench RCV-CORR-RIBOZYME: Fitness prediction on ribozyme assays, supervised, random cross validationNABench ribozyme assays (NABench split)Spearman, unitless0.4290.556RNA-FM
NABench RCV-CORR-TRNA: Fitness prediction on tRNA assays, supervised, random cross validationNABench tRNA assays (NABench split)Spearman, unitless0.4330.587RNA-FM
NABench SELEX-FS: Overall fitness prediction on NABench SELEX assays, Few-shot Spearman ρNABench SELEX assays (NABench split)Spearman, unitless0.5640.617RNA-FM
NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρNABench SELEX assays (NABench split)Spearman, unitless0.6260.685RNA-FM
NABench SELEX-ZS-AUC: Overall fitness prediction on NABench SELEX assays, Zero-shot AUCNABench SELEX assays (NABench split)AUROC, unitless0.5260.55RNA-FM
NABench SELEX-ZS-CORR: Overall fitness prediction on NABench SELEX assays, Zero-shot Spearman ρNABench SELEX assays (NABench split)Spearman, unitless0.0390.085RNA-FM
NABench SELEX-ZS-MCC: Overall fitness prediction on NABench SELEX assays, Zero-shot MCCNABench SELEX assays (NABench split)MCC, unitless0.0270.05RNA-FM
NABench SELEX-ZS-NDCG: Overall fitness prediction on NABench SELEX assays, Zero-shot NDCGNABench SELEX assays (NABench split)NDCG (cutoff not stated), unitless0.1950.194Tie
NABench ZS-AUC-APTAMER: Fitness prediction on aptamer assays, zero-shotNABench aptamer assays (NABench split)AUROC, unitless0.5240.578RNA-FM
NABench ZS-AUC-ENHANCER: Fitness prediction on enhancer assays, zero-shotNABench enhancer assays (NABench split)AUROC, unitless0.5280.529Tie
NABench ZS-AUC-MRNA: Fitness prediction on mRNA assays, zero-shotNABench mRNA assays (NABench split)AUROC, unitless0.5210.638RNA-FM
NABench ZS-AUC-PROMOTER: Fitness prediction on promoter assays, zero-shotNABench promoter assays (NABench split)AUROC, unitless0.5730.555Nucleotide Transformer
NABench ZS-AUC-RIBOZYME: Fitness prediction on ribozyme assays, zero-shotNABench ribozyme assays (NABench split)AUROC, unitless0.5370.559RNA-FM
NABench ZS-CORR-APTAMER: Fitness prediction on aptamer assays, zero-shotNABench aptamer assays (NABench split)Spearman, unitless0.0810.167RNA-FM
NABench ZS-CORR-ENHANCER: Fitness prediction on enhancer assays, zero-shotNABench enhancer assays (NABench split)Spearman, unitless0.0060.011RNA-FM
NABench ZS-CORR-MRNA: Fitness prediction on mRNA assays, zero-shotNABench mRNA assays (NABench split)Spearman, unitless0.0740.257RNA-FM
NABench ZS-CORR-PROMOTER: Fitness prediction on promoter assays, zero-shotNABench promoter assays (NABench split)Spearman, unitless0.0910.098RNA-FM
NABench ZS-CORR-RIBOZYME: Fitness prediction on ribozyme assays, zero-shotNABench ribozyme assays (NABench split)Spearman, unitless0.0640.103RNA-FM
Comparisons in Genome modelling and design across all… (52)
ProtocolDatasetMetricNucleotide TransformerRNA-FMHigher
Zero-shot BRCA1 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUPRC (zero-shot; BRCA1 'Both' (coding and noncoding) SNVs), unitless0.2850.206Nucleotide Transformer
Zero-shot BRCA1 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUROC (zero-shot; BRCA1 'Both' (coding and noncoding) SNVs), unitless0.550.493Nucleotide Transformer
Zero-shot BRCA1 coding SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUPRC (zero-shot; BRCA1 coding SNVs), unitless0.2120.21Tie
Zero-shot BRCA1 coding SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUROC (zero-shot; BRCA1 coding SNVs), unitless0.5090.497Nucleotide Transformer
Zero-shot BRCA1 intronic SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUPRC (zero-shot; BRCA1 intronic SNVs), unitless0.07250.0156Nucleotide Transformer
Zero-shot BRCA1 intronic SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUROC (zero-shot; BRCA1 intronic SNVs), unitless0.6880.389Nucleotide Transformer
Zero-shot BRCA1 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUPRC (zero-shot; BRCA1 noncoding SNVs), unitless0.4510.208Nucleotide Transformer
Zero-shot BRCA1 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUROC (zero-shot; BRCA1 noncoding SNVs), unitless0.6490.468Nucleotide Transformer
Zero-shot BRCA1 splice region SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUPRC (zero-shot; BRCA1 splice region SNVs), unitless0.6110.428Nucleotide Transformer
Zero-shot BRCA1 splice region SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUROC (zero-shot; BRCA1 splice region SNVs), unitless0.6340.487Nucleotide Transformer
Zero-shot BRCA2 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA2 SNVs with functional classifications, Huang et al. 2025 (Brixi et al. 2026)AUPRC (zero-shot; BRCA2 noncoding SNVs), unitless0.3610.312Nucleotide Transformer
Zero-shot BRCA2 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA2 SNVs with functional classifications, Huang et al. 2025 (Brixi et al. 2026)AUROC (zero-shot; BRCA2 noncoding SNVs), unitless0.5550.54Nucleotide Transformer
Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) non-SNVs classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) non-SNVs), unitless0.01570.0151Nucleotide Transformer
Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) non-SNVs classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) non-SNVs), unitless0.510.508Tie
Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs), unitless0.005450.00362Nucleotide Transformer
Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs), unitless0.520.536RNA-FM
Zero-shot ClinVar noncoding indels classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding indels), unitless0.1770.187RNA-FM
Zero-shot ClinVar noncoding indels classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding indels), unitless0.5050.513RNA-FM
Zero-shot ClinVar noncoding microsatellite variants classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding microsatellite variants), unitless0.03640.0131Nucleotide Transformer
Zero-shot ClinVar noncoding microsatellite variants classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding microsatellite variants), unitless0.7860.617Nucleotide Transformer
Zero-shot ClinVar noncoding non-SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding non-SNVs, far from splice site), unitless0.04430.0695RNA-FM
Zero-shot ClinVar noncoding non-SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding non-SNVs, far from splice site), unitless0.5180.51Nucleotide Transformer
Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding non-SNVs, highly conserved), unitless0.7320.746RNA-FM
Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding non-SNVs, highly conserved), unitless0.5030.517RNA-FM
Zero-shot ClinVar noncoding non-SNVs, intergenic classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding non-SNVs, intergenic), unitless0.7290.71Nucleotide Transformer
Zero-shot ClinVar noncoding non-SNVs, intergenic classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding non-SNVs, intergenic), unitless0.6250.625Tie
Zero-shot ClinVar noncoding non-SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding non-SNVs, moderately conserved), unitless0.1640.182RNA-FM
Zero-shot ClinVar noncoding non-SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding non-SNVs, moderately conserved), unitless0.5020.528RNA-FM
Zero-shot ClinVar noncoding non-SNVs, near splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding non-SNVs, near splice site), unitless0.50.519RNA-FM
Zero-shot ClinVar noncoding non-SNVs, near splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding non-SNVs, near splice site), unitless0.5190.514Tie
Zero-shot ClinVar noncoding non-SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding non-SNVs, not conserved), unitless0.04710.0695RNA-FM
Zero-shot ClinVar noncoding non-SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding non-SNVs, not conserved), unitless0.5840.502Nucleotide Transformer
Zero-shot ClinVar noncoding non-SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding non-SNVs, poorly conserved), unitless0.02430.0355RNA-FM
Zero-shot ClinVar noncoding non-SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding non-SNVs, poorly conserved), unitless0.5430.569RNA-FM
Zero-shot ClinVar noncoding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding SNVs, far from splice site), unitless0.01450.0158RNA-FM
Zero-shot ClinVar noncoding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding SNVs, far from splice site), unitless0.510.551RNA-FM
Zero-shot ClinVar noncoding SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding SNVs, highly conserved), unitless0.920.901Nucleotide Transformer
Zero-shot ClinVar noncoding SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding SNVs, highly conserved), unitless0.5520.52Nucleotide Transformer
Zero-shot ClinVar noncoding SNVs, intergenic classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding SNVs, intergenic), unitless0.2160.274RNA-FM
Zero-shot ClinVar noncoding SNVs, intergenic classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding SNVs, intergenic), unitless0.6550.519Nucleotide Transformer
Zero-shot ClinVar noncoding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding SNVs, moderately conserved), unitless0.07730.075Nucleotide Transformer
Zero-shot ClinVar noncoding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding SNVs, moderately conserved), unitless0.5230.52Tie
Zero-shot ClinVar noncoding SNVs, near splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding SNVs, near splice site), unitless0.8410.824Nucleotide Transformer
Zero-shot ClinVar noncoding SNVs, near splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding SNVs, near splice site), unitless0.5330.503Nucleotide Transformer
Zero-shot ClinVar noncoding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding SNVs, not conserved), unitless0.0110.0144RNA-FM
Zero-shot ClinVar noncoding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding SNVs, not conserved), unitless0.5160.601RNA-FM
Zero-shot ClinVar noncoding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding SNVs, poorly conserved), unitless0.0230.0309RNA-FM
Zero-shot ClinVar noncoding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding SNVs, poorly conserved), unitless0.5020.574RNA-FM
Zero-shot SpliceVarDB 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)SpliceVarDB experimentally validated splice variants (Brixi et al. 2026)AUPRC (zero-shot; SpliceVarDB 'Both' (coding and noncoding) SNVs), unitless0.6010.627RNA-FM
Zero-shot SpliceVarDB 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)SpliceVarDB experimentally validated splice variants (Brixi et al. 2026)AUROC (zero-shot; SpliceVarDB 'Both' (coding and noncoding) SNVs), unitless0.4910.531RNA-FM
Zero-shot SpliceVarDB exonic SNVs classification (Evo 2 paper, Supplementary Data 1)SpliceVarDB experimentally validated splice variants (Brixi et al. 2026)AUPRC (zero-shot; SpliceVarDB exonic SNVs), unitless0.3850.421RNA-FM
Zero-shot SpliceVarDB exonic SNVs classification (Evo 2 paper, Supplementary Data 1)SpliceVarDB experimentally validated splice variants (Brixi et al. 2026)AUROC (zero-shot; SpliceVarDB exonic SNVs), unitless0.490.56RNA-FM
Comparisons in Benchmarking pre-trained genomic… (15)
ProtocolDatasetMetricNucleotide TransformerRNA-FMHigher
GTEx tissue-specific splicing prediction, Splice acceptors and donors (You et al. 2026 Supplementary Table 5)GTEx-derived tissue-specific splice site usage dataset (You et al. 2026)AUPRC (GTEx splicing task, Splice acceptors and donors, averaged over categories), fraction0.8830.796Nucleotide Transformer
GTEx tissue-specific splicing prediction, Splice-15class (You et al. 2026 Supplementary Table 5)GTEx-derived tissue-specific splice site usage dataset (You et al. 2026)AUPRC (GTEx splicing task, Splice-15class, averaged over categories), fraction0.8650.677Nucleotide Transformer
GTEx tissue-specific splicing prediction, Splice-53class (You et al. 2026 Supplementary Table 5)GTEx-derived tissue-specific splice site usage dataset (You et al. 2026)AUPRC (GTEx splicing task, Splice-53class, averaged over categories), fraction0.8630.684Nucleotide Transformer
NT-splice-sites-acceptors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Nucleotide Transformer benchmark splice-site dataset, acceptorsAccuracy (NT-splice-sites-acceptors, fine-tuned), fraction0.990.98Nucleotide Transformer
NT-splice-sites-acceptors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Nucleotide Transformer benchmark splice-site dataset, acceptorsF1 (NT-splice-sites-acceptors, fine-tuned), fraction0.990.98Nucleotide Transformer
NT-splice-sites-acceptors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Nucleotide Transformer benchmark splice-site dataset, acceptorsPrecision (NT-splice-sites-acceptors, fine-tuned), fraction0.990.98Nucleotide Transformer
NT-splice-sites-acceptors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Nucleotide Transformer benchmark splice-site dataset, acceptorsRecall (NT-splice-sites-acceptors, fine-tuned), fraction0.990.98Nucleotide Transformer
NT-splice-sites-all splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Nucleotide Transformer benchmark splice-site dataset, all sitesAccuracy (NT-splice-sites-all, fine-tuned), fraction0.9840.981Tie
NT-splice-sites-all splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Nucleotide Transformer benchmark splice-site dataset, all sitesF1 (NT-splice-sites-all, fine-tuned), fraction0.9840.981Tie
NT-splice-sites-all splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Nucleotide Transformer benchmark splice-site dataset, all sitesPrecision (NT-splice-sites-all, fine-tuned), fraction0.9840.981Tie
NT-splice-sites-all splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Nucleotide Transformer benchmark splice-site dataset, all sitesRecall (NT-splice-sites-all, fine-tuned), fraction0.9840.981Tie
NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Nucleotide Transformer benchmark splice-site dataset, donorsAccuracy (NT-splice-sites-donors, fine-tuned), fraction0.9910.984Tie
NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Nucleotide Transformer benchmark splice-site dataset, donorsF1 (NT-splice-sites-donors, fine-tuned), fraction0.9910.984Tie
NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Nucleotide Transformer benchmark splice-site dataset, donorsPrecision (NT-splice-sites-donors, fine-tuned), fraction0.9910.984Tie
NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Nucleotide Transformer benchmark splice-site dataset, donorsRecall (NT-splice-sites-donors, fine-tuned), fraction0.9910.984Tie
Comparisons in mRNABench (10)
Comparisons in RNAGym fitness leaderboard (4)
ProtocolDatasetMetricNucleotide TransformerRNA-FMHigher
RNAGym v0.1.1 fitness, signed Spearman, AptamerRNAGym Aptamer DMS assays (2)Spearman (mean signed Spearman over the 2 Aptamer assays), unitless-0.08860.0004RNA-FM
RNAGym v0.1.1 fitness, signed Spearman, macro over 3 ncRNA categoriesRNAGym ncRNA DMS assays (31)Spearman (macro-mean over 3 ncRNA categories (equal category weights)), unitless0.120.101Nucleotide Transformer
RNAGym v0.1.1 fitness, signed Spearman, RibozymeRNAGym Ribozyme DMS assays (26)Spearman (mean signed Spearman over the 26 Ribozyme assays), unitless0.133-0.0303Nucleotide Transformer
RNAGym v0.1.1 fitness, signed Spearman, tRNARNAGym tRNA DMS assays (3)Spearman (mean signed Spearman over the 3 tRNA assays), unitless0.3170.334RNA-FM

What disagrees

Other studies
rank Nucleotide Transformer above RNA-FM in 16 of 16 comparisons
This study
ranks RNA-FM above Nucleotide Transformer in 22 of 25 comparisons
Compared
Nucleotide Transformer, RNA-FM
Study that disagrees
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction
Other studies
mRNABench: A curated benchmark for mature mRNA property and function prediction, Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications, You et al. 2026, Supplementary Information, mRNABench: A curated benchmark for mature mRNA property and function prediction
Rule
Ordering reversal; unknown
Model identity
Matched across studies partly through links not yet reviewed

The compared numbers

Each value links to its result record and source. Compare values within one protocol; the rule compares rankings, not raw values across protocols.

In the study that disagrees (50)
StudyToolProtocol or benchmarkMetricValue
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench FS-CORR-APTAMER: Fitness prediction on aptamer assays, few-shotSpearman0.166
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench FS-CORR-ENHANCER: Fitness prediction on enhancer assays, few-shotSpearman0.053
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench FS-CORR-MRNA: Fitness prediction on mRNA assays, few-shotSpearman0.256
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench FS-CORR-PROMOTER: Fitness prediction on promoter assays, few-shotSpearman0.071
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench FS-CORR-RIBOZYME: Fitness prediction on ribozyme assays, few-shotSpearman0.135
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench RCV-CORR-APTAMER: Fitness prediction on aptamer assays, supervised, random cross validationSpearman0.36
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench RCV-CORR-ENHANCER: Fitness prediction on enhancer assays, supervised, random cross validationSpearman0.21
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench RCV-CORR-MRNA: Fitness prediction on mRNA assays, supervised, random cross validationSpearman0.56
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench RCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, random cross validationSpearman0.636
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench RCV-CORR-RIBOZYME: Fitness prediction on ribozyme assays, supervised, random cross validationSpearman0.429
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench RCV-CORR-TRNA: Fitness prediction on tRNA assays, supervised, random cross validationSpearman0.433
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench SELEX-FS: Overall fitness prediction on NABench SELEX assays, Few-shot Spearman ρSpearman0.564
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρSpearman0.626
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench SELEX-ZS-AUC: Overall fitness prediction on NABench SELEX assays, Zero-shot AUCAUROC0.526
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench SELEX-ZS-CORR: Overall fitness prediction on NABench SELEX assays, Zero-shot Spearman ρSpearman0.039
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench SELEX-ZS-MCC: Overall fitness prediction on NABench SELEX assays, Zero-shot MCCMCC0.027
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench ZS-AUC-APTAMER: Fitness prediction on aptamer assays, zero-shotAUROC0.524
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench ZS-AUC-MRNA: Fitness prediction on mRNA assays, zero-shotAUROC0.521
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench ZS-AUC-PROMOTER: Fitness prediction on promoter assays, zero-shotAUROC0.573
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench ZS-AUC-RIBOZYME: Fitness prediction on ribozyme assays, zero-shotAUROC0.537
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench ZS-CORR-APTAMER: Fitness prediction on aptamer assays, zero-shotSpearman0.081
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench ZS-CORR-ENHANCER: Fitness prediction on enhancer assays, zero-shotSpearman0.006
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench ZS-CORR-MRNA: Fitness prediction on mRNA assays, zero-shotSpearman0.074
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench ZS-CORR-PROMOTER: Fitness prediction on promoter assays, zero-shotSpearman0.091
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionN.T.-v2-500mNABench ZS-CORR-RIBOZYME: Fitness prediction on ribozyme assays, zero-shotSpearman0.064
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench FS-CORR-APTAMER: Fitness prediction on aptamer assays, few-shotSpearman0.248
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench FS-CORR-ENHANCER: Fitness prediction on enhancer assays, few-shotSpearman0.009
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench FS-CORR-MRNA: Fitness prediction on mRNA assays, few-shotSpearman0.318
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench FS-CORR-PROMOTER: Fitness prediction on promoter assays, few-shotSpearman0.159
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench FS-CORR-RIBOZYME: Fitness prediction on ribozyme assays, few-shotSpearman0.164
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench RCV-CORR-APTAMER: Fitness prediction on aptamer assays, supervised, random cross validationSpearman0.53
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench RCV-CORR-ENHANCER: Fitness prediction on enhancer assays, supervised, random cross validationSpearman0.256
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench RCV-CORR-MRNA: Fitness prediction on mRNA assays, supervised, random cross validationSpearman0.597
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench RCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, random cross validationSpearman0.582
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench RCV-CORR-RIBOZYME: Fitness prediction on ribozyme assays, supervised, random cross validationSpearman0.556
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench RCV-CORR-TRNA: Fitness prediction on tRNA assays, supervised, random cross validationSpearman0.587
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench SELEX-FS: Overall fitness prediction on NABench SELEX assays, Few-shot Spearman ρSpearman0.617
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρSpearman0.685
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench SELEX-ZS-AUC: Overall fitness prediction on NABench SELEX assays, Zero-shot AUCAUROC0.55
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench SELEX-ZS-CORR: Overall fitness prediction on NABench SELEX assays, Zero-shot Spearman ρSpearman0.085
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench SELEX-ZS-MCC: Overall fitness prediction on NABench SELEX assays, Zero-shot MCCMCC0.05
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench ZS-AUC-APTAMER: Fitness prediction on aptamer assays, zero-shotAUROC0.578
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench ZS-AUC-MRNA: Fitness prediction on mRNA assays, zero-shotAUROC0.638
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench ZS-AUC-PROMOTER: Fitness prediction on promoter assays, zero-shotAUROC0.555
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench ZS-AUC-RIBOZYME: Fitness prediction on ribozyme assays, zero-shotAUROC0.559
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench ZS-CORR-APTAMER: Fitness prediction on aptamer assays, zero-shotSpearman0.167
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench ZS-CORR-ENHANCER: Fitness prediction on enhancer assays, zero-shotSpearman0.011
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench ZS-CORR-MRNA: Fitness prediction on mRNA assays, zero-shotSpearman0.257
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench ZS-CORR-PROMOTER: Fitness prediction on promoter assays, zero-shotSpearman0.098
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness PredictionRNA-FMNABench ZS-CORR-RIBOZYME: Fitness prediction on ribozyme assays, zero-shotSpearman0.103
In the other studies (32)
StudyToolProtocol or benchmarkMetricValue
Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary InformationNucleotideTransformer fine-tuned with an appended convolutional layer (You et al. 2026)NT-splice-sites-acceptors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Accuracy (NT-splice-sites-acceptors, fine-tuned)0.9899(0.0014)
Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary InformationNucleotideTransformer fine-tuned with an appended convolutional layer (You et al. 2026)NT-splice-sites-acceptors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)F1 (NT-splice-sites-acceptors, fine-tuned)0.9899(0.0014)
Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary InformationNucleotideTransformer fine-tuned with an appended convolutional layer (You et al. 2026)NT-splice-sites-acceptors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Precision (NT-splice-sites-acceptors, fine-tuned)0.9899(0.0014)
Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary InformationNucleotideTransformer fine-tuned with an appended convolutional layer (You et al. 2026)NT-splice-sites-acceptors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Recall (NT-splice-sites-acceptors, fine-tuned)0.9900(0.0014)
Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary InformationRNAFM fine-tuned with an appended convolutional layer (You et al. 2026)NT-splice-sites-acceptors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Accuracy (NT-splice-sites-acceptors, fine-tuned)0.9796(0.0007)
Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary InformationRNAFM fine-tuned with an appended convolutional layer (You et al. 2026)NT-splice-sites-acceptors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)F1 (NT-splice-sites-acceptors, fine-tuned)0.9796(0.0007)
Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary InformationRNAFM fine-tuned with an appended convolutional layer (You et al. 2026)NT-splice-sites-acceptors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Precision (NT-splice-sites-acceptors, fine-tuned)0.9796(0.0007)
Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary InformationRNAFM fine-tuned with an appended convolutional layer (You et al. 2026)NT-splice-sites-acceptors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)Recall (NT-splice-sites-acceptors, fine-tuned)0.9796(0.0007)
Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary InformationNucleotideTransformer fine-tuned with an appended convolutional layer (You et al. 2026)GTEx tissue-specific splicing prediction, Splice acceptors and donors (You et al. 2026 Supplementary Table 5)AUPRC (GTEx splicing task, Splice acceptors and donors, averaged over categories)0.8826(0.0036)
Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary InformationRNAFM fine-tuned with an appended convolutional layer (You et al. 2026)GTEx tissue-specific splicing prediction, Splice acceptors and donors (You et al. 2026 Supplementary Table 5)AUPRC (GTEx splicing task, Splice acceptors and donors, averaged over categories)0.7959(0.0011)
Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary InformationNucleotideTransformer fine-tuned with an appended convolutional layer (You et al. 2026)GTEx tissue-specific splicing prediction, Splice-15class (You et al. 2026 Supplementary Table 5)AUPRC (GTEx splicing task, Splice-15class, averaged over categories)0.8646(0.0032)
Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary InformationRNAFM fine-tuned with an appended convolutional layer (You et al. 2026)GTEx tissue-specific splicing prediction, Splice-15class (You et al. 2026 Supplementary Table 5)AUPRC (GTEx splicing task, Splice-15class, averaged over categories)0.6770(0.0033)
Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary InformationNucleotideTransformer fine-tuned with an appended convolutional layer (You et al. 2026)GTEx tissue-specific splicing prediction, Splice-53class (You et al. 2026 Supplementary Table 5)AUPRC (GTEx splicing task, Splice-53class, averaged over categories)0.8634(0.0004)
Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary InformationRNAFM fine-tuned with an appended convolutional layer (You et al. 2026)GTEx tissue-specific splicing prediction, Splice-53class (You et al. 2026 Supplementary Table 5)AUPRC (GTEx splicing task, Splice-53class, averaged over categories)0.6844(0.0035)
mRNABench: A curated benchmark for mature mRNA property and function predictionNTmRNABench ECLIP: eCLIP binding site predictionAUPRC40.5
mRNABench: A curated benchmark for mature mRNA property and function predictionNTmRNABench GO: Gene Ontology term predictionAUPRC36
mRNABench: A curated benchmark for mature mRNA property and function predictionNTmRNABench HL: mRNA half lifePearson0.57
mRNABench: A curated benchmark for mature mRNA property and function predictionNTmRNABench MRL-HL-PAIR: Paired mean ribosome load and half lifePearson0.57
mRNABench: A curated benchmark for mature mRNA property and function predictionNTmRNABench MRL-MPRA: Mean ribosome load on an MPRA libraryPearson0.6
mRNABench: A curated benchmark for mature mRNA property and function predictionNTmRNABench MRL: Mean ribosome loadPearson0.34
mRNABench: A curated benchmark for mature mRNA property and function predictionNTmRNABench MRNA-LOC-LR: mRNA localisation, long rangeAUPRC76.6
mRNABench: A curated benchmark for mature mRNA property and function predictionNTmRNABench MRNA-LOC-SR: mRNA localisation, short rangeAUPRC72.2
mRNABench: A curated benchmark for mature mRNA property and function predictionNTmRNABench VEP: Variant effect predictionAUPRC31.8
mRNABench: A curated benchmark for mature mRNA property and function predictionRNA-FMmRNABench ECLIP: eCLIP binding site predictionAUPRC35
mRNABench: A curated benchmark for mature mRNA property and function predictionRNA-FMmRNABench GO: Gene Ontology term predictionAUPRC32.2
mRNABench: A curated benchmark for mature mRNA property and function predictionRNA-FMmRNABench HL: mRNA half lifePearson0.47
mRNABench: A curated benchmark for mature mRNA property and function predictionRNA-FMmRNABench MRL-HL-PAIR: Paired mean ribosome load and half lifePearson0.49
mRNABench: A curated benchmark for mature mRNA property and function predictionRNA-FMmRNABench MRL-MPRA: Mean ribosome load on an MPRA libraryPearson0.49
mRNABench: A curated benchmark for mature mRNA property and function predictionRNA-FMmRNABench MRL: Mean ribosome loadPearson0.29
mRNABench: A curated benchmark for mature mRNA property and function predictionRNA-FMmRNABench MRNA-LOC-LR: mRNA localisation, long rangeAUPRC74.3
mRNABench: A curated benchmark for mature mRNA property and function predictionRNA-FMmRNABench MRNA-LOC-SR: mRNA localisation, short rangeAUPRC67
mRNABench: A curated benchmark for mature mRNA property and function predictionRNA-FMmRNABench VEP: Variant effect predictionAUPRC25.7

Follow-up

Current state: Not yet reviewed.

No one has reviewed this finding yet.

How to help resolve this

If you know why these studies disagree, for example a different population, metric or preprocessing step, or you have a corrected value, tell us through the contribution form. A reviewer checks every submission against its source before anything changes, and the step is added to the follow-up above.

Finding discrepancy-98fbe0ac6c21dbd2 · All contested results · How findings are made and followed up