Configuration: AIDO.DNA-300M (ViroBench classification) Protocol: ViroBench ALL viruses host classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 82.82 (1.15)% Macro F1 (ViroBench ALL viruses, host, G-Split)percent · higher
Uncertainty: SD 1.15
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source AIDO.DNA-300M on ViroBench ALL viruses host classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-host-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'AIDO.DNA-300M', column 'ALL viruses / Host / G-Split' (text-layer line 2569) Configuration: AIDO.DNA-300M (ViroBench classification) Protocol: ViroBench ALL viruses taxonomy classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 71.27 (2.63)% Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)percent · higher
Uncertainty: SD 2.63
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source AIDO.DNA-300M on ViroBench ALL viruses taxonomy classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-taxonomy-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'AIDO.DNA-300M', column 'ALL viruses / Taxonomy / G-Split' (text-layer line 2569) Configuration: AIDO.DNA-7B (ViroBench classification) Protocol: ViroBench ALL viruses host classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 80.65 (1.23)% Macro F1 (ViroBench ALL viruses, host, G-Split)percent · higher
Uncertainty: SD 1.23
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source AIDO.DNA-7B on ViroBench ALL viruses host classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-host-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'AIDO.DNA-7B', column 'ALL viruses / Host / G-Split' (text-layer line 2570) Configuration: AIDO.DNA-7B (ViroBench classification) Protocol: ViroBench ALL viruses taxonomy classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 69.87 (3.05)% Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)percent · higher
Uncertainty: SD 3.05
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source AIDO.DNA-7B on ViroBench ALL viruses taxonomy classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-taxonomy-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'AIDO.DNA-7B', column 'ALL viruses / Taxonomy / G-Split' (text-layer line 2570) Configuration: AIDO.RNA-1.6B (ViroBench classification) Protocol: ViroBench ALL viruses host classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 69.24 (1.81)% Macro F1 (ViroBench ALL viruses, host, G-Split)percent · higher
Uncertainty: SD 1.81
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source AIDO.RNA-1.6B on ViroBench ALL viruses host classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-host-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'AIDO.RNA-1.6B', column 'ALL viruses / Host / G-Split' (text-layer line 2607) Configuration: AIDO.RNA-1.6B (ViroBench classification) Protocol: ViroBench ALL viruses taxonomy classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 53.28 (7.02)% Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)percent · higher
Uncertainty: SD 7.02
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source AIDO.RNA-1.6B on ViroBench ALL viruses taxonomy classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-taxonomy-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'AIDO.RNA-1.6B', column 'ALL viruses / Taxonomy / G-Split' (text-layer line 2607) Configuration: AIDO.RNA-1.6B-CDS (ViroBench classification) Protocol: ViroBench ALL viruses host classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 77.74 (1.30)% Macro F1 (ViroBench ALL viruses, host, G-Split)percent · higher
Uncertainty: SD 1.30
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source AIDO.RNA-1.6B-CDS on ViroBench ALL viruses host classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-host-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'AIDO.RNA-1.6B-CDS', column 'ALL viruses / Host / G-Split' (text-layer line 2609) Configuration: AIDO.RNA-1.6B-CDS (ViroBench classification) Protocol: ViroBench ALL viruses taxonomy classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 60.84 (6.35)% Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)percent · higher
Uncertainty: SD 6.35
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source AIDO.RNA-1.6B-CDS on ViroBench ALL viruses taxonomy classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-taxonomy-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'AIDO.RNA-1.6B-CDS', column 'ALL viruses / Taxonomy / G-Split' (text-layer line 2609) Configuration: AIDO.RNA-650M (ViroBench classification) Protocol: ViroBench ALL viruses host classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 74.60 (1.86)% Macro F1 (ViroBench ALL viruses, host, G-Split)percent · higher
Uncertainty: SD 1.86
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source AIDO.RNA-650M on ViroBench ALL viruses host classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-host-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'AIDO.RNA-650M', column 'ALL viruses / Host / G-Split' (text-layer line 2606) Configuration: AIDO.RNA-650M (ViroBench classification) Protocol: ViroBench ALL viruses taxonomy classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 55.75 (7.12)% Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)percent · higher
Uncertainty: SD 7.12
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source AIDO.RNA-650M on ViroBench ALL viruses taxonomy classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-taxonomy-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'AIDO.RNA-650M', column 'ALL viruses / Taxonomy / G-Split' (text-layer line 2606) Configuration: AIDO.RNA-650M-CDS (ViroBench classification) Protocol: ViroBench ALL viruses host classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 79.29 (0.42)% Macro F1 (ViroBench ALL viruses, host, G-Split)percent · higher
Uncertainty: SD 0.42
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source AIDO.RNA-650M-CDS on ViroBench ALL viruses host classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-host-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'AIDO.RNA-650M-CDS', column 'ALL viruses / Host / G-Split' (text-layer line 2608) Configuration: AIDO.RNA-650M-CDS (ViroBench classification) Protocol: ViroBench ALL viruses taxonomy classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 65.25 (3.84)% Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)percent · higher
Uncertainty: SD 3.84
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source AIDO.RNA-650M-CDS on ViroBench ALL viruses taxonomy classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-taxonomy-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'AIDO.RNA-650M-CDS', column 'ALL viruses / Taxonomy / G-Split' (text-layer line 2608) Configuration: BiLSTM (ViroBench classification) Protocol: ViroBench ALL viruses host classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 84.40 (0.98)% Macro F1 (ViroBench ALL viruses, host, G-Split)percent · higher
Uncertainty: SD 0.98
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source BiLSTM on ViroBench ALL viruses host classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-host-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'BiLSTM', column 'ALL viruses / Host / G-Split' (text-layer line 2534) Configuration: BiLSTM (ViroBench classification) Protocol: ViroBench ALL viruses taxonomy classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 66.05 (1.89)% Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)percent · higher
Uncertainty: SD 1.89
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source BiLSTM on ViroBench ALL viruses taxonomy classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-taxonomy-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'BiLSTM', column 'ALL viruses / Taxonomy / G-Split' (text-layer line 2534) Configuration: BiRNA-BERT (ViroBench classification) Protocol: ViroBench ALL viruses host classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 64.71 (1.59)% Macro F1 (ViroBench ALL viruses, host, G-Split)percent · higher
Uncertainty: SD 1.59
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source BiRNA-BERT on ViroBench ALL viruses host classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-host-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'BiRNA-BERT', column 'ALL viruses / Host / G-Split' (text-layer line 2612) Configuration: BiRNA-BERT (ViroBench classification) Protocol: ViroBench ALL viruses taxonomy classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 33.34 (6.78)% Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)percent · higher
Uncertainty: SD 6.78
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source BiRNA-BERT on ViroBench ALL viruses taxonomy classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-taxonomy-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'BiRNA-BERT', column 'ALL viruses / Taxonomy / G-Split' (text-layer line 2612) Configuration: BLAST (ViroBench classification) Protocol: ViroBench ALL viruses host classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 92.50 (0.00)% Macro F1 (ViroBench ALL viruses, host, G-Split)percent · higher
Uncertainty: SD 0.00
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source BLAST on ViroBench ALL viruses host classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-host-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'BLAST', column 'ALL viruses / Host / G-Split' (text-layer line 2532) Configuration: BLAST (ViroBench classification) Protocol: ViroBench ALL viruses taxonomy classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 47.67 (0.00)% Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)percent · higher
Uncertainty: SD 0.00
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source BLAST on ViroBench ALL viruses taxonomy classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-taxonomy-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'BLAST', column 'ALL viruses / Taxonomy / G-Split' (text-layer line 2532) Configuration: Caduceus-ph (ViroBench classification) Protocol: ViroBench ALL viruses host classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 55.21 (1.34)% Macro F1 (ViroBench ALL viruses, host, G-Split)percent · higher
Uncertainty: SD 1.34
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source Caduceus-ph on ViroBench ALL viruses host classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-host-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'Caduceus-ph', column 'ALL viruses / Host / G-Split' (text-layer line 2571) Configuration: Caduceus-ph (ViroBench classification) Protocol: ViroBench ALL viruses taxonomy classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 30.87 (6.17)% Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)percent · higher
Uncertainty: SD 6.17
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source Caduceus-ph on ViroBench ALL viruses taxonomy classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-taxonomy-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'Caduceus-ph', column 'ALL viruses / Taxonomy / G-Split' (text-layer line 2571) Configuration: Caduceus-ps (ViroBench classification) Protocol: ViroBench ALL viruses host classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 54.57 (5.57)% Macro F1 (ViroBench ALL viruses, host, G-Split)percent · higher
Uncertainty: SD 5.57
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source Caduceus-ps on ViroBench ALL viruses host classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-host-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'Caduceus-ps', column 'ALL viruses / Host / G-Split' (text-layer line 2572) Configuration: Caduceus-ps (ViroBench classification) Protocol: ViroBench ALL viruses taxonomy classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 33.56 (6.61)% Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)percent · higher
Uncertainty: SD 6.61
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source Caduceus-ps on ViroBench ALL viruses taxonomy classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-taxonomy-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'Caduceus-ps', column 'ALL viruses / Taxonomy / G-Split' (text-layer line 2572) Configuration: CNN (ViroBench classification) Protocol: ViroBench ALL viruses host classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 69.29 (2.51)% Macro F1 (ViroBench ALL viruses, host, G-Split)percent · higher
Uncertainty: SD 2.51
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source CNN on ViroBench ALL viruses host classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-host-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'CNN', column 'ALL viruses / Host / G-Split' (text-layer line 2535) Configuration: CNN (ViroBench classification) Protocol: ViroBench ALL viruses taxonomy classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 34.72 (10.96)% Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)percent · higher
Uncertainty: SD 10.96
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source CNN on ViroBench ALL viruses taxonomy classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-taxonomy-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'CNN', column 'ALL viruses / Taxonomy / G-Split' (text-layer line 2535) Configuration: DNABERT-2-117M (ViroBench classification) Protocol: ViroBench ALL viruses host classification, G-Split, Macro-F1 Dataset: ViroBench ALL viruses, G-Split test set 49.48 (1.56)% Macro F1 (ViroBench ALL viruses, host, G-Split)percent · higher
Uncertainty: SD 1.56
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'
Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'
Methods, coverage and source DNABERT-2-117M on ViroBench ALL viruses host classification (G-Split)
lit-microbial-20261011-virobench-protocol-all-host-g-split
Aggregation: Not reported
ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'DNABERT-2-117M', column 'ALL viruses / Host / G-Split' (text-layer line 2582)