Models / genomics / hyenadna-tiny-1k-seqlen-hf / benchmarks

genomics/hyenadna-tiny-1k-seqlen-hf

Visibility: PUBLIC

Model card FilesBenchmarks

Group by

Genomic Benchmarks accuracy genomics/genomic-benchmarks-accuracy

Drawn from: Genomic_Benchmarks_demo_coding_vs_intergenomic_seqs, Genomic_Benchmarks_human_enhancers_cohn, Genomic_Benchmarks_human_nontata_promoters

atlas-full-v1

Metric

Value

95% CI

n

Rank

Best in catalogue

Source

Overlap

Accuracy (logistic probe, mean of 3 sets) ↑ higher is better · probe

By dataset: 3 levels

dataset	Value [95% CI]	n
Coding vs intergenomic sequences (demo)	0.843 [0.838, 0.847]	25000
Human enhancers (Cohn)	0.690 [0.679, 0.700]	6948
Human non-TATA promoters	0.790 [0.782, 0.799]	9034

0.774

[0.769, 0.779]

40982

5 / 5

0.821

reproduced

overlap

Train/test overlap declared by the evaluator: genomics/ucsc-hg38

Macro F1 (logistic probe, mean of 3 sets) ↑ higher is better · probe · secondary

By dataset: 3 levels

dataset	Value [95% CI]	n
Coding vs intergenomic sequences (demo)	0.843 [0.838, 0.847]	25000
Human enhancers (Cohn)	0.688 [0.678, 0.699]	6948
Human non-TATA promoters	0.790 [0.782, 0.798]	9034

0.773

[0.769, 0.778]

40982

—

0.821

reproduced

overlap

Train/test overlap declared by the evaluator: genomics/ucsc-hg38

Protein abundance from coding sequence (E. coli) rna-ml/coding-sequence-protein-abundance

atlas-n100-v1

Metric	Value	95% CI	n	Rank	Best in catalogue	Source	Overlap	Board
Spearman ρ (zero-shot pseudo-log-likelihood) ↑ higher is better · zero-shot	−0.069	[−0.281, 0.139]	100	11 / 11	0.552	reproduced	none declared	Board
Spearman ρ (ridge probe) ↑ higher is better · probe	0.486	[0.304, 0.626]	100	10 / 11	0.688	reproduced	none declared	Board
RMSE (ridge probe) ↓ lower is better · log10 ppm · probe	1.160	[1.006, 1.303]	100	10 / 11	0.973	reproduced	none declared	Board
Pearson r (ridge probe) ↑ higher is better · probe · secondary	0.461	[0.307, 0.596]	100	—	0.665	reproduced	none declared	Board
R² (ridge probe) ↑ higher is better · probe · secondary	0.162	[−0.044, 0.324]	100	—	0.411	reproduced	none declared	Board