2026-08-06 snapshot

47 benchmarks, with the protocol attached.

Find public numeric results or an auditable gap. Result rows are not counts of independent experiments.

47 / 47 benchmarks

B01Numeric results available

Genome Understanding Evaluation (GUE)

28 datasets/tasks in the native packaging; mapped here to five task families.

Tier BGenomic element classificationPromoter recognitionEnhancer recognitionTF binding-site prediction
Protocols
1
Results
10
Works
1
B02Numeric results available

Nucleotide Transformer benchmark

Eighteen downstream tasks are benchmark instances, not eighteen unique task families.

Tier BGenomic element classificationPromoter recognitionEnhancer recognitionTF binding-site prediction
Protocols
67
Results
821
Works
1
B03Numeric results available

BEND

Human-genome tasks with biologically aligned splits; inspect each track for leakage controls.

Tier BTF binding-site predictionChromatin accessibility predictionSplice-site predictionSequence-to-gene-expression prediction
Protocols
7
Results
105
Works
1
B04No public numeric result

DART-Eval

Regulatory DNA evaluation across zero-shot, probing and fine-tuning regimes.

Tier BTF binding-site predictionChromatin accessibility predictionSequence motif discoveryEnhancer activity prediction
Protocols
0
Results
0
Works
0
B05No public numeric result

GenBench

Framework and dataset suite; native task count follows current release documentation.

Tier BGenomic element classificationPromoter recognitionEnhancer recognitionSplice-site prediction
Protocols
0
Results
0
Works
0
B06No public numeric result

Genomic Benchmarks

Widely reused classification datasets; simple random-style splits can inflate biological generalization.

Tier CGenomic element classificationPromoter recognitionEnhancer recognition
Protocols
0
Results
0
Works
0
B07Numeric results available

DNALongBench

Long-range genomic tasks; exact sequence length and cell-type packaging vary by track.

Tier BChromatin accessibility predictionHistone-mark prediction3D genome contact predictionSequence-to-gene-expression prediction
Protocols
2
Results
6
Works
1
B09Numeric results available

BEACON

Thirteen native tasks; some reuse OpenVaccine, Optimus and CRISPR datasets.

Tier BRNA secondary-structure base-pair predictionRNA contact or distance-map predictionRNA probing-reactivity predictionSplice-site prediction
Protocols
13
Results
221
Works
1
B10Numeric results available

RNA-Scope

Board is public; DeepASmRNA and DeeReCT-PolyA/PAS are exposed as distinct tracks; verify exact release and frozen splits before comparative claims.

Tier BncRNA family classificationRNA modification-site predictionRNA subcellular localizationRNA secondary-structure base-pair prediction
Protocols
79
Results
2,093
Works
1
B11Numeric results available

RNAGym

Three core tasks plus a task-family view of the ribozyme-assay subset; the subset track is separated from the aggregate DMS-effect track.

Tier BRNA DMS effect predictionRNA secondary-structure base-pair predictionRNA 3D coordinate predictionRibozyme activity prediction
Protocols
2
Results
7
Works
2
B12No public numeric result

Benchmarking pre-trained gLMs for RNA sequence applications

Four native study processes; the GTEx tissue-specific splicing evaluation is additionally mapped to the alternative-splicing task family without changing the native-task count.

Tier CncRNA family classificationRNA modification-site predictionSplice-site predictionTranslation efficiency or ribosome-load prediction
Protocols
0
Results
0
Works
0
B13Numeric results available

RNA-Puzzles

Blind, rolling CASP-like assessment; puzzle count and target composition change by round.

Tier ARNA 3D coordinate predictionRNA 3D model quality assessmentAll-atom nucleic-acid complex structure prediction
Protocols
50
Results
5,657
Works
1
B14Numeric results available

CASP15 RNA

First dedicated CASP RNA season; preserve target/category filters.

Tier ARNA 3D coordinate predictionRNA 3D model quality assessmentAll-atom nucleic-acid complex structure prediction
Protocols
9
Results
312
Works
1
B15Numeric results available

CASP16 RNA/DNA

Includes RNA and nucleic-acid-containing targets; 42-target figure is reported for the richer RNA set in later assessment work.

Tier ARNA 3D coordinate predictionRNA 3D model quality assessmentAll-atom nucleic-acid complex structure predictionNucleic-acid–protein interface or docking
Protocols
2
Results
258
Works
1
B17Numeric results available

OpenVaccine

Same raw competition data is repackaged by several RNA benchmark suites.

Tier ARNA degradation and vaccine-stability prediction
Protocols
9
Results
15
Works
1
B18Numeric results available

Eterna100

Community-standard inverse-folding set; protocol differences across folding engines reduce comparability.

Tier CRNA secondary-structure inverse folding
Protocols
1
Results
7
Works
1
B19No public numeric result

NC-Bench

Focused benchmark for non-canonical RNA base pairs.

Tier BRNA non-canonical base-pair prediction
Protocols
0
Results
0
Works
0
B20No public numeric result

CAGI molecular/functional challenges

Only molecular and functional variant challenges are in scope; phenotype-from-exome and patient-level tasks are excluded.

Tier ARegulatory variant-effect predictionExpression variant-effect predictionSplicing variant-effect predictionMolecular functional or pathogenic variant interpretation
Protocols
0
Results
0
Works
0
B21No public numeric result

DREAM5 TF–DNA motif recognition

Historic blinded TF–DNA specificity assessment.

Tier ATF–DNA binding specificity
Protocols
0
Results
0
Works
0
B22Restricted

ENCODE-DREAM in vivo TF binding

Held-out cell types and chromosomes improve realism, but access is through Synapse.

Tier ATF binding-site predictionTF–DNA binding specificity
Protocols
0
Results
0
Works
0
B23Numeric results available

PRDBv2 / protein–RNA docking benchmark

Docking benchmark; target version, bound/unbound state and redundancy filters must be recorded.

Tier CNucleic-acid–protein interface or docking
Protocols
2
Results
4
Works
1
B24No standard numeric protocol

HARIBOSS / RNA–small-molecule structure benchmark

Useful for binding and docking, but not a single standardized leaderboard.

Tier CRNA–small-molecule binding predictionNucleic-acid–small-molecule docking
Protocols
0
Results
0
Works
0
B25No public numeric result

R-SIM / RNAmigos2 benchmark

Decoy construction and pocket redundancy are material evaluation choices.

Tier CRNA–small-molecule binding predictionNucleic-acid–small-molecule docking
Protocols
0
Results
0
Works
0
B26No public numeric result

NucleoBench

Official repository lists 17 design tasks. The ribosomal-loading task is separated as 5′UTR/translation-control design; the remaining instances stay consolidated under cis-regulatory design.

Tier BEnhancer or cis-regulatory design5′UTR and translation-control design
Protocols
0
Results
0
Works
0
B27Numeric results available

OligoGym

Twelve curated ASO/siRNA/shRNA datasets with explicit split comparisons.

Tier BsiRNA, ASO or shRNA design
Protocols
24
Results
45,932
Works
1
B28No public numeric result

RNAglib structure–function benchmark

Seven RNA structure–function datasets; task-level splits and structural redundancy controls should be preserved.

Tier BRNA 3D model quality assessmentRNA–protein binding predictionRNA–small-molecule binding predictionNucleic-acid–protein interface or docking
Protocols
0
Results
0
Works
0
B29No public numeric result

NABench

Large-scale nucleotide fitness benchmark; verify repository release before production adoption.

Tier BNucleic-acid fitness predictionRNA DMS effect prediction
Protocols
0
Results
0
Works
0
B30Restricted

Random Promoter DREAM Challenge

Prospective promoter-expression prediction challenge with experimental readout; not counted as a sequence-generation benchmark.

Tier APromoter activity prediction
Protocols
0
Results
0
Works
0
B31No public numeric result

NucleoDock external benchmark

External set of 125 nucleic-acid–ligand complexes; model-paper benchmark, not community suite.

Tier CNucleic-acid–small-molecule docking
Protocols
0
Results
0
Works
0
B32No public numeric result

SMRTnet RNA–small-molecule benchmark

Emerging benchmark for RNA–small-molecule interaction; check release artifacts and negative construction.

Tier CRNA–small-molecule binding prediction
Protocols
0
Results
0
Works
0
B33No public numeric result

OmniGenBench

Meta-suite packaging RGB, BEACON, GUE, Genomic Benchmarks and PGB; native_task_count=5 suites, not the sum of their downstream tasks.

Tier BGenomic element classificationPromoter recognitionEnhancer recognitionTF binding-site prediction
Protocols
0
Results
0
Works
0
B34Numeric results available

ERNIE-RNA downstream evaluation study

One-time model study spanning 15 named data packages; PrismNet is additionally stratified into 17 HeLa RBP assays.

Tier CRNA secondary-structure base-pair predictionRNA contact or distance-map predictionTranslation efficiency or ribosome-load predictionRNA–protein binding prediction
Protocols
12
Results
231
Works
1
B35Numeric results available

Stanford RNA 3D Folding Challenge

Two time-separated competitions with hidden targets; submissions provide five candidate 3D structures and are evaluated best-of-five.

Tier ARNA 3D coordinate predictionRNA 3D model quality assessmentAll-atom nucleic-acid complex structure prediction
Protocols
22
Results
82
Works
1
B36No public numeric result

GenoArmory

Adversarial robustness wrapper over eight GUE histone-mark datasets; four attack families and three defense strategies are evaluation regimes, not new biological task families.

Tier BHistone-mark prediction
Protocols
0
Results
0
Works
0
B37No public numeric result

RNAtive model-quality benchmark

Two released evaluation collections: CASP15 predicted models and Randstr decoys; benchmark package is fully archived on Zenodo.

Tier CRNA 3D model quality assessment
Protocols
0
Results
0
Works
0
B38Numeric results available

EternaBench

Thirty-one chemical-mapping, riboswitch and external thermodynamic datasets; repository is archived but versioned and reproducible.

Tier CRNA probing-reactivity predictionRNA conformational ensemble predictionAptamer–target affinity prediction
Protocols
8
Results
107
Works
1
B39No standard numeric protocol

AptaBench

6,289 DNA/RNA aptamer–ligand records with fixed stratified, ligand-disjoint and aptamer-disjoint five-fold protocols; anonymous pre-review status should be preserved.

Tier CRNA–small-molecule binding predictionAptamer–target affinity prediction
Protocols
0
Results
0
Works
0
B40Numeric results available

RNA–RNA Interactions Benchmark

Manually confirmed interaction regions across archaea, bacteria and eukaryotes; the repository moved from UCanCompBio to Gardner-BinfLab.

Tier CRNA–RNA interaction prediction
Protocols
7
Results
84
Works
1
B41No public numeric result

RnaBench Riboswitch Design Benchmark

Fixed generative riboswitch design evaluation over 685,109 unique sequences with validity and novelty metrics.

Tier BProgrammable RNA-switch design
Protocols
0
Results
0
Works
0
B42No public numeric result

Deep DNAshape benchmark evaluation

Evaluation against experimental-structure and molecular-dynamics DNA-shape labels; a reusable study protocol rather than a community leaderboard.

Tier CDNA shape prediction
Protocols
0
Results
0
Works
0
B43Numeric results available

RNP-ΔΔG blind mutation benchmark

Blind and independent RNA–protein affinity tests; only RNA-side mutations are in scope. MS2, diverse-complex and PUM2 tests remain separate protocols.

Tier CRNA-binding variant-effect prediction
Protocols
3
Results
3
Works
1
B44Numeric results available

ATGC-Gen promoter-generation evaluation

100,000 generated 1,024-bp promoters evaluated with the Sei H3K4me3 activity oracle, MSE, KS and fluency; comparisons are restricted to the same source table.

Tier CPromoter sequence design
Protocols
1
Results
15
Works
1
B45No public numeric result

RDesign tertiary RNA inverse-design benchmark

Fixed tertiary-structure-to-sequence design evaluation released with code and benchmark data; computational structural recovery only unless separately validated.

Tier CRNA 3D-conditioned design
Protocols
0
Results
0
Works
0
B46No public numeric result

LinearDesign mRNA co-design evaluation

Multi-objective mRNA design with prospective wet-lab measurements of stability, expression and immunogenicity; it must not be ranked with computational-only protocols.

Tier CmRNA coding and stability co-design
Protocols
0
Results
0
Works
0
B47No public numeric result

RhoDesign light-up aptamer evaluation

Structure-guided light-up aptamer generation with prospective fluorescence validation; secondary mapping to tertiary RNA design is recorded separately.

Tier CAptamer designRNA 3D-conditioned design
Protocols
0
Results
0
Works
0