mRNA Design Benchmark (CodonBench 2026)
First open mRNA therapeutic design benchmark: codon optimization, UTR design, 5' cap accessibility, and expression prediction across HEK293 + iPSC.
Composite
82.0
Experimental validation
Prospective
Stages
Hit IDLead ID / ADMET
Modalities
rna-therapeutic
Task types
codon-optimizationrna-structureexpression-prediction
Size
sequences: 52,000
constructs: 1,840
constructs: 1,840
License
CC-BY-4.0
First release
2026-01
Last updated
2026-04
Official site
Leaderboard
Dataset
→ dataset
Code / GitHub
HuggingFace
→ HF
Paper
CodonBench: evaluating AI for mRNA therapeutic design · Zhang H, et al. · 2026 · paper · doi:10.1038/s41551-026-01123-8 · 38 citations
Flags
none
Experts
—
Groups
—
Hosted by
—
Related benchmarks
—
Rubric (7-criterion)
rigor
4
coverage
4
maintenance
4
adoption
3
quality
4
accessibility
5
industry_relevance
5
Notes
Designed with Moderna and Deep Genomics; includes held-out wet-lab validation track.