Where one study disagrees with what other studies report for the same models, and what we are doing to resolve each case.
These are automatic leads, not findings of error. Each release, a check compares how every study ranks the models it shares with other studies. It flags a study that reverses the order the others agree on, or whose gap to a shared reference model lies well outside theirs. Different tasks, populations or metrics often explain a flag.
A flag never hides a result. Flagged results stay in every table, page and download, marked Contested. A result is withheld only when a reviewer marks it disputed.
mRNABench: A curated benchmark for mature mRNA property and function prediction ranks DNABERT-2 above RNA-FM in 7 of 7 comparisons; other studies rank RNA-FM above DNABERT-2 in 30 of 30.
2 papers rank RNA-FM above DNABERT-2 in all 30 comparisons that are not ties (4 are ties). MRNABench ranks DNABERT-2 above RNA-FM in all 7 comparisons that are not ties (3 are ties).
Comparative Analysis of Deep Learning Models for Predicting Causative Regulatory Variants ranks HyenaDNA above DNABERT-2 in 3 of 4 comparisons; other studies rank DNABERT-2 above HyenaDNA in 89 of 108.
3 papers rank DNABERT-2 above HyenaDNA in 89 of their 115 comparisons and HyenaDNA higher in 19; 7 are ties. Comparative Analysis of Deep Learning… ranks HyenaDNA above DNABERT-2 in 3 of its 4 comparisons and DNABERT-2 higher in 1.
GENEB leaderboard (leaderboard.json, 13 task-type aggregates) ranks DNABERT-2 above Evo in 35 of 45 comparisons; other studies rank Evo above DNABERT-2 in 6 of 6.
Zero-shot benchmarking of RNA language… ranks Evo above DNABERT-2 in all 6 of its comparisons. GENEB leaderboard ranks DNABERT-2 above Evo in 35 of its 45 comparisons and Evo higher in 10.