RLTasksby ulam.ai
Models / Reported model

Reported model / MODEL EVIDENCE

ESM-1v

1 benchmarks · 1 observations · 1 sources

Scores at a glance

1 benchmarks · large dot: ESM-1v; small dots: closest models where reported

ProteinGym ↗0.371 Spearman rho
0.370.37

ESM-1v · ProteinGym · ProteinGym substitutions · mean Spearman correlation · RITA report · ProteinGym comparison ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

There are not enough shared scored settings to identify close comparisons reliably.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. RITA: a Study on Scaling Up Generative Protein Sequence Models — published result table ↗

    Daniel Hesslow, Niccoló Zanichelli, Pascal Notin, Iacopo Poli, Debora Marks · 2022

Names used in source tables

ESM-1v