# FrontierBioML leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/external-frontier-bio-ml

FrontierBioML: Evaluating agents on machine learning tasks in computational biology. Every model the catalog carries a published FrontierBioML value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Offline agent sandbox (4 to 32 CPUs, no GPU, about 6 hours); the submitted prediction script runs twice on held-out data; 3 runs per task, 75 per model |
| Tasks | 25 machine learning tasks in computational biology across antibodies, designed binders, protein engineering, structural biology and functional genomics |
| Difficulty | Building and validating models on messy biological data that generalize to held-out antigens, families, cell types and targets |
| Published by | [FrontierBioML: Evaluating agents on machine learning tasks in computational biology](https://valenlabs.com/blog/frontierbioml) |

Valen Labs' benchmark of AI agents doing machine learning work in computational biology: 25 tasks in antibody development, designed binders, protein engineering, structural biology and functional genomics. Each agent builds a model from experimental data in an offline sandbox, and its prediction script is scored on held-out measurements, from 0 (a simple baseline) to 100 (a perfect answer), over three runs per task.

## FrontierBioML ranking

No model in the catalog has a published FrontierBioML score. The benchmark is defined by FrontierBioML: Evaluating agents on machine learning tasks in computational biology, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
