# BioMysteryBench (Vals) 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-vals-bio-mystery-bench

Vals BioMysteryBench agent leaderboard. Every model the catalog carries a published BioMysteryBench (Vals) value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Average task accuracy across three runs |
| Tasks | End-to-end bioinformatics investigations from raw data |
| Difficulty | Agentic biological analysis |
| Published by | [Vals BioMysteryBench](https://www.vals.ai/benchmarks/biomysterybench) |

Independent agent runs on biological data investigations, split by human-solvable and human-difficult tasks.

## BioMysteryBench (Vals) ranking

No model in the catalog has a published BioMysteryBench (Vals) score. The benchmark is defined by Vals BioMysteryBench, 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.
