Skip to main content
ModelScale

external benchmark

BioMysteryBench (Vals) leaderboard

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

Categoryexternal
MeasureAverage task accuracy across three runs
TasksEnd-to-end bioinformatics investigations from raw data
DifficultyAgentic biological analysis

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

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.

All leaderboards