Skip to main content
ModelScale

external benchmark

Vals Terminal-Bench 2.0 mirror leaderboard

Vals-hosted Terminal-Bench 2.0 mirror. Every model the catalog carries a published Vals Terminal-Bench 2.0 mirror value for, ranked by that value.

Categoryexternal
MeasureAccuracy score
TasksTerminal task difficulty splits
DifficultyTerminal-based agent execution

Vals AI hosted Terminal-Bench 2.0 view with easy, medium, and hard task splits.

No model in the catalog has a published Vals Terminal-Bench 2.0 mirror score.

The benchmark is defined by Vals Terminal-Bench 2.0, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

All leaderboards