Skip to main content
ModelScale

external benchmark

Terminal-Bench 2.1 leaderboard

Vals Terminal-Bench 2.1. Every model the catalog carries a published Terminal-Bench 2.1 value for, ranked by that value.

Categoryexternal
MeasureAccuracy score
TasksTerminal-based task execution
DifficultyFrontier terminal-agent execution
Published byTerminal-Bench 2.1

State-of-the-art set of difficult terminal-based tasks

No model in the catalog has a published Terminal-Bench 2.1 score.

The benchmark is defined by Terminal-Bench 2.1, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

All leaderboards