Announcement
Frontier-Bench is now Terminal Bench 3.0
Frontier-Bench has a new name and our benchmark is following suit.
Earlier today, Frontier Bench announced that it is becoming Terminal Bench 3.0. The new name was chosen by the original benchmark’s community in a Discord vote, marking its next chapter as part of the Terminal Bench series.
Because our tasks are based on the original Frontier Bench, we’re following suit. From today, our Frontier Bench benchmark will be known as Terminal Bench 3.0. The tasks and results remain the same, only the name is changing.
Talk to us
Revelo works with model labs on:
- Training datasets for code generation
- Evaluations of new and unreleased models
- Leaderboard analysis, including failure modes and agent trajectories