IntelligenceLab/LHTB-leaderboard

Name: LHTB Leaderboard — Long-Horizon Terminal-Bench
Creator: IntelligenceLab

LHTB Leaderboard — Long-Horizon Terminal-Bench: Harbor dataset on Hugging Face. This repository hosts submitted runs for Long-Horizon Terminal-Bench (LHTB), a 46-task benchmark measuring how well LLM agents sustain useful work in a containerized terminal over hundreds of steps. Every entry below…

IntelligenceLab/LHTB-leaderboard on the Hugging Face Hub