Long-Horizon-Terminal-Bench
Explore score history ↗Evaluates long-horizon terminal tasks in a containerized environment with hidden verifiers and dense reward grading across 46 tasks and nine categories.
- Released
- 2026-07-09
- Institutions
- Tencent (China) · Indiana University · National University of Singapore
- Evaluates
- Agents & Tool Use, Code, General AI, Multimodal, Software & AI Compute
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- source-reviewed
Long-Horizon-Terminal-Bench paper, code and dataset
No reported scores are on record for this benchmark yet.