SkillTV-Bench
Explore score history ↗Evaluates whether a judge can verify long-horizon agent executions using original instructions, normalized trajectories, task-time skills, and inspectable artifacts in a runnable environment.
- Released
- 2026-08-06
- Institutions
- Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · University College London
- Evaluates
- Agents, General AI, Language & Knowledge
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
SkillTV-Bench paper and code
No reported scores are on record for this benchmark yet.