MobileJudgeBench
Explore score history ↗MobileJudgeBench evaluates LLM-as-judge methods on mobile agent trajectories. It includes 931 human-annotated trajectories from 6 mobile agent benchmarks, covering 4 agent models and 68 apps.
- Released
- 2026-08-11
- Institutions
- Mila - Quebec Artificial Intelligence Institute · Concordia University · Shanghai University
- Evaluates
- Agents, Agents & Tool Use, General AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
MobileJudgeBench paper
No reported scores are on record for this benchmark yet.