PhAIL (Physical AI Leaderboard) Benchmark
Explore score history ↗A real-robot leaderboard for vision-language-action policies on a Franka FR3. It scores policies with Human-Relative Throughput computed from time-to-success distributions and uses Kolmogorov-Smirnov significance tests.
- Released
- 2026-05-28
- Institutions
- Positron Systems (United States)
- Evaluates
- Robotics, Robotics & Embodied AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
PhAIL (Physical AI Leaderboard) paper and code
No reported scores are on record for this benchmark yet.