RoboSemanticBench
Explore score history ↗RoboSemanticBench (RSB) is an embodied benchmark evaluating whether vision-language-action models use instruction semantics to select and grasp the correct physical target among candidate blocks in response to math or general-knowledge questions. It includes six suites with four- or ten-choice variants, procedural arithmetic, GSM8K-style, and MMLU-style questions, with diagnostic metrics separating task success from grasp success.
- Released
- 2026-06-01
- Evaluates
- Robotics & Embodied AI, cs.RO
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
RoboSemanticBench paper and code
No reported scores are on record for this benchmark yet.