Benchmark
EMBODIEDSWE-BENCH
What is EMBODIEDSWE-BENCH?
Simulation benchmark for coding agents spanning contact-rich manipulation, deformable objects, and long-horizon tasks up to half an hour.
- Released
- 2026-09-23
- Evaluates
- Robot manipulation, Robotics, Robotics & Embodied AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-name-audit-deferred
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2609.27308
EMBODIEDSWE-BENCH paper
No reported scores are on record for this benchmark yet.