Benchmark
TVRBench
What is TVRBench?
A simulated indoor benchmark in which foundation models must actively move and turn to reproduce the viewpoint shown in a target image.
- Released
- 2026-05-31
- Evaluates
- Agents, Agents & Tool Use, Geometric reasoning, Robotics & Embodied AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2606.01247
TVRBench paper and code
No reported scores are on record for this benchmark yet.