Benchmark
GeoVAD-Bench
What is GeoVAD-Bench?
A diagnostic benchmark for visual chain-of-thought in geometry problem solving, with five-dimensional trajectory diagnosis and controlled intervention settings.
- Released
- 2026-09-11
- Evaluates
- Geometric reasoning, Language & Knowledge, Reasoning, 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/2609.12606
GeoVAD-Bench paper
No reported scores are on record for this benchmark yet.