EgoProx Benchmark
Explore score history ↗EgoProx evaluates multimodal large language models on egocentric 3D proximity reasoning, with tasks organized along a cognitive hierarchy covering intention, exploration, exploitation, and chain-of-actions reasoning.
- Released
- 2026-05-23
- Institutions
- ByteDance (China) · Tsinghua University · Beijing Institute for General Artificial Intelligence
- Evaluates
- General AI, Geometric reasoning, Reasoning, Vision & 3D
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
EgoProx paper
No reported scores are on record for this benchmark yet.