Benchmark
ActiveVision Benchmark
What is ActiveVision?
ActiveVision evaluates whether multimodal large language models can perform repeated, active visual perception across 17 tasks in three categories.
- Released
- 2026-07-17
- Evaluates
- General AI, Vision & 3D, cs.CV
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2607.16165
ActiveVision paper
- Paper https://arxiv.org/abs/2607.16165
- Website https://activevision.dev
No reported scores are on record for this benchmark yet.