GuideMe Benchmark
Explore score history ↗GuideMe is a benchmark for evaluating multimodal large language models on streaming video task guidance. It includes 2,458 videos (223.7 hours) with 47,775 interaction samples covering next-step instructions, completion feedback, error detection, and corrective guidance. Assessment uses temporal-semantic matching, behavioral classification, and LLM-as-a-Judge.
- Released
- 2026-07-03
- Evaluates
- General AI, Vision & 3D, cs.CV
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
GuideMe paper and code
No reported scores are on record for this benchmark yet.