Benchmark
GuideMe Benchmark
What is GuideMe?
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…
- Released
- 2026-07-03
- Evaluates
- General AI, Vision & 3D, cs.CV
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2607.02991
GuideMe paper
No reported scores are on record for this benchmark yet.