Benchmark RadarAI BENCHMARK PROFILE
SLVMBench
SLVMBench evaluates video-LLMs' ability to learn skills from long video memory and apply them to real-time tasks, using 2-3 hour streams with embedded tutorials and human-annotated questions.
- Released
- 2026-07-13
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
This is the first benchmark to test skill learning from long-context video memory, revealing significant limitations in current video LLMs and providing a realistic evaluation for skill acquisition.
Motivation
We introduce Skill Learning from Video Memory (SLVMBench), the first benchmark that jointly evaluates whether video large language models (video-LLMs) can learn skills from long video memory and apply them to real-time tasks.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.