Benchmark RadarAI BENCHMARK PROFILE
OVIBench
Evaluates VLMs on online video question answering under user interruptions, with offline simulation and multi-dimensional metrics.
- Released
- 2026-08-23
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Addresses the gap between offline benchmarks and real-time interactive video QA, which is essential for practical VLM deployment.
Motivation
Recent vision language models (VLMs) have achieved strong progress in video understanding.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.