AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
OpenCompass Hub
Threat-Signature_Eval
Threat Signature Eval is a domain-specific benchmark for evaluating video-language models on real-world physical security / surveillance footage. It measures how well a model can recognize and classify security-relevant events into a 10-category threat taxonomy (e.g., Fire & Smoke, Fighting & Violen
Evaluation context and evidence
- Source
- OpenCompass Hub
- Publisher
- Ambient.ai
- Benchmark release
- 2025-11-19
- Collected
- 2026-08-18
- Modality
- video
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 0
This source record has no numeric results in our collection. That does not mean a score of zero or that no public results exist. Consult the original resources above.