DisasterBench
Evaluates multimodal reasoning for UAV-based disaster response across 14 scene types and 9 tasks spanning pre-, during-, and post-disaster stages.
- Released
- 2026-06-04
- Readiness
- Runnable
- Primary field
- General AI
Why it matters
Addresses the lack of benchmarks covering multi-stage disaster reasoning with causal attribution, prediction, and decision-making under low-altitude UAV views and on-site compute constraints, offering a means to compare models on practical emergency-response tasks.
Motivation
When a disaster unfolds, responders must answer not only what is happening, but also why it is happening, what will happen next, and what to do now, often from noisy low-altitude UAV views and under tight on-site compute constraints.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.