DisasterBench (UAV) - Situation Understanding and Classification: leaderboard

Metric: Accuracy (%) on situation understanding and classification (SUC) questions on the 3,000-question test split of low-altitude UAV disaster images (14 disaster scene types), multiple choice scored by strict exact match on the final option letter; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 21 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro94.14
2Gemini 2.5 Flash92.83
3GPT-592.51
4Claude Sonnet 4.591.86
5Gemini 2.0 Flash89.9
6Grok 489.58
7GPT-4o86.32
8Qwen 2.5 VL 7B Instruct85.02
9InternVL3.5-8B83.71
10GPT-4o Mini81.76
11InternVL2-8B81.43

Interactive version: theaggregate.ai/benchmark?slug=disasterbench-uav-situation-understanding-and-classification · How It Works · Data refreshed daily, snapshot 2026-09-29.