DisasterBench (UAV) - Disaster-Chain Summary: leaderboard

Metric: Accuracy (%) on disaster-chain summary (DCS) 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: Around December 2026. 21 models tracked.

Top models

#ModelScore
1Gemini 2.0 Flash92.4
2Gemini 2.5 Pro90.49
3GPT-590.11
4Gemini 2.5 Flash87.07
5Qwen 2.5 VL 7B Instruct86.69
6Claude Sonnet 4.586.12
7InternVL2-8B84.98
8Grok 482.51
9GPT-4o79.85
10InternVL3.5-8B78.9
11GPT-4o Mini73.19

Interactive version: theaggregate.ai/benchmark?slug=disasterbench-uav-disaster-chain-summary · How It Works · Data refreshed daily, snapshot 2026-09-29.