DisasterBench (UAV) - Disaster-Chain Summary: leaderboard

DisasterBench (2026, UAV disaster response) is a multiple-choice reasoning benchmark over low-altitude drone images of 14 disaster-related scene types, covering tasks before, during and after a disaster. This board is exact-match accuracy (%) on the disaster-chain summary questions of the test split; higher is better.

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 February 2027. 21 models tracked.

Top models

#ModelScoreOverall rank
1Gemini 2.0 Flash92.4#704
2Gemini 2.5 Pro90.49#266
3GPT-590.11#167
4Gemini 2.5 Flash87.07#453
5Qwen 2.5 VL 7B Instruct86.69#1833
6Claude Sonnet 4.586.12#250
7InternVL2-8B84.98#2988
8Grok 482.51#307
9GPT-4o79.85#741
10GPT-4o Mini73.19#1623

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=disasterbench-uav-disaster-chain-summary · How It Works · Data refreshed daily, snapshot 2026-11-13.