DisasterBench (UAV) - Emergency Resource Allocation: leaderboard

Metric: Accuracy (%) on emergency resource allocation (ERA) 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
1GPT-597.48
2Gemini 2.5 Pro93.28
3Claude Sonnet 4.593.28
4InternVL2-8B92.44
5Qwen 2.5 VL 7B Instruct92.44
6Gemini 2.5 Flash91.6
7Grok 489.92
8Gemini 2.0 Flash88.24
9InternVL3.5-8B88.24
10GPT-4o83.19
11GPT-4o Mini83.19

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