DisasterBench (UAV) - Propagation Path Inference: leaderboard

Metric: Accuracy (%) on propagation path inference (PPI) 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 June 2027. 21 models tracked.

Top models

#ModelScore
1GPT-578.57
2Gemini 2.5 Pro76.49
3Grok 476.19
4Gemini 2.0 Flash75.89
5Qwen 2.5 VL 7B Instruct72.32
6Claude Sonnet 4.568.45
7InternVL2-8B65.18
8GPT-4o Mini63.39
9Gemini 2.5 Flash63.1
10InternVL3.5-8B61.31
11GPT-4o58.33

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