DisasterBench (UAV) - Trigger Mechanism Identification: leaderboard
Metric: Accuracy (%) on trigger mechanism identification (TMI) 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
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 84.06 |
| 2 | GPT-5 | 84.06 |
| 3 | Gemini 2.5 Flash | 83.33 |
| 4 | Claude Sonnet 4.5 | 80.07 |
| 5 | GPT-4o | 76.81 |
| 6 | Gemini 2.0 Flash | 76.45 |
| 7 | Grok 4 | 76.09 |
| 8 | Qwen 2.5 VL 7B Instruct | 67.03 |
| 9 | GPT-4o Mini | 64.86 |
| 10 | InternVL2-8B | 63.77 |
| 11 | InternVL3.5-8B | 54.35 |
Interactive version: theaggregate.ai/benchmark?slug=disasterbench-uav-trigger-mechanism-identification · How It Works · Data refreshed daily, snapshot 2026-09-29.