DORA - Disaster Perception and Assessment: leaderboard

DORA evaluates model agents answering disaster-response questions with a 108-tool geospatial library under a ReAct loop. This series reports final-answer accuracy for disaster perception and assessment; the five tasks cover 515 expert-authored cases across 45 disasters. Only the thirteen agent runs enter this panel; expert gold trajectories and tool-free VLM runs use different protocols. Higher is better.

Metric: Final-answer accuracy (%; ReAct agent with tools). Source: github.com. Saturation forecast: Around February 2027. 13 models tracked. Updated 2 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Sonnet 4.654.43#173
2Gemini 3 Flash54.19#174
3MiMo-V2-Pro53.68#329
4Grok 4.1 Fast53.07#429
5GPT-5.452.85#135
6MiniMax-M2.751.87#533
7Gemma 4 31B51.46#385
8Qwen 3.5 397B A17B51.03#255
9DeepSeek V3.249.8#417
10Step 3.5 Flash49.7#520
11GPT-5.4 Nano44.4#645
12GPT-OSS-120B42.7#707
13Qwen 3.5 35B A3B14.15#490

No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=dora-disaster-perception-and-assessment · How It Works · Data refreshed daily, snapshot 2026-11-17.