DORA - Disaster Operational Planning: leaderboard
Metric: Final-answer accuracy (%; ReAct agent with tools). Source: github.com. Saturation forecast: Around May 2027. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 59.82 |
| 2 | MiMo-V2-Pro | 55.48 |
| 3 | Grok 4.1 Fast | 54.23 |
| 4 | GPT-5.4 | 53.5 |
| 5 | Gemma 4 31B | 52.33 |
| 6 | Claude Sonnet 4.6 | 51.82 |
| 7 | Qwen 3.5 397B A17B | 51.82 |
| 8 | DeepSeek V3.2 | 50.57 |
| 9 | MiniMax-M2.7 | 50.16 |
| 10 | Step 3.5 Flash | 48.33 |
| 11 | GPT-OSS-120B | 42 |
| 12 | GPT-5.4 Nano | 39.98 |
| 13 | Qwen 3.5 35B A3B | 33.08 |
Interactive version: theaggregate.ai/benchmark?slug=dora-disaster-operational-planning · How It Works · Data refreshed daily, snapshot 2026-10-02.