DORA - Multimodal Report Synthesis: 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 multimodal report synthesis; 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 April 2027. 13 models tracked. Updated 2 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 397B A17B | 49.17 | #255 |
| 2 | Claude Sonnet 4.6 | 45.53 | #173 |
| 3 | Gemini 3 Flash | 45.31 | #174 |
| 4 | Grok 4.1 Fast | 44.52 | #429 |
| 5 | MiMo-V2-Pro | 44.26 | #329 |
| 6 | Gemma 4 31B | 42.03 | #385 |
| 7 | Step 3.5 Flash | 41.58 | #520 |
| 8 | DeepSeek V3.2 | 41.01 | #417 |
| 9 | MiniMax-M2.7 | 40.62 | #533 |
| 10 | GPT-5.4 | 29.11 | #135 |
| 11 | GPT-OSS-120B | 28.84 | #707 |
| 12 | GPT-5.4 Nano | 27.37 | #645 |
| 13 | Qwen 3.5 35B A3B | 21.3 | #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-multimodal-report-synthesis · How It Works · Data refreshed daily, snapshot 2026-11-17.