DORA - Temporal Evolution Reasoning: 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 temporal evolution reasoning; 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
1MiMo-V2-Pro63.58#329
2Qwen 3.5 397B A17B61.83#255
3Gemma 4 31B61.03#385
4Gemini 3 Flash60.4#174
5Claude Sonnet 4.660.05#173
6Grok 4.1 Fast55.28#429
7GPT-5.451.9#135
8DeepSeek V3.250.62#417
9MiniMax-M2.750.59#533
10Step 3.5 Flash48.9#520
11GPT-5.4 Nano45.55#645
12Qwen 3.5 35B A3B37.62#490
13GPT-OSS-120B24.43#707

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

Interactive version: theaggregate.ai/benchmark?slug=dora-temporal-evolution-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-17.