DisasterBench - RAP: leaderboard
Metric: Exact-match accuracy (%) over the 233 DisasterBench planning tasks (35 single-tool, 166 chain and 32 branching workflows over 26 disaster-response tools): a plan counts only when every step matches the ground truth in tool identity, parameter bindings and inter-step dependencies; planning method: Reasoning via Planning, Monte Carlo tree search guided by usefulness and self-consistency rewards (temperature 0.5); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 72.1 |
| 2 | GPT-5.4 | 65.67 |
| 3 | Qwen 3 Max | 63.09 |
| 4 | Qwen 3 Max (Thinking) | 61.37 |
| 5 | Qwen 3.5 27B | 58.8 |
| 6 | Gemma 4 31B | 50.64 |
| 7 | Qwen 3.5 9B | 42.92 |
| 8 | DeepSeek R1 | 35.19 |
| 9 | DeepSeek V3.2 | 34.33 |
| 10 | Llama 3.3 70B | 28.76 |
| 11 | Llama 3.1 8B | 28.33 |
| 12 | Ministral 3 14B | 18.88 |
Interactive version: theaggregate.ai/benchmark?slug=disasterbench-rap · How It Works · Data refreshed daily, snapshot 2026-10-07.