DisasterBench - Chain-of-Thought: leaderboard
Chain-of-thought planning, with intermediate reasoning before the plan, on DisasterBench (2026), which tests whether an LLM can compose executable disaster-response workflows from 26 specialized tools under typed interface constraints. Exact-match accuracy over the planning tasks (every step must match in tool, parameter bindings and dependencies), percent; higher is better.
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: intermediate reasoning before the final plan (temperature 0); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 72.53 | #99 | |
| 2 | Qwen 3 Max | Thinking | 66.52 | #415 |
| 3 | Gemma 4 31B | 63.09 | #382 | |
| 4 | DeepSeek R1 | 62.66 | #482 | |
| 5 | GPT-5.4 | 62.23 | #135 | |
| 6 | Qwen 3.5 27B | 62.23 | #375 | |
| 7 | Qwen 3.5 9B | 61.37 | #828 | |
| 8 | Llama 3.3 70B | 58.8 | #1514 | |
| 9 | DeepSeek V3.2 | 36.05 | #419 | |
| 10 | Ministral 3 14B | 33.48 | #1870 | |
| 11 | Ministral 8B (DisasterBench checkpoint unspecified) | 31.33 | ||
| 12 | Llama 3.1 8B | 26.18 | #5196 | |
| 13 | Ministral 3B (DisasterBench checkpoint unspecified) | 21.03 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=disasterbench-chain-of-thought · How It Works · Data refreshed daily, snapshot 2026-11-21.