GeoAgentBench (Plan-and-React): leaderboard

GeoAgentBench (2026) is a dynamic execution benchmark for tool-augmented GIS agents: spatial analysis tasks run in a sandbox of 117 atomic GIS tools and are scored on the tool trajectory, the parameters of the executed calls and the produced map. This board is parameter execution accuracy in percent, the share of gold steps whose final matching call has equivalent parameters, with the agent using a global plan with step-wise reactive execution; higher is better.

Metric: Parameter Execution Accuracy (%): share of ground-truth steps whose last matching tool call has semantically equivalent parameters, on 53 spatial analysis tasks over 117 atomic GIS tools in an executable sandbox (30 steps per task), agents under the authors' Plan-and-React framework (global plan with step-wise reactive execution); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1DeepSeek V347.34#729
2Claude Sonnet 4.646.11#173
3Gemini 2.5 Flash43.19#463
4GPT-4o40.69#751
5GPT-4o Mini36.15#1667
6Llama 3.1 8B Instruct21.59#4600
7Qwen 2.5 7B Instruct16.9#2723

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

Interactive version: theaggregate.ai/benchmark?slug=geoagentbench-plan-and-react · How It Works · Data refreshed daily, snapshot 2026-11-21.