GeoAgentBench (Plan-and-React) - Tool Retrieval F1: 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 F1 in percent between the tools the agent invokes and the gold tool set, with the agent using a global plan with step-wise reactive execution; higher is better.

Metric: Tools-Any-Order F1 (%) between the tools the agent invokes and the ground-truth tool set, 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
1Claude Sonnet 4.684.94#173
2DeepSeek V380.64#729
3GPT-4o79.55#751
4Gemini 2.5 Flash75.11#463
5GPT-4o Mini70.95#1667
6Llama 3.1 8B Instruct47.11#4600
7Qwen 2.5 7B Instruct44.79#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-tool-retrieval-f1 · How It Works · Data refreshed daily, snapshot 2026-11-21.