GeoAgentBench (Plan-and-React) - Tool Exact Match: 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 the percentage of the gold tool sequence matched exactly from the first step, with the agent using a global plan with step-wise reactive execution; higher is better.

Metric: Tools-Exact-Match (%): share of the ground-truth tool sequence matched exactly from the first step, 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 V351.16#736
2Claude Sonnet 4.645.5#179
3GPT-4o Mini41.1#1680
4GPT-4o38.58#754
5Gemini 2.5 Flash30.52#466
6Llama 3.1 8B Instruct18.93#4655
7Qwen 2.5 7B Instruct16.14#2732

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

Interactive version: theaggregate.ai/benchmark?slug=geoagentbench-plan-and-react-tool-exact-match · How It Works · Data refreshed daily, snapshot 2026-11-22.