GISAgentBench: leaderboard
Metric: Strict task success rate (%; share of the 349 tasks whose output file matches the exact ground-truth output within the task's declared tolerance under deterministic structural and value checks, no LLM judge; LangChain ReAct agent over a fixed harness of 128 GIS APIs backed by QGIS, GDAL and GeoPandas; 50 tool calls per task, temperature 0, one run per task, July 2026). Source: arxiv.org. Saturation forecast: Around March 2028. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 32.7 |
| 2 | Claude Opus 4.6 | 29.5 |
| 3 | DeepSeek V4 Pro | 27.5 |
| 4 | GPT-5.4 | 22.9 |
| 5 | Qwen 3.6 27B | 17.8 |
| 6 | GPT-OSS-120B | 12.3 |
Interactive version: theaggregate.ai/benchmark?slug=gisagentbench · How It Works · Data refreshed daily, snapshot 2026-09-29.