GISAgentBench - Remote Sensing and Image Analysis: leaderboard
The Remote Sensing and Image Analysis family of GISAgentBench (University of Florida, 2026): 45 tasks that process raster imagery or derived indices through masking, classification, pixel computation or zonal summaries. Strict task success rate in percent against exact ground-truth output files under deterministic checks; higher is better.
Metric: Strict task success rate (%; share of the 45 Remote Sensing and Image Analysis 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 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 37.8 | #94 |
| 2 | Claude Opus 4.6 | 33.3 | #102 |
| 3 | DeepSeek V4 Pro | 24.4 | #188 |
| 4 | GPT-5.4 | 20 | #123 |
| 5 | Qwen 3.6 27B | 15.6 | #341 |
| 6 | GPT-OSS-120B | 13.3 | #700 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=gisagentbench-remote-sensing-and-image-analysis · How It Works · Data refreshed daily, snapshot 2026-11-13.