Axis Spatial Spatial Intelligence Index

Search modelsMenu

ThinkGeo drawn (judged) benchmark leaderboard

Mark, label or chart what the question asks on an aerial image (judged, calibration pending), answered from the images alone, with no tools. A standalone evaluation: its scores are shown here and on model pages, but it is not counted in any index or ranking until more models have run it.

Score

ThinkGeo drawn (judged) score

Share of questions answered correctly, 0 to 100 · Higher is better

No model has a score yet.

How to read this chart

What this metric means. The share of questions the model answered correctly from the images alone, with no tools.

Rows. Default: each developer's best model, then the best of each other model family (such as Opus, Sonnet and Haiku), then the best of the rest, up to 16, or one per family where there are more. Tables keep every entry.

Data table: ThinkGeo drawn (judged) score
ThinkGeo drawn (judged) score
ModelThinkGeo drawn (judged) score

Background

ThinkGeo asks an agent to find objects in an aerial or radar image and show the answer on the image: draw a box on the smallest plane, label each aircraft with a number, write the count of ships, or plot a chart. The source ships no answer key for these, because the answer is a picture, so they were left out of every other evaluation.

Licence: questions and images as ThinkGeo (CC-BY-4.0 as declared on the dataset card); the imagery comes from other remote-sensing datasets whose own terms also apply.

Published by Mohamed bin Zayed University of AI (ThinkGeo); rubrics by Axis Spatial.

Related links

Explore evaluations