Axis Spatial Spatial Intelligence Index

Search modelsMenu

Hallucination detection benchmark for geospatial AI

How well AI models do hallucination detection on satellite, aerial and map data: 2 sets with results, scored the same way for every model.

Sets

Hallucination detection: sets that cover it
SetIndexTasks of this typeBest score on the setModels
EVE hallucinationSpatial Intelligence Indexall6810
EVE hallucination detectionSpatial Intelligence Indexall8611

Top models

Mean of each model's best score on the 2 sets, 0 to 100, for the 9 models that have run all of them.

Top models on hallucination detection
RankModelDeveloperScore
1Claude Opus 5.5Anthropic77
2Claude Sonnet 5.5Anthropic76
3Nemotron 3.5 Super VL 120BNVIDIA75
4Step 5 PreviewStepFun74
5Claude Haiku 5.5Anthropic74
6GLM-5.3-FlashZ.ai74
7Nemotron 3 UltraNVIDIA73
8Nemotron 3.5 Lightning 30BNVIDIA71
9Nemotron 3 Nano Omni 30BNVIDIA63

Every task type · Every evaluation · Methodology

Frequently asked questions

Which AI model is best at hallucination detection on geospatial data?
Claude Opus 5.5 leads, on the sets below. Mean of each model's best score on the 2 sets, 0 to 100, for the 9 models that have run all of them.
What is this hallucination detection benchmark?
Every task in our sets that asks for hallucination detection, in GIS and Earth observation work, with each set's own score. It is a view over the sets, not an index of its own.
Which index does it count in?
Each set counts in one index: the Spatial Intelligence Index, as the table shows.