Axis Spatial Spatial Intelligence Index

Search modelsMenu

Spatial Intelligence Index

How well AI models understand the physical world, at planetary scale: the mean of each model's best score on sets the top models have not solved.

Ranking

Each model once, at its best score on each set, 0 to 100, equal weights. DVL-Bench and GS-QA2 Full join the index once 10 models have finished them.

Spatial Intelligence Index: ranked models
RankModelDeveloperIndexBigEarthNet.txtGeoChronoMultiGlobeQA
1Claude Sonnet 5.5Anthropic70.9577680
2Claude Opus 5.5Anthropic70.7607479
3Claude Haiku 5.5Anthropic68.0547377
4Claude Opus 5Anthropic67.7537179
5Qwen 3.8 27BAlibaba (Qwen)63.7486974
6Claude Opus 4.8Anthropic60.9485975
7Claude Opus 4.7Anthropic59.8495477
8Claude Sonnet 5Anthropic58.3475573
9Step 5 PreviewStepFun56.9494973
10Muse Glimmer 30BMeta56.1465072
11Nemotron 3.5 Super VL 120BNVIDIA55.7474872
12MiniMax M3.1 FlashMiniMax54.4444772
13Qwen 3.6 35B-A3BAlibaba (Qwen)50.4453472
14Claude Haiku 4.5Anthropic50.3453670
15Nemotron 3 Nano Omni 30BNVIDIA38.4373148

Provisional

Not run: one set each, so these are not ranked. The index is the mean of the sets each has.

Spatial Intelligence Index: provisional models
RankModelDeveloperIndexBigEarthNet.txtGeoChronoMultiGlobeQA
–Mistral Large 4Mistral AI52.64362–

Models per set

  • DVL-Bench: 8 models (not counted yet)
  • BigEarthNet.txt: 16 models
  • GeoChrono: 16 models
  • MultiGlobeQA: 29 models
  • GS-QA2 Full: 6 models (not counted yet)

Best score on each set · Methodology

Frequently asked questions

What is the Spatial Intelligence Index?
A single score for how well an AI model understands the physical world: the mean of its best score on sets that still separate models, each from 0 to 100, all weighted equally.
Which sets count?
DVL-Bench, BigEarthNet.txt, GeoChrono, MultiGlobeQA and GS-QA2 Full, once enough models have finished a set (10 or more). A set leaves the index once the top models solve it.
Why is a model missing?
A model is ranked only when it has a finished run on every set that counts. A model one set short is listed as provisional, with its mean over the sets it has, and is never given 0 for the missing one.