aiaimodel.cards
← All benchmarks

Spatial reasoning (SpatialGenEval)

We haven't written a description for this benchmark yet; see the card notes below for how each maker ran it.

Your workloadRAG over docs · 12K in · 600 out · 50K requests/mo · 30% cached
  1. 1Ideogram 4.0 · Ideogram
    0.76 score

“Best value”: no other model here reports a higher score at a lower cost for your workload. Scores are self-reported by each maker with different settings, so treat close calls as ties.

How each maker reported it

  • Ideogram 4.0 launch post

    Ideogram's own numbers. Absolute scores 0–1 (7Bench with Magic Prompt on; SpatialGenEval judged with gemini-2.5-flash). Elo is from Ideogram's internal arena: 4,366 blind graphic-designer votes across nine pipelines. The Hugging Face card also reports a blind typography test by ContraLabs (ten designers): Ideogram 4 picked best of four 47.9% of the time vs 30.0% for Nano Banana 2.

Only each model's own maker's number is shown; scores a maker reports for rival models are left out.