Skip to content

Blueprint-Bench 2

An agentic spatial reasoning benchmark reported as a normalized score.

2 models

Higher is better.

  1. 1Claude Fable 5Anthropic38.6
  2. 2Gemini 3.5 FlashGoogle33.6
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric
Normalized score
Tasks
Spatial reasoning from blueprints
Authors
Google DeepMind (2026)

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.