AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
Model reports
Blueprint-Bench 2
Spatial-reasoning set: 50 apartments, ~20 photos each, scored by a connectivity-graph grader, with a public leaderboard on the Andon Labs eval page (run in-house; dataset not openly downloadable). Builds on the original Blueprint-Bench paper (arXiv:2509.25229), a distinct instrument released 2025-09-24 whose scores must not be compared across versions.
Evaluation context and evidence
- Source
- Model reports
- Publisher
- Not recorded
- Benchmark release
- 2026-05-04
- Collected
- Not recorded
- Modality
- Not recorded
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 0
This source record has no numeric results in our collection. That does not mean a score of zero or that no public results exist. Consult the original resources above.