multimodal benchmark
Blueprint-Bench 2 Leaderboard
Blueprint-Bench 2 is a multimodal benchmark for evaluating models on architectural blueprints and other structured spatial documents.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
Blueprint-Bench 2 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score38.60% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score33.60% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
Blueprint-Bench 2 Highlights
The leading models and scores on this benchmark.
Blueprint-Bench 2 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Blueprint-Bench 2
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Blueprint-Bench 2?
What Blueprint-Bench 2 measures and how its scores work.
Blueprint-Bench 2 is an agentic spatial reasoning benchmark that evaluates models on architectural blueprints and other structured spatial documents.
It measures a model's ability to understand, plan, and reason over these documents, with results reported as a normalized Score in ratio units.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Blueprint-Bench 2
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Blueprint-Bench 2.
Which model scores highest on Blueprint-Bench 2?
Claude Fable 5 is currently ranked first with 38.60%.
What are the top three models on Blueprint-Bench 2?
The current leaders are Claude Fable 5 (38.60%) and Gemini 3.5 Flash (33.60%).
Which Blueprint-Bench 2 model has the lowest official input price?
Gemini 3.5 Flash has the lowest matched official input price at $1.5 input / $9.0 output per 1M tokens.
Which models are fastest among Blueprint-Bench 2 results?
The fastest matched records are Gemini 3.5 Flash (210.94 tok/s via Google) and Claude Fable 5 (43.18 tok/s via Anthropic).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.