# Blueprint-Bench 2 — AI model rankings

Can the AI reason about space and layout — for example, understanding a floor plan or blueprint? Higher is better.

6 tracked models have a published Blueprint-Bench 2 score. Higher is better. Scores are as published at each model's release.

## Ranking

| Rank | Model | Developer | Score | Released |
| --- | --- | --- | --- | --- |
| 1 | GPT-5.5 | OpenAI | 36.2% | Apr 23 2026 |
| 2 | Gemini 3.5 Flash | Google | 33.6% | May 19 2026 |
| 3 | Gemini 3.1 Pro | Google | 26.5% | Feb 19 2026 |
| 4 | Claude Opus 4.7 | Anthropic | 24.5% | Apr 16 2026 |
| 5 | Claude Sonnet 4.6 | Anthropic | 6.7% | Feb 17 2026 |
| 6 | Gemini 3.0 Flash | Google | 0% | Dec 17 2025 |


---

Canonical page: https://aireleasetracker.com/benchmark/blueprint-bench-2
Full dataset: https://aireleasetracker.com/llms-full.txt · JSON: https://aireleasetracker.com/models.json
Source: AI Release Tracker (https://aireleasetracker.com). Benchmark scores are the figures published by the releasing lab at launch.