Blueprint-Bench 2 leaderboard

As of November 14, 2026, among the results listed here, Google Gemini 4 Carbon has the highest reported Blueprint-Bench 2 score, 58.6% (Similarity score), published by Google on October 28, 2026, ahead of Google Gemini 4 Argon at 54.4%. 3 models have a Blueprint-Bench 2 result in our records.

Scores as the model makers published them, not re-run by us; each row links to its announcement.

Best reported score

58.6%

Google Gemini 4 Carbon

Reported by Google, October 28, 2026 · Similarity score

Runner-up

54.4%

Google Gemini 4 Argon

Reported by Google, October 28, 2026 · Similarity score

3 models ranked · 1 maker

Reported Blueprint-Bench 2 scores

Blueprint-Bench 2 scores reported by model makers
Rank	Model	Score	Setting	Reported by	Date
1	Gemini 4 Carbon	58.6%	Similarity score	Google	October 28, 2026 · read from the maker's chart
2	Gemini 4 Argon	54.4%	Similarity score	Google	October 28, 2026 · read from the maker's chart
3	Gemini 3.5 Flash	33.6%	Not published	Google	May 19, 2026 (model release)

How much to trust these numbers

Source: Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
Settings: Settings differ between makers. Check the Setting column before comparing two scores.
Spread: 58.6% to 33.6% across 3 models.
Freshness: Newest result published October 28, 2026; oldest May 19, 2026.
Charts: Some values were read from charts in the announcements. Two independent readings had to match exactly.

What Blueprint-Bench 2 measures

Models turn about 20 apartment photos into 2D floor plans, with scores reporting normalized connectivity as a percentage. Source: Blueprint-Bench 2