GPT-5.6 Ranks Fourth in 3D Spatial Benchmark

Afinetheorem · x · 2026-07-10

The repost states that GPT 5.6 Sol ranks 4th on Blueprint-Bench 2, followed by Terra at 5th and Luna at 10th. It emphasizes that Blueprint-Bench 2 evaluates whether AI agents can comprehend 3D space. The original quoted post also mentions that GPT-5.6 Sol, Terra, and Luna will be publicly released this Thursday, with expanded preview access already rolling out globally.

Original post →

More from Models

Models channel →