Qwen-3.8 27B scores 52 on intelligence index, rivaling GPT-5.6 Luna

haider1 · x · 2026-08-18

Qwen-3.8 27B achieves a score of 52 on the intelligence index, performing similarly to GPT-5.6 Luna at maximum reasoning levels. Despite having only 27 billion parameters, the open-weight model is lightweight enough to run locally on capable consumer hardware.

Related event: Qwen3.8-27B matches top closed-source models on benchmarks while running on a single consumer GPU(20 posts)→

Original post →

More from Models

Models channel →