Qwen 3.8 27B scores 52, matching GPT-5.6 Luna at a fraction of the size
Qwen 3.8 27B scored 52 on the Artificial Analysis Intelligence Index, matching GPT-5.6 Luna (max) and one point behind far larger frontier models like GLM-5.2 (753B) and DeepSeek V4 Pro (1.7T). An open-weights model this small keeping pace with closed giants reshapes what on-device AI can do.