AI model chart reportedly lists scores of 0–4 out of 70
The user lists GPT 5.6 Luna at 4/70, with DeepSeek V4.1, GLM-5.3 and Grok 4.6 tied at 3/70.
TLDR
A user describes an AI model chart as “brutal,” listing GPT 5.6 Luna at 4/70 and DeepSeek V4.1, GLM-5.3 and Grok 4.6 tied at 3/70. Their rundown puts Kimi K3 at 2/70, Qwen 3.8 Max and Qwen 3.8 37B at 1/70, and GLM 5.3-Flash at 0/70.
Combined views
34.4K
2 Sources, first seen 19d ago
313 likes