News for hackers. Stuff that matters.
Re:Kimi K2.7-Code: open-source coding model with better toke... by 0xbadcafebee on Friday June 12, 2026 @11:34AM (#48505469)
DeepSeek v4 Pro is not actually that good a model compared to GLM 5.1 and Kimi K2.6. It's an okay coder/thinker for the price.
Re:Kimi K2.7-Code: open-source coding model with better toke... by bel8 on Friday June 12, 2026 @01:06PM (#48506648)
How so? In my experience trying these models using opencode Go, DeepSeek is superior to GLM 5.1.

If anything, DS4 has 1 million context window, while GLM 5.1 has 200K.

There are also benchmarks comparing the two: https://artificialanalysis.ai/models/comparisons/deepseek-v4...