8 engineers on Hacker News describe using GLM first-hand: 3 endorse it, 1 regret it, 1 are mixed.
“the models I primarily use are DeepSeek V4.1 Flash 1017 and GLM 5.3 Flash. If you use skills to their full potential they feel SotA to me”
endorse · personal · tomburgs · 2026-11-05 · source ↗ · wrong label?“GLM, Qwen and Deepseek are incredible tool callers, but their prose is insufferable.”
mixed · personal · guhcampos · 2026-11-05 · source ↗ · wrong label?“In many cases, it was superior to Gemini 3 Pro... What I did is set the default models to 4.6 (now 4.7)”
endorse · personal · csomar · 2025-12-23 · source ↗ · wrong label?“GLM's code was generally about twice as long, and about 30% less readable than Sonnet's even at the same length.”
regret · personal · andai · 2025-12-23 · source ↗ · wrong label?“We use GLM. It seems pretty good.”
endorse · personal · peaton · 2014-11-13 · source ↗ · wrong label?“I've tested it against GLM-5.3-flash and Opus 5.5. DS 4.1 comes out tops for me.”
neutral · personal · ilitirit · 2026-10-17 · source ↗ · wrong label?“We used to run GLM-5 class models but have now changed to smaller ones as we're able to serve more concurrent users”
neutral · production · nejch · 2026-08-30 · source ↗ · wrong label?“so we could switch between DeepSeek v4, GLM 5.1, and Qwen 3.7 models”
neutral · production · ignoramous · 2026-06-03 · source ↗ · wrong label?