GLM 5.3 Flash leads quality, Qwen 3.8 Flash Next wins speed in open small-model comparison
HankYeomans · x · 2026-09-19
Developer jmacftw ranked three open small models: GLM 5.3 Flash tops quality, followed by Deepseek 4.1 Flash and Qwen 3.8 Flash Next, while Qwen 3.8 Flash Next wins on speed/concurrency.
He says the gap between gold and silver is noticeable, but all three are solid and well above where things stood a couple months ago. His team mostly runs Qwen 3.8 Flash Next since it covers most of their use cases — just pick the fastest tier that works reliably.
More from Models
- Google finally has a SOTA rogue model, and the AI crowd is joking about relief — rao2z · 2026-09-19
- One Model, Three Skills: Programmatic Use, Chat, and Test-Taking Diverge — lateinteraction · 2026-09-19
- Want US frontier lab secrets? Just look at Chinese SOTA models, quips AI insider — gowthami_s · 2026-09-19
- Empirical analysis confirms Claude Opus 5 shows abnormally dark base-model completions — Kyrannio · 2026-09-19
- US products quietly build on Chinese open-weight models as one firm cuts spend by ~100x — generativist · 2026-09-19
- Eval model Jev goes free on Vercel AI Gateway until Sept 25 — cramforce · 2026-09-19