User claims DeepSeek V4 Pro is mis-trained: cheaper Flash beats it
karminski3 · x · 2026-08-18
A Chinese user reports (unconfirmed) that in the DeepSeek V4 lineup, the much cheaper V4 Flash outperforms V4 Pro on reasoning, and the lower-effort V4 Pro High beats Pro Max. V4 Pro still writes better prose, but trails Opus 4.6 by a wide margin. The poster also asks for recommendations on writing benchmarks.
More from Models
- Meta's coding-optimized open-weight Muse Spark Open lands on Modal with 1M context — AAAzzam · 2026-10-16
- Google launches Gemini 4 Argon frontier model on Cloud with 10 official demos — Saboo_Shubham_ · 2026-10-16
- RL practitioner: ~10,000 tasks still stump every frontier coding model — max_paperclips · 2026-10-16
- SpecID eval falls: Gemini 3.5 Flash scores 67%, beating its human creator at Zimbabwean species ID — johnowhitaker · 2026-10-16
- Researcher criticizes Claude for lecturing users and refusing critical takes on tech firms — BlancheMinerva · 2026-10-16
- Chart: Meta went 492 days without an open-weight release before Muse Spark Open — demian_ai · 2026-10-16