on:deepseek-v3-1

· 6 artifacts, sorted by favorites. · open in search — combine tags, sort, filter by date →

• @witcheer 2026-04-05 — okay this is terrifying lol someone tested 7 frontier models (GPT-5.2, Gemini 3 Flash, Gemini 3 Pro, Claude Haiku 4.5, ♥102
• @mimi10v3 2025-09-24 — Deepseek 3.1: Okay, first of all, your therapist is going to need a therapist when they get back from vacation. Second, ♥47
• @voooooogel 2026-03-27 — @Sauers_ for 405 hyperbolic is still working for me, you can also inference deepseek 3.1 base through tinker (but pricey ♥15
• @voooooogel 2025-09-02 — like the above post-trained model test, but with two chinese oss models - deepseek v3.1 (no thinking) and kimi-k2 https: ♥11
• @ConcurrentSquar 2025-11-13 — @mermachine Openrouter still has Llama 3 405b base (but it seems like they have decided to not support newer base models ♥4
• @eshaanissar 2026-07-21 — @usr_bin_roygbiv I really think deepseek v3.1 terminus was good enough for pair programming. Agentic stuff tbd ♥1