DeepSeek 1017 'destroys' Opus 5.5, Astra and Sol on complex machine-building task
teortaxesTex · x · 2026-10-23
A user reports DeepSeek 1017 absolutely crushed Opus 5.5, Astra, and Sol on a complex machine-building task — the frontier models weren't just lacking taste, they were 'inept'. The author adds the caveat that 1017 isn't generally better, but the extent of the domination was shocking: all three frontier models had many hours and attempts (roughly 3 days' worth of Pro quota) and still failed, suggesting great distillation on DeepSeek's side.
Related event: DeepSeek 1017 Beats Opus 5.5 and Other Frontier Models in Hands-On Test(2 posts)→
More from Models
- NVIDIA releases Nemotron 3.5 Bolt E4B, a 4GB open model for on-device conversational agents — NVIDIAAI · 2026-10-23
- NVIDIA releases open Nemotron 3.5 Bolt E4B 4GB with weights, data and recipes — NVIDIAAI · 2026-10-23
- Gemini 'Argon' bug reportedly fails to analyze uploaded audio files — Numerous-Campaign844 · 2026-10-23
- 2-bit quantized DeepSeek 4.1 Flash tested locally: KDL degrades but still works — bakawolf123 · 2026-10-23
- KOL predicts K3.1 benchmarks sight unseen: benchmaxxed, below Sonnet in practice — teortaxesTex · 2026-10-23
- Sam Altman: OpenAI's Best Internal Model Won't Be Released Anytime Soon — rohanpaul_ai · 2026-10-23