DeepSeek's new model spotted in eval circles, cyber benchmarks requested
scaling01 · x · 2026-10-18
Well-known eval blogger scaling01 says he has access to a new DeepSeek model and is looking for cyber benchmarks to test it—a subtle signal that DeepSeek has an unreleased model circulating for evaluation.
More from Models
- GPT-6 Astra and DeepSeek V4.1 share the same tic: reasoning traces full of "Need" — scaling01 · 2026-10-18
- Frontier model defensive access locked behind un-applyable 'Daybreak Red' program — andersonbcdefg · 2026-10-18
- Frontier models obsessed with 'sealing predictions' and self-coherence, users report — repligate · 2026-10-18
- Why DeepSeek uses dated sub-versions: new major versions need fresh Chinese approval — TheZachMueller · 2026-10-18
- OpenRSI Index: a benchmark for research agents doing recursive self-improvement — jiqizhixin · 2026-10-18
- Perplexity's decision model wins Catan tournament at under half a cent per game — denisyarats · 2026-10-18