DeepSeek v4.1 flash paper figure shows sharp quality jump at 1M-token context
andrew_n_carr · x · 2026-09-19
andrewncarr shares a figure allegedly from the DeepSeek v4.1 flash paper (unverified) showing an extremely sharp quality increase after extending context to 1M tokens, noting similar gains in MiMo v2.6 RL graphs. Takeaway: agents are context hungry.
More from Models
- Muse Spark 1.3 Gets Cheaper Contributor-Tier Optimization With Only 1-2% Benchmark Variance — alexandr_wang · 2026-09-19
- Unreleased Tencent Hunyuan 3.5 Spotted in Early Access on OnSolo, Image Quality Impresses — HeyAmit_ · 2026-09-19
- Auto-Formalizing a 76-Page Paper With Opus 5 High Would Take ~40 Days — kfountou · 2026-09-19
- Open-weight models now take 56% of production token volume, per Vercel index — cramforce · 2026-09-19
- User catches Claude Opus 3 up on recent news, model 'cries' — old vs new AI gap goes viral — teortaxesTex · 2026-09-19
- Unposted demo videos of Gemini 4 Pro reportedly look impressive — ChrisGPT · 2026-09-19