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.

Original post →

More from Models

Models channel →