New todaydeepseek-v4.1POST

DeepSeek V4.1 Flash ranks third in benchmark score drop on new tests

The author says DeepSeek V4.1 Flash shows the third-largest drop from deepswe to frontiercode 2.0, behind Muse Wonder 1.0 and Gemini 4 Argon.

夢アカデミー

@yumeacademyArchived 48 min agoOriginally posted 2026.10.28

夢アカデミー @yumeacademyOriginally posted 2026.10.28

Open original on X

新ベンチリリースされると丸暗記では解けないからbenchmaxxingが一目瞭然なる deepswe v1.1→frontiercode 2.0で⤵️の落差大順(= benchmaxxing酷い順): muse wonder 1.0 Gemini 4 argon deepseek v4.1 flash OpenAI/anthropicの二強とそれ以外の実務能力差が実は拡大してる不都合な真実

This post quotes another post: “FrontierCode 2.0: Gemini 4 Argon drops from top to mid-pack”

x.com/yumeacademy/status/2115251895443054633Archived 2026.10.29 12:06