AI Navigate
インサイト最新記事AI大全カオスマップ

Alibaba's open model Qwen3.6 leads Google's Gemma 4 across agentic coding benchmarks

THE DECODER / 4/18/2026

📰 NewsSignals & Early TrendsIndustry & Market MovesModels & Research
Read original →
共有:

Key Points

  • Alibaba released the open-source Qwen3.6-35B-A3B, which activates only three parameters per step out of 35B while still delivering strong performance.
  • On agentic coding and reasoning benchmarks, Qwen3.6-35B-A3B outperforms Google’s Gemma 4-31B despite using fewer active parameters.
  • The results highlight that efficient routing/activation strategies can improve benchmark outcomes relative to larger or conventionally configured models.
  • The comparison suggests growing competitiveness among major open(-weight) model ecosystems for practical coding agent tasks.

Chromatic glitch pattern of overlapping hexagrams that conveys a lively retro-futurism through RGB color shifts.

Alibaba's new open-source Qwen3.6-35B-A3B activates just three of its 35 billion parameters at a time, yet beats Google's larger Gemma 4-31B on coding and reasoning benchmarks.

The article Alibaba's open model Qwen3.6 leads Google's Gemma 4 across agentic coding benchmarks appeared first on The Decoder.

💡 Insights using this article

This article is featured in our daily AI news digest — key takeaways and action items at a glance.

📅 4/18DailyView insight →

関連おすすめサービス

※当サイトはアフィリエイト広告を利用しています
🎧

Notta搭載AI議事録イヤホン ZENCHORD1

AI時代の仕事術。Notta搭載で会議の議事録を自動生成するスマートイヤホン。

🎙️

AI搭載ボイスレコーダー Plaud

世界100万人が愛用。AIで文字起こし・要約を自動化するボイスレコーダー。

🖼️

画像高画質化AIツール Aiarty Image Enhancer

AIで画像を高画質化。写真・イラストを簡単にアップスケール。