AIThe Decoder1h ago
Alibaba's open model Qwen3.6 leads Google's Gemma 4 across agentic coding benchmarks
TL;DRAlibaba's efficient open-source model outperforms Google's on coding tasks using fewer active parameters.
Why it matters: Open-source models matching or beating Google's suggests competitive pressure and democratizes access to capable AI for developers.
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…
Read full articleSource: The Decoder · Opens in new tab