Alibaba's Qwen3-Coder-Next achieves 70.6 on SWE-Bench with sparse MoE

Alibaba's Qwen3-Coder-Next, an 80 billion parameter model with 3 billion active parameters, has achieved a 70.6 score on the SWE-Bench Verified benchmark. This performance is notable as it rivals top closed-source models while offering downloadable weights under the Apache 2.0 license. The model employs a sparse Mixture-of-Experts architecture and a hybrid attention mechanism, combining linear attention for long contexts with standard attention for global context reconstruction. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Sets a new SOTA for open-source coding models on SWE-Bench, making advanced coding assistance more accessible.

RANK_REASON The cluster details a new open-source model release with benchmark performance metrics. [lever_c_demoted from research: ic=1 ai=1.0]

Read on dev.to — LLM tag →

• Alibaba
• Apache 2.0
• Mixture-of-Experts
• Qwen3-Coder-Next
• SWE-Agent
• SWE-Bench Verified

• model release
• paper
• product