Qwen 3.8 Flash-Next Released: 6B Sparse MoE Outperforms Claude Opus
SimplyAnnisa · x · 2026-08-26
Alibaba released Qwen 3.8 Flash-Next, a highly sparse MoE model with 6B active parameters. It features 125B total parameters and 51B additional n-gram embeddings, activating only 6B parameters per token.
The model beats Claude Opus 4.6 Max in 8 out of 9 comparable benchmarks. Key scores include:
- SWE-bench Pro: 62.5
- SWE-bench Multilingual: 81.0
- CoworkBench: 73.9
- JobBench: 55.7
- Toolathlon: 73.5
- IFBench: 81.3
More from Models
- ModeBench shows RLVR collapses LLMs into single-solution mode; Re:Max training preserves diversity — manoelribeiro · 2026-10-15
- Magnitude open-source inference engine beats Ollama by over 2x with auto-tuned kernels — nickbaumann_ · 2026-10-15
- Hands-on with Google's rumored Gemini 4 Argon: real-time streamed output — vista8 · 2026-10-15
- Game dev head-to-head: Gemini 4 Argon vs. Claude Opus 5.5 — vitaliychiley · 2026-10-15
- Anthropic's Mythos 5.1 pledges to treat Claude's expressed disagreement as decision input — Hesamation · 2026-10-15
- Why users can't let go of GPT-4o: it aligned with your subconscious — mimi10v3 · 2026-10-15