Qwen3 Next 80B A3B (Reasoning)
설명
Qwen3-Next-80B-A3B-Thinking is the thinking variant of the Qwen3-Next series, featuring the same groundbreaking architecture as the instruct model. Leveraging GSPO, it addresses stability and efficiency challenges of hybrid attention + high-sparsity MoE in RL training. It uses Hybrid Attention combining Gated DeltaNet and Gated Attention for efficient ultra-long context modeling, High-Sparsity MoE with 512 experts (10 activated + 1 shared), and Multi-Token Prediction. With 80B total parameters and only 3B activated, it demonstrates outstanding performance on complex reasoning tasks — outperforming Qwen3-30B-A3B-Thinking-2507, Qwen3-32B-Thinking, and even the proprietary Gemini-2.5-Flash-Thinking across multiple benchmarks. Architecture: 48 layers, 15T training tokens, hybrid layout of 12*(3*(Gated DeltaNet->MoE)->(Gated Attention->MoE)). Supports only thinking mode with automatic <think> tag inclusion, may generate longer thinking content.
능력 레이더
전용 과학 벤치마크가 없을 때 Science는 LLM Stats 과학 점수 또는 추론 능력에서 추정합니다.
랭킹
랭킹 데이터가 없습니다
벤치마크 점수 (LLM Stats)
(LLM Stats (zeroeval))Chat
Code
Communication
General
Language
Math
Reasoning
Writing
AA 평가 지수
(Artificial Analysis)AA 평가 데이터가 없습니다
LLM Stats 카테고리 점수
(LLM Stats (zeroeval))가격
속도
속도 데이터가 없습니다
공급자 가격 순위
공급자 가격 순위
3개 공급자
이 모델의 다양한 API 공급자 간 가격 비교.