모델 목록으로
Alibaba독점

Qwen3-Coder-Next

Qwen3-Coder-Next is a programming-specialized foundation model developed by Alibaba. With 80B parameters and a long 256K context window, it enables advanced code generation and analysis.

파라미터

80.0B

컨텍스트

256K

라이선스

https://huggingface.co/Qwen/Qwen2.5-72B/blob/main/LICENSE

출시일

2026-02-03

API 가격

이 모델의 API 가격 정보는 현재 공개되지 않았습니다

강점

  • 80B strong parameter scale
  • 256K extensive context window
  • Advanced programming capabilities

약점

  • Closed license model
  • Large model size up to 48GB
  • High computational resource requirement

활용 사례

  • Large codebase analysis
  • Auto-generating complex features
  • Advanced programming assistance

심층 분석

Release Date

February 2026

Total Parameters

80B

MoE with 512 experts

Active Parameters

3B per token

10 experts + 1 shared active

Layers

48

Hidden Dimension

2,048

Context Window

262,144 tokens

Architecture

Hybrid: Gated DeltaNet + Gated Attention + MoE

Input Price

$0.07-$0.12/1M tokens

Output Price

$0.30-$0.75/1M tokens

SWE-bench Verified

70.6

Competitive with DeepSeek-V3.2 (70.2) at 671B

강점

  • SWE-bench 70.6 at only 3B active parameters — competitive with 671B DeepSeek-V3.2 (70.2)
  • Incredibly cheap: $0.07/$0.30 on Alibaba Cloud, $0.12/$0.75 on third-party providers
  • Trained on 800K verifiable executable tasks with RL for long-horizon agent coding
  • 256K context for keeping entire codebases in a single session
  • Apache 2.0 licensed — available for self-hosting and fine-tuning

약점

  • Non-thinking mode only — does not support blocks
  • SWE-bench Pro 44.3% leaves significant room for improvement on harder tasks
  • Terminal-Bench 36.2% is notably lower than larger coding models
  • 80B total parameters still require ~46GB VRAM at 4-bit quantization
  • Specialized for coding — may underperform on general knowledge tasks

경쟁사 비교

ModelArenaSWEGPQAPrice
DeepSeek-V3.2~143070.2~82$0.14/$0.28
GLM-4.7~142074.2~80Proprietary
Qwen3-Coder-Next~140070.6~75$0.07/$0.30
Claude Sonnet 4.6~1470~78~87$3.00/$15.00
GPT-4o~1450~72~85$2.50/$10.00

Qwen3-Coder-Next is an open-weight coding-specialized model from February 2026, built on the Qwen3-Next-80B-A3B backbone with 80B total parameters and only 3B active per token. It achieves SWE-bench Verified 70.6 — competitive with the 671B DeepSeek-V3.2 — at a fraction of the compute cost. Trained on 800K executable tasks with reinforcement learning, it is purpose-built for agentic coding workflows, IDE copilots, and long-horizon development tasks.

분석 생성일: 2026-05-24