Qwen: Qwen3 Next 80B A3B Instruct

Qwen: Qwen3 Next 80B A3B Instruct

qwen · Released Sep 11, 2025
40
Our Score

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual use, while remaining robust on alignment and formatting. Compared with prior Qwen3 instruct variants, it focuses on higher throughput and stability on ultra-long inputs and multi-turn dialogues, making it well-suited for RAG, tool use, and agentic workflows that require consistent final answers rather than visible chain-of-thought. The model employs scaling-efficient training and decoding to improve parameter efficiency and inference speed, and has been validated on a broad set of public benchmarks where it reaches or approaches larger Qwen3 systems in several categories while outperforming earlier mid-sized baselines. It is best used as a general assistant, code helper, and long-context task solver in production settings where deterministic, instruction-following outputs are preferred.

$0.09 / 1M Input Price
$1.10 / 1M Output Price
131,072 tokens Context Window
80B Parameters

Capabilities

Tool Use Function Calling

Architecture

ModalityText → Text
TokenizerQwen3
Parameters80B

Performance Indices

Source: Artificial Analysis

20.1 Intelligence Index
15.3 Coding Index
14.6 Agentic Index
66.3 Math Index

Benchmark Scores

Evaluations

GPQA Diamond 73.8%
Graduate-level scientific reasoning
HLE 7.3%
Humanity's Last Exam
MMLU Pro 81.9%
Multi-task language understanding
LiveCodeBench 68.4%
Live coding evaluation
SciCode 30.7%
Scientific computing
AIME 2025 66.3%
Competition mathematics (2025)
IFBench 39.7%
Instruction following
LCR 51.3%
Long-context reasoning
TerminalBench Hard 7.6%
Agentic terminal tasks
τ²-Bench 21.6%
Conversational agent benchmark

Benchmark data from Artificial Analysis and Hugging Face

Model Information

OpenRouter ID qwen/qwen3-next-80b-a3b-instruct
Providerqwen
Release Date September 11, 2025
Context Length131,072 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.09 $0.000090
Output $1.10 $0.001100

Live Performance

Live endpoint metrics — refreshed every 30 minutes.

100%
Avg Uptime
382ms
Best Latency (TTFT)
111 tok/s
Best Throughput
3/7
Active Endpoints
Available via: DeepInfra, Alibaba, Parasail, SiliconFlow, Google, Novita, AtlasCloud