LLMOpen weights

Qwen3 Next 80B A3B Instruct

Alibaba

Updated May 22, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type: LLM
Access: Open weights
Released: September 11, 2025
License: apache_2_0
Context window: 262,144 tokens
Knowledge cutoff: September 30, 2025
Output speed: 161 tok/s
Latency (TTFT): 1.14s
Input: Text
Output: Text
API pricing: $0.09 in · $1.10 out / 1M tokens

Capabilities

Function callingStructured output

Benchmarks

Reasoning

72.9

Coding

MultiPL-E	87.8
Aider Polyglot	49.8
LiveCodeBench	68.4

Math

69.5

Agents

TAU-bench Retail	60.9
TAU-bench Airline	44
τ²-bench Retail	57.3
τ²-bench Airline	45.5

General

MMLU-Pro	80.6
IFEval	87.6
Multi-IF	75.8
Humanity’s Last Exam	7.3

Compare Qwen3 Next 80B A3B Instruct with

vs Sonar Reasoning Pro vs R1 1776 vs Qwen3.7 Max vs Gemini 3.5 Flash

See all Qwen3 Next 80B A3B Instruct alternatives →