Home/Models/Qwen3 Next 80B A3B Instruct
Alibaba Qwen logo

Qwen3 Next 80B A3B Instruct

by Alibaba Qwen · Released Sep 2025

Open Source
50.0
avg score
Rank #109
Compare
Better than 53% of all models
Context
262K tokens (~131 books)
Input $/1M
$0.09
Output $/1M
$1.10
Type
text
License
Open Source
Benchmarks
18 tested
Data updated today
About

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...

Tested on 18 benchmarks with 54.4% average. Top scores: Chatbot Arena Elo — Overall (1401.6%), OpenCompass — IFEval (87.6%), OpenCompass — MMLU-Pro (81.3%).

Looking for similar performance at lower cost?
Gemma 2 9B scores 50.3 (101% as good) at $0.03/1M input · 67% cheaper
Capabilities
coding
44.3
#87 globally
reasoning
52.3
#44 globally
math
69.7
#33 globally
knowledge
52.9
#85 globally
speed
27.5
#50 globally
language
57.7
#93 globally
Benchmark Scores
Compare All
Tested on 18 benchmarks · Ranked across 7 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
LiveBench — Coding

Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.

68.2
OpenCompass — LiveCodeBenchV6

OpenCompass Live Code Bench v6. Fresh competitive programming problems to evaluate code generation without memorization.

54.8
LiveBench — Agentic Coding

LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.

10.0
LiveBench — Reasoning

Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.

54.8
LiveBench — Data Analysis

Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.

49.8
LiveBench — Mathematics

Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.

70.2
OpenCompass — AIME2025

OpenCompass evaluation on AIME 2025 problems. Tests mathematical reasoning on fresh competition problems.

69.2
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · Alibaba Qwen Qwen 3
See the full Qwen 3 family →
Links
Documentation
Community
BenchGecko API
qwen3-next-80b-a3b-instruct
Specifications
  • Typetext
  • Context262K tokens (~131 books)
  • ReleasedSep 2025
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.001
Available On
Alibaba Qwen logoAlibaba Qwen$0.09
Share & Export
Tweet
Qwen3 Next 80B A3B Instruct is an open-source text AI model by Alibaba Qwen, released in September 2025. It has an average benchmark score of 50.0. Context window: 262K tokens.