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%).
Gemma 2 9B scores 50.3 (101% as good) at $0.03/1M input · 67% cheaper
Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.
OpenCompass Live Code Bench v6. Fresh competitive programming problems to evaluate code generation without memorization.
LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.
Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.
Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.
Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.
OpenCompass evaluation on AIME 2025 problems. Tests mathematical reasoning on fresh competition problems.
- Typetext
- Context262K tokens (~131 books)
- ReleasedSep 2025
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.001