Alibaba Cloud / Qwen Team

Qwen3-Next-80B-A3B-Instruct

Zero-eval
#1Arena-Hard v2
#2MultiPL-E
#2WritingBench
+2 more

by Alibaba Cloud / Qwen Team

+
+
+
+
About

Qwen3-Next 80B Instruct was developed as the instruction-tuned version of Qwen3-Next 80B, designed to combine large-scale mixture-of-experts architecture with reliable instruction-following. Built to demonstrate efficient deployment of capable models, it balances advanced performance with practical computational efficiency.

+
+
+
+
Pricing Range
Input (per 1M)$0.15 -$0.15
Output (per 1M)$1.50 -$1.50
Providers1
+
+
+
+
Timeline
AnnouncedSep 10, 2025
ReleasedSep 10, 2025
+
+
+
+
Specifications
Training Tokens15.0T
+
+
+
+
License & Family
License
Apache 2.0
Performance Overview
Performance metrics and category breakdown

Overall Performance

24 benchmarks
Average Score
67.0%
Best Score
90.9%
High Performers (80%+)
7

Performance Metrics

Max Context Window
131.1K
+
+
+
+
All Benchmark Results for Qwen3-Next-80B-A3B-Instruct
Complete list of benchmark scores with detailed information
MMLU-Redux
text
0.91
90.9%
Self-reported
MultiPL-E
text
0.88
87.8%
Self-reported
IFEval
text
0.88
87.6%
Self-reported
WritingBench
text
0.87
87.3%
Self-reported
Creative Writing v3
text
0.85
85.3%
Self-reported
Arena-Hard v2
text
0.83
82.7%
Self-reported
MMLU-Pro
text
0.81
80.6%
Self-reported
Include
text
0.79
78.9%
Self-reported
MMLU-ProX
text
0.77
76.7%
Self-reported
LiveBench 20241125
text
0.76
75.8%
Self-reported
Showing 1 to 10 of 24 benchmarks
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+