Alibaba
Qwen3 Next 80B A3B Instruct
A new generation of open-source, non-thinking mode model powered by Qwen3. This version demonstrates superior Chinese text understanding, augmented logical reasoning, and enhanced capabilities in text generation tasks over the previous iteration (Qwen3-235B-A22B-Instruct-2507).
Qwen model releasesModel Snapshot
TypeLanguage
ReleaseSep 11, 2025
Context262,144
Tagstool-use
Overall
Rank #331 across 600
13.7
Coding
No rank
n/a
Blended Price
Rank #184 across 379
$0.875/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed186.5 tok/s
First Token0.99s
Max Output262,144
Pricing
Blended$0.875/M
Input$0.500/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 13.7 | #331 |
| Artificial Analysis Math Index | math | 66.3 | #105 |
| MMLU-Pro | reasoning | 81.9% | #71 |
| GPQA | reasoning | 73.8% | #230 |
| Humanity's Last Exam |