Alibaba
Qwen3 30B A3B (Non-reasoning)
Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...
Qwen model releasesModel Snapshot
ReleaseApr 28, 2025
Context40,960
Overall
Rank #442 across 566
6.8
Coding
No rank
n/a
Blended Price
Rank #93 across 371
$0.350/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 Speed113.9 tok/s
First Token0.98s
Max Output16,384
Pricing
Blended$0.350/M
Input$0.200/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 6.8 | #442 |
| Artificial Analysis Math Index | math | 21.7 | #207 |
| MMLU-Pro | reasoning | 71.0% | #222 |
| GPQA | reasoning | 51.5% | #390 |
| Humanity's Last Exam |