Qwen3 Coder 30B A3B Instruct
Intelligence
20
#258/523
Coding
19.4
#217/429
Math
29
#189/265
Speed
26 tok/s
TTFT: 1.44s
Pricing
$0.45 / $2.25
per 1M tokens (in/out)
Qwen3 Coder 30B A3B Instruct by Alibaba is designed for coding and mathematical tasks. It processes at 25.935 tokens per second and is priced at $0.45 per million input tokens, targeting professional users.
When to Use Qwen3 Coder 30B A3B Instruct
✓ Best For
- Software development and coding assistance.
- Mathematical problem solving.
- Instruction-based tasks requiring high accuracy.
✗ Not Ideal For
- General conversational AI tasks.
- Applications requiring extremely low latency.
How Qwen3 Coder 30B A3B Instruct Compares
Intelligence Index · Higher is better
Trillion LabsOpenAIAlibaba
Benchmark Profile
Coding Index
xAIAnthropicAlibabaPrime IntellectNVIDIA
Output Speed · tok/s
Nous ResearchAlibaba
Math Index
UpstageMistralAlibaba
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (15)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 20 | |
| Coding Index | 19.4 | |
| Math Index | 29 | |
| MMLU-Pro | 706% | |
| GPQA | 516% | |
| LiveCodeBench | 403% | |
| HLE | 4% | |
| SciCode | 27.8% | |
| IFBench | 32.7% | |
| LCR | 29% | |
| TerminalBench Hard | 15.2% | |
| Tau2 | 34.5% | |
| AIME | 29.7% | |
| AIME 2025 | 29% | |
| MATH 500 | 89.3% |
Data: Artificial Analysis · Updated: April 2, 2026
Frequently Asked Questions (15)
When was Qwen3 Coder 30B A3B Instruct released?
Qwen3 Coder 30B A3B Instruct was released on July 31, 2025.
Who created Qwen3 Coder 30B A3B Instruct?
Qwen3 Coder 30B A3B Instruct was created by Alibaba.
How intelligent is Qwen3 Coder 30B A3B Instruct?
Qwen3 Coder 30B A3B Instruct scores 20 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 12).
How fast is Qwen3 Coder 30B A3B Instruct?
Qwen3 Coder 30B A3B Instruct generates output at 25.7 tokens per second (based on Alibaba's API), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 97.8 t/s).
What is the latency of Qwen3 Coder 30B A3B Instruct?
Qwen3 Coder 30B A3B Instruct has a time to first token (TTFT) of 2.61s (based on Alibaba's API), which is at the higher end compared to other open weight non-reasoning models of similar size (median: 1.62s).
How much does Qwen3 Coder 30B A3B Instruct cost?
Qwen3 Coder 30B A3B Instruct costs $0.45 per 1M input tokens (at the higher end, median: $0.15) and $2.25 per 1M output tokens (at the higher end, median: $0.30), based on Alibaba's API.
What is Qwen3 Coder 30B A3B Instruct API pricing?
Qwen3 Coder 30B A3B Instruct costs $0.45 per 1M input tokens and $2.25 per 1M output tokens (based on Alibaba's API). For a blended rate (3:1 input to output ratio), this is $0.90 per 1M tokens. Pricing may vary by provider.
How verbose is Qwen3 Coder 30B A3B Instruct?
When evaluated on the Intelligence Index, Qwen3 Coder 30B A3B Instruct generated 13M output tokens, which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 5.3M).
Is Qwen3 Coder 30B A3B Instruct a reasoning model?
No, Qwen3 Coder 30B A3B Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Qwen3 Coder 30B A3B Instruct support?
Qwen3 Coder 30B A3B Instruct supports text input.
What output modalities does Qwen3 Coder 30B A3B Instruct support?
Qwen3 Coder 30B A3B Instruct supports text output.
Can Qwen3 Coder 30B A3B Instruct process images?
No, Qwen3 Coder 30B A3B Instruct does not support image input. It can only process text.
Is Qwen3 Coder 30B A3B Instruct multimodal?
No, Qwen3 Coder 30B A3B Instruct is not multimodal. It only supports text input.
What is the context window of Qwen3 Coder 30B A3B Instruct?
Qwen3 Coder 30B A3B Instruct has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Is Qwen3 Coder 30B A3B Instruct open source?
Yes, Qwen3 Coder 30B A3B Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.
