Qwen3 Coder Next
Intelligence
28.3
#176/523
Coding
22.9
#188/429
Math
—
Speed
158 tok/s
TTFT: 888.00s
Pricing
$0.35 / $1.20
per 1M tokens (in/out)
Qwen3 Coder Next is Alibaba’s model designed for coding tasks and mathematical computations. It processes at 158.259 tokens per second and is priced at $0.35 per million input tokens, targeting developers and data scientists.
When to Use Qwen3 Coder Next
✓ Best For
- Automating coding tasks.
- Performing mathematical computations.
- Supporting software development projects.
✗ Not Ideal For
- Users needing high-speed processing for real-time applications.
- Tasks requiring advanced mathematical capabilities.
How Qwen3 Coder Next Compares
Intelligence Index · Higher is better
NVIDIADeepSeekAlibabaServiceNow
Benchmark Profile
Coding Index
InclusionAILG AI ResearchAlibabaOpenAIMistral
Output Speed · tok/s
Reka AISarvamAlibabaOpenAIMeta
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (9)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 28.3 | |
| Coding Index | 22.9 | |
| GPQA | 737% | |
| HLE | 93% | |
| SciCode | 32.3% | |
| IFBench | 35.2% | |
| LCR | 40% | |
| TerminalBench Hard | 18.2% | |
| Tau2 | 79.5% |
Data: Artificial Analysis · Updated: March 27, 2026
Frequently Asked Questions (15)
When was Qwen3 Coder Next released?
Qwen3 Coder Next was released on February 3, 2026.
Who created Qwen3 Coder Next?
Qwen3 Coder Next was created by Alibaba.
How intelligent is Qwen3 Coder Next?
Qwen3 Coder Next scores 28 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 13).
How fast is Qwen3 Coder Next?
Qwen3 Coder Next generates output at 147.7 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight non-reasoning models of similar size (median: 60.3 t/s).
What is the latency of Qwen3 Coder Next?
Qwen3 Coder Next has a time to first token (TTFT) of 1.33s (based on the median across providers serving the model), which is very competitive compared to other open weight non-reasoning models of similar size (median: 1.65s).
How much does Qwen3 Coder Next cost?
Qwen3 Coder Next costs $0.35 per 1M input tokens (better than average, median: $0.52) and $1.20 per 1M output tokens (somewhat higher than average, median: $0.81), based on the median across providers serving the model.
What is Qwen3 Coder Next API pricing?
Qwen3 Coder Next costs $0.35 per 1M input tokens and $1.20 per 1M output tokens (based on the median across providers serving the model). For a blended rate (3:1 input to output ratio), this is $0.60 per 1M tokens. Pricing may vary by provider.
How verbose is Qwen3 Coder Next?
When evaluated on the Intelligence Index, Qwen3 Coder Next generated 26M output tokens, which is at the higher end compared to other open weight non-reasoning models of similar size (median: 3.8M).
Is Qwen3 Coder Next a reasoning model?
No, Qwen3 Coder Next is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Qwen3 Coder Next support?
Qwen3 Coder Next supports text input.
What output modalities does Qwen3 Coder Next support?
Qwen3 Coder Next supports text output.
Can Qwen3 Coder Next process images?
No, Qwen3 Coder Next does not support image input. It can only process text.
Is Qwen3 Coder Next multimodal?
No, Qwen3 Coder Next is not multimodal. It only supports text input.
What is the context window of Qwen3 Coder Next?
Qwen3 Coder Next 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 Next open source?
Yes, Qwen3 Coder Next is open weights. The model weights are publicly available and can be downloaded for self-hosting.
