Qwen3.5 122B A10B (Reasoning)
Intelligence
41.6
#77/523
Coding
34.7
#96/429
Math
—
Speed
160 tok/s
TTFT: 1.03s
Pricing
$0.40 / $3.20
per 1M tokens (in/out)
Qwen3.5-122B-A10B is a multimodal Mixture-of-Experts model with 122 billion total parameters and 10 billion activated parameters. It combines strong reasoning, coding, long-context, and visual understanding performance with production-friendly efficiency and a native 262K context window.
Qwen3.5 122B A10B (Reasoning) is Alibaba’s advanced model designed for reasoning tasks. It processes at 160.153 tokens per second and is priced at $0.4 per million input tokens, targeting professional users.
When to Use Qwen3.5 122B A10B (Reasoning)
✓ Best For
- Natural language understanding
- Complex reasoning tasks
- Coding assistance
✗ Not Ideal For
- High-speed applications requiring low latency
- Basic arithmetic calculations
How Qwen3.5 122B A10B (Reasoning) Compares
Intelligence Index · Higher is better
OpenAIDeepSeekAlibabaXiaomixAI
Benchmark Profile
Coding Index
AlibabaKimiOpenAIStepFun
Output Speed · tok/s
AlibabaAnthropicNVIDIA
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (9)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 41.6 | |
| Coding Index | 34.7 | |
| GPQA | 857% | |
| HLE | 234% | |
| SciCode | 42% | |
| IFBench | 75.7% | |
| LCR | 66.7% | |
| TerminalBench Hard | 31.1% | |
| Tau2 | 93.6% |
Data: Artificial Analysis · Updated: April 10, 2026
Frequently Asked Questions (15)
When was Qwen3.5 122B A10B (Reasoning) released?
Qwen3.5 122B A10B (Reasoning) was released on February 24, 2026.
Who created Qwen3.5 122B A10B (Reasoning)?
Qwen3.5 122B A10B (Reasoning) was created by Alibaba.
How intelligent is Qwen3.5 122B A10B (Reasoning)?
Qwen3.5 122B A10B (Reasoning) scores 42 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 15).
How fast is Qwen3.5 122B A10B (Reasoning)?
Qwen3.5 122B A10B (Reasoning) generates output at 122.7 tokens per second (based on Alibaba's API), which is above average compared to other open weight models of similar size (median: 77.6 t/s).
What is the latency of Qwen3.5 122B A10B (Reasoning)?
Qwen3.5 122B A10B (Reasoning) has a time to first token (TTFT) of 2.36s (based on Alibaba's API), which is somewhat higher than average compared to other open weight models of similar size (median: 1.90s).
How much does Qwen3.5 122B A10B (Reasoning) cost?
Qwen3.5 122B A10B (Reasoning) costs $0.40 per 1M input tokens (better than average, median: $0.38) and $3.20 per 1M output tokens (at the higher end, median: $0.82), based on Alibaba's API.
What is Qwen3.5 122B A10B (Reasoning) API pricing?
Qwen3.5 122B A10B (Reasoning) costs $0.40 per 1M input tokens and $3.20 per 1M output tokens (based on Alibaba's API). For a blended rate (3:1 input to output ratio), this is $1.10 per 1M tokens. Pricing may vary by provider.
How verbose is Qwen3.5 122B A10B (Reasoning)?
When evaluated on the Intelligence Index, Qwen3.5 122B A10B (Reasoning) generated 91M output tokens, which is at the higher end compared to other open weight models of similar size (median: 15M).
Is Qwen3.5 122B A10B (Reasoning) a reasoning model?
Yes, Qwen3.5 122B A10B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
What input modalities does Qwen3.5 122B A10B (Reasoning) support?
Qwen3.5 122B A10B (Reasoning) supports text and image input.
What output modalities does Qwen3.5 122B A10B (Reasoning) support?
Qwen3.5 122B A10B (Reasoning) supports text output.
Can Qwen3.5 122B A10B (Reasoning) process images?
Yes, Qwen3.5 122B A10B (Reasoning) supports image input and can analyze, describe, and answer questions about images.
Is Qwen3.5 122B A10B (Reasoning) multimodal?
Yes, Qwen3.5 122B A10B (Reasoning) is multimodal. It can process text and image input and generate text output.
What is the context window of Qwen3.5 122B A10B (Reasoning)?
Qwen3.5 122B A10B (Reasoning) has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Is Qwen3.5 122B A10B (Reasoning) open source?
Yes, Qwen3.5 122B A10B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
