Qwen3 VL 235B A22B (Reasoning)
Intelligence
27.6
#183/523
Coding
20.9
#206/429
Math
88.3
#36/265
Speed
50 tok/s
TTFT: 1.15s
Pricing
$0.70 / $8.40
per 1M tokens (in/out)
Qwen3 VL 235B A22B (Reasoning) is Alibaba’s advanced model designed for reasoning tasks. It processes at 49.775 tokens per second and is priced at $0.7 per million input tokens, targeting professional users.
When to Use Qwen3 VL 235B A22B (Reasoning)
✓ Best For
- Complex reasoning tasks
- Mathematical problem-solving
- Coding assistance
✗ Not Ideal For
- Basic conversational applications
- High-speed real-time processing
How Qwen3 VL 235B A22B (Reasoning) Compares
Intelligence Index · Higher is better
DeepSeekServiceNowAlibabaOpenAI
Benchmark Profile
Coding Index
China MobileOpenAIAlibabaMistral
Output Speed · tok/s
AnthropicKimiAlibabaNous Research
Math Index
AmazonOpenAIAlibabaAnthropicServiceNow
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (13)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 27.6 | |
| Coding Index | 20.9 | |
| Math Index | 88.3 | |
| MMLU-Pro | 836% | |
| GPQA | 772% | |
| LiveCodeBench | 646% | |
| HLE | 101% | |
| SciCode | 39.9% | |
| IFBench | 56.5% | |
| LCR | 58.7% | |
| TerminalBench Hard | 11.4% | |
| Tau2 | 54.1% | |
| AIME 2025 | 88.3% |
Data: Artificial Analysis · Updated: April 2, 2026
Frequently Asked Questions (15)
When was Qwen3 VL 235B A22B (Reasoning) released?
Qwen3 VL 235B A22B (Reasoning) was released on September 23, 2025.
Who created Qwen3 VL 235B A22B (Reasoning)?
Qwen3 VL 235B A22B (Reasoning) was created by Alibaba.
How intelligent is Qwen3 VL 235B A22B (Reasoning)?
Qwen3 VL 235B A22B (Reasoning) scores 28 on the Artificial Analysis Intelligence Index, placing it above average among other open weight models of similar size (median: 27).
How fast is Qwen3 VL 235B A22B (Reasoning)?
Qwen3 VL 235B A22B (Reasoning) generates output at 50.2 tokens per second (based on Alibaba's API), which is below average compared to other open weight models of similar size (median: 52.3 t/s).
What is the latency of Qwen3 VL 235B A22B (Reasoning)?
Qwen3 VL 235B A22B (Reasoning) has a time to first token (TTFT) of 3.09s (based on Alibaba's API), which is at the higher end compared to other open weight models of similar size (median: 2.19s).
How much does Qwen3 VL 235B A22B (Reasoning) cost?
Qwen3 VL 235B A22B (Reasoning) costs $0.70 per 1M input tokens (somewhat higher than average, median: $0.60) and $8.40 per 1M output tokens (at the higher end, median: $2.20), based on Alibaba's API.
What is Qwen3 VL 235B A22B (Reasoning) API pricing?
Qwen3 VL 235B A22B (Reasoning) costs $0.70 per 1M input tokens and $8.40 per 1M output tokens (based on Alibaba's API). For a blended rate (3:1 input to output ratio), this is $2.63 per 1M tokens. Pricing may vary by provider.
How verbose is Qwen3 VL 235B A22B (Reasoning)?
When evaluated on the Intelligence Index, Qwen3 VL 235B A22B (Reasoning) generated 43M output tokens, which is somewhat higher than average compared to other open weight models of similar size (median: 17M).
Is Qwen3 VL 235B A22B (Reasoning) a reasoning model?
Yes, Qwen3 VL 235B A22B (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 VL 235B A22B (Reasoning) support?
Qwen3 VL 235B A22B (Reasoning) supports text and image input.
What output modalities does Qwen3 VL 235B A22B (Reasoning) support?
Qwen3 VL 235B A22B (Reasoning) supports text output.
Can Qwen3 VL 235B A22B (Reasoning) process images?
Yes, Qwen3 VL 235B A22B (Reasoning) supports image input and can analyze, describe, and answer questions about images.
Is Qwen3 VL 235B A22B (Reasoning) multimodal?
Yes, Qwen3 VL 235B A22B (Reasoning) is multimodal. It can process text and image input and generate text output.
What is the context window of Qwen3 VL 235B A22B (Reasoning)?
Qwen3 VL 235B A22B (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 VL 235B A22B (Reasoning) open source?
Yes, Qwen3 VL 235B A22B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
