Alibaba • LLM
Qwen: Qwen3.5-122B-A10B by Alibaba
Context Window
262K tokens
Input Price/1M
$0.40
Output Price/1M
$3.20
Parameters
—
Speed
137 tok/s
Latency (TTFT)
2.4s
Max Output
82K tokens
Qwen: Qwen3.5-122B-A10B results on the main AI model evaluation benchmarks. Higher scores indicate better performance.
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Terminal-Bench Hard | 31.0 | 100.0 | — |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA Coding Index | 45.7 | 100.0 | Artificial Analysis official API |
| SciCode | 42.0 | 100.0 | — |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA-LCR | 67.0 | 100.0 | — |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| LMArena Elo | 1417.0 | 2000.0 | Crowdsourced blind pairwise comparisons |
| AA Intelligence Index | 32.8 | 100.0 | Artificial Analysis official API |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| GPQA Diamond | 86.0 | 100.0 | Artificial Analysis official API |
| IFBench | 76.0 | 100.0 | — |
| HLE | 23.0 | 100.0 | — |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Tau²-Bench | 94.0 | 100.0 | — |
Qwen: Qwen3.5-122B-A10B is an AI model developed by Alibaba, classified as a large language model (LLM). It is a multimodal model, capable of processing text, images, and potentially other media types. As an open source model, it is available for download, customization, and on-premises deployment. With a context window of 262K tokens, it is suitable for processing long documents such as contracts, books, and complete codebases.
Qwen: Qwen3.5-122B-A10B is usage-based, priced at $0.4/1M input tokens and $3.2/1M output tokens. For context: 1 million tokens is approximately 750,000 words, or about 10 average-length books. At this aggressive price point, it is one of the most cost-effective options on the market, ideal for high-volume applications like chatbots, bulk document analysis, and automation.
Qwen: Qwen3.5-122B-A10B was evaluated on 10 different benchmarks, covering categories like Agentic, Coding, Long Context, overall, Reasoning, Tool Use. Results show exceptional performance across available evaluations.
It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.
Qwen: Qwen3.5-122B-A10B is suitable for a wide range of AI applications: long document analysis (contracts, legal proceedings, codebases), multimodal processing combining text and images, high-volume chatbots and automated support, text generation, summarization, translation, and general assistance.
In the 2026 AI model ecosystem, Qwen: Qwen3.5-122B-A10B competes directly with similarly capable models. Alibaba competes in this segment against OpenAI, Anthropic, Google, and Meta. The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.
For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.
Qwen: Qwen3.5-122B-A10B is an AI model developed by Alibaba. It is a language model (LLM), with multimodal support (text, image and more), open source.
Qwen: Qwen3.5-122B-A10B costs $0.4/1M input tokens and $3.2/1M output tokens. For heavy usage (e.g., a chatbot handling 100k messages/month), costs can range from $10 to $1,000 depending on volume.
In available benchmarks, Qwen: Qwen3.5-122B-A10B scored: Terminal-Bench Hard: 31/100, AA Coding Index: 45.7/100, SciCode: 42/100. See the full table above for a detailed comparison.
Yes, Qwen: Qwen3.5-122B-A10B is an open source model. You can deploy it on-premises, customize it via fine-tuning, and maintain full control over your data. Check the official repository for the specific license.
Qwen: Qwen3.5-122B-A10B excels at general-purpose language tasks. With its large context window, it handles long documents, codebases, and extended conversations.
Last updated: August 10, 2026 • View methodology →