ModelBeat
Models/Qwen3.5-122B-A10B
All models
A

Alibaba: Qwen3.5-122B-A10B

qwen/qwen3.5-122b-a10b

Qwen3.5-122B-A10B is Alibaba’s open-weights AI model, released Feb 24, 2026. It costs $0.26/M input and $2.08/M output tokens, and handles a 262K-token context window. Its strongest use case is agentic & tools, where it ranks in the 73rd percentile of the models Model Beat tracks.

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.

Context
262K
Input
$0.26 / 1M
Output
$2.08 / 1M
Released
Feb 24, 2026
Modalities
textimagevideotext
Strongest atAgentic & Tools top 27%

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where Qwen3.5-122B-A10B lands among all models tracked on Model Beat.

56.0
Intelligence Index
Artificial Analysis
56th percentile of tracked models
46.0
Coding Index
Artificial Analysis
46th percentile of tracked models
73.0
Agentic Index
Artificial Analysis
73rd percentile of tracked models

Reasoning

2 evals
GPQA Diamond85.7%

Graduate-level scientific reasoning

Humanity's Last Exam23.4%

Frontier of human expert knowledge

Coding

1 evals
SciCode42.0%

Scientific research coding

Agentic & Tools

1 evals
τ²-bench93.6%

Tool-agent-user reliability

Compare Qwen3.5-122B-A10B with

Frequently asked questions

What is Qwen3.5-122B-A10B?

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.

Who created Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B is an AI model developed by Alibaba, part of the Qwen family, released Feb 24, 2026.

How much does Qwen3.5-122B-A10B cost?

Qwen3.5-122B-A10B's list price from Alibaba is $0.26 per million input tokens and $2.08 per million output tokens.

What is Qwen3.5-122B-A10B's context window?

Qwen3.5-122B-A10B supports a context window of up to 262K tokens.

How does Qwen3.5-122B-A10B perform on benchmarks?

On standardized evaluations tracked by Epoch AI, Qwen3.5-122B-A10B scores 93.6% on τ²-bench, 85.7% on GPQA Diamond, 23.4% on Humanity's Last Exam.

Is Qwen3.5-122B-A10B open source?

Qwen3.5-122B-A10B is released with open weights (Open weights (restricted use)), so the model can be downloaded and self-hosted.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Jul 30, 2026.