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. In terms of...
Tested on 15 benchmarks. Top scores: Chatbot Arena Elo — Overall (1416.1%), Chatbot Arena Elo — Coding (1359.8%), Artificial Analysis · tau2-Bench Telecom (84.5%).
Chatbot Arena overall Elo rating. Crowdsourced human preference ranking from blind head-to-head comparisons across all topics.
Chatbot Arena coding Elo. Human preference ranking specifically for coding tasks and technical questions.
- Typemultimodal
- Context262K tokens (~131 books)
- ReleasedFeb 2026
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.003
Frequently Asked Questions
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteGemma 3 12B (free) · Google DeepMindQwen3 Next 80B A3B Instruct (free) · Alibaba QwenKey facts · as of 2026-10-05
- Qwen3.5-122B-A10B by Alibaba Qwen. Not enough public benchmark scores to rank yet.
- List price $0.26 input · $2.08 output per 1M tokens (as of 2026-10-05).
- Sold by 4 providers (as of 2026-10-05): Alibaba $0.26 in / $2.08 out · SiliconFlow (fp8) $0.26 in / $2.08 out · AtlasCloud (fp8) $0.30 in / $2.40 out · Novita (bf16) $0.40 in / $3.20 out. Every provider
How to cite · data as of 2026-10-05
Qwen3.5-122B-A10B · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/qwen3-5-122b-a10b
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP