AI BriefingNotes on Qwen-Max-0428
Key point
The Qwen team has released a large-scale model, **Qwen-Max-0428**, which surpasses the performance of the existing Qwen1.5-110B-Chat.
Details
Following the Qwen1.5 series ranging from 0.5B to 110B parameters, the Qwen team has released a larger-scale model, Qwen-Max-0428. This model is an instruction-tuned model fine-tuned for chat services.
Having entered the top 10 of the Chatbot Arena leaderboard, this model also showed performance surpassing the previous largest model, Qwen1.5-110B-Chat, in the MT-Bench evaluation.
The key benchmark results are as follows:
- MT-Bench: Qwen-Max-0428 (8.96) vs Qwen1.5-110B-Chat (8.88)
- Arena: Qwen-Max-0428 (1186) vs Qwen1.5-110B-Chat (1172)
Users can try out the model via the Hugging Face Spaces demo, and it is also accessible through the DashScope API. In particular, the DashScope API is compatible with the OpenAI API format, making it easy to integrate into existing workflows.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Qwen Releases Qwen3.8-LiveTranslate, a Real-Time Simultaneous Interpretation Model with 2.3-Second Latency