Alibaba Qwen3.8-Max tops Artificial Analysis Agentic Index, first Chinese model at #1
On August 6, Artificial Analysis released its latest leaderboard with Qwen3.8-Max at 55.4, surpassing Claude Opus 5 and GPT-5.6 to top the Agentic Index globally. This is the first time a Chinese model has reached #1, beating the previous best of 50.1 by Kimi K3.
On August 6, third-party evaluator Artificial Analysis released its latest agent capability leaderboard, placing Alibaba Qwen3.8-Max at 55.4 on the Agentic Index, ahead of Anthropic Claude Opus 5 and OpenAI GPT-5.6. This is the first time a Chinese model has reached the top of the ranking, surpassing the previous Chinese best of 50.1 set by Moonshot Kimi K3.
The Agentic Index measures a model's ability to call tools to solve complex problems, a key metric for moving from basic chat to professional deployment. The list had been dominated by Claude and GPT series, making Qwen3.8-Max's ascent a milestone for Chinese models in agentic engineering.
Qwen3.8-Max was released by Alibaba on August 3 with 2.4 trillion total parameters and 95B activated, priced at $2 per million input tokens and $6 per million output. Alibaba committed to open-weight release in the week of August 10, but as of August 7 weights had not appeared and license terms remain undisclosed.