What is the Code Arena ranking for Qwen3.6 Plus?

Qwen3.6 Plus currently holds the #7 position on the Arena.ai Code Arena leaderboard with a score of 1476. This represents a 16-point improvement since its preview phase. The ranking is based on crowdsourced, blind A/B testing where users compare model outputs to determine which provides better coding assistance in real-world scenarios.

How does Alibaba rank as an AI lab for coding?

Following the latest performance updates for Qwen3.6 Plus, Alibaba Group has moved up to become the #3 ranked AI lab globally in the Code Arena. This ranking places the company directly behind the top two frontier model labs, establishing it as a primary provider for developers and organizations building autonomous agentic coding workflows.

What is the difference between Qwen3.6 Plus and the Preview version?

The production version of Qwen3.6 Plus shows measurable performance gains over the initial Preview release. In the Code Arena, the score increased by 16 points to reach 1476. In the Text Arena, the model improved by 13 points, landing at the #36 spot on the general language leaderboard after receiving more community votes.

Alibaba Qwen3.6 Plus Climbs to Top Seven in Global Code Arena Rankings

Agentic Coding

Evaluation

Benchmark

Performance

Qwen

Published Apr 21, 2026

Arena.ai, a community-driven platform for evaluating AI models through blind A/B testing, released updated rankings for Qwen3.6 Plus. The model climbed to #7 in the Code Arena with a score of 1476, a 16-point increase since its preview. This performance establishes Alibaba Group as the third-ranked lab for coding globally.

This ranking provides objective validation for the production-ready Qwen3.6-Plus model following its recent move out of trial status. While Alibaba has consistently released high-performing open-source sparse models, these crowdsourced results prove their proprietary "Plus" variant is a legitimate peer to the most capable frontier models.

You can now integrate a top-tier coding model that rivals frontier labs for agentic workflows (AI systems that autonomously execute multi-step tasks). The model is available via the Qwen API and third-party providers. For teams building autonomous coding agents, Qwen3.6 Plus is now a primary contender for production-grade reasoning.

Read the full update →

Frequently asked questions

What is the Code Arena ranking for Qwen3.6 Plus?: Qwen3.6 Plus currently holds the #7 position on the Arena.ai Code Arena leaderboard with a score of 1476. This represents a 16-point improvement since its preview phase. The ranking is based on crowdsourced, blind A/B testing where users compare model outputs to determine which provides better coding assistance in real-world scenarios.
How does Alibaba rank as an AI lab for coding?: Following the latest performance updates for Qwen3.6 Plus, Alibaba Group has moved up to become the #3 ranked AI lab globally in the Code Arena. This ranking places the company directly behind the top two frontier model labs, establishing it as a primary provider for developers and organizations building autonomous agentic coding workflows.
What is the difference between Qwen3.6 Plus and the Preview version?: The production version of Qwen3.6 Plus shows measurable performance gains over the initial Preview release. In the Code Arena, the score increased by 16 points to reach 1476. In the Text Arena, the model improved by 13 points, landing at the #36 spot on the general language leaderboard after receiving more community votes.