Qwen3.8-Max Secures Fourth Place on Frontend Code Arena Leaderboard

Alibaba's Tongyi Qianwen team announced that its flagship model Qwen3.8‑Max has entered the Frontend Code Arena leaderboard with a score of 1,668, ranking fourth overall.

The leaderboard, a recognized benchmark for AI‑driven frontend coding ability, lists the top models as follows:

Claude Opus 5 (Max) – 1,705 points – #1

Kimi K3 (Max) – 1,676 points – #2

Claude Opus 5 (High) – 1,669 points – #3

Qwen3.8‑Max – 1,668 points – #4

From the scores, Qwen3.8‑Max (1,668) is virtually tied with Claude Opus 5 (High) (1,669) and trails the leader by only 37 points.

In individual sub‑domains, Qwen3.8‑Max also performed well:

Consumer Product – #2

Brand & Marketing – #3

Reference‑based Design – #3

Gaming – #3

Content Creation Tools – #3

Data & Analytics – #4

Simulations – #5

The results indicate that domestic large‑language models are steadily closing the gap with leading international models in frontend coding tasks, achieving first‑tier scores across both overall and specialized categories.

Source: @Arena