Qwen3.8-27B Hits #9 on Code Arena WebDev Leaderboard
arena · x · 2026-08-25
Alibaba's Qwen3.8-27B model ranked #9 overall on the Code Arena: WebDev leaderboard with 1595 points. The 27B variant achieved higher rankings in specific categories: #6 in Consumer Product (1587), #7 in Brand & Marketing (1627), and #8 in Gaming (1645).
Related event: Qwen3.8-27B Ranks Ninth on Code Arena Leaderboard(3 posts)→
More from Models
- User praises Muse-Spark's capabilities, especially multimodal — adonis_singh · 2026-08-25
- Developer finds small models sufficient for 66% of tasks previously handled by large models — intellectronica · 2026-08-25
- MiniMax H3 Max launches with fal tuning for enhanced prompt adherence and visual quality — gorkem · 2026-08-25
- Speculation on 0x alpha's free tokens hints at continuous learning breakthrough — doodlestein · 2026-08-25
- Image comparison: Opus 5 benchmark cost significantly lower than GPT 5.6 Sol — dejavucoder · 2026-08-25
- LLM testing: Opus best for teaching, domestic models offer high value for coding — Yuchenj_UW · 2026-08-25