Qwen2.5-27B hits Code Arena Top 10, leading its size class
Alibaba_Qwen · x · 2026-08-25
Qwen2.5-27B ranked #9 on Code Arena WebDev with 1595 points. It is the only model in its size class to reach the top 10, reshaping the Pareto Frontier. Its performance significantly surpasses Gemma 2-31B (released in April, ranked #80), trailing the much larger Qwen2.5-Max by just 6 ranks.
Related event: Qwen3.8-27B Ranks 9th on Code Arena, Smallest Model in Top 10(4 posts)→
More from Models
- User swaps one word, gets very different AI results — claims sexism — RecordingThis6802 · 2026-08-25
- Fal releases post-trained H3 model co-optimized with custom inference stack — isidentical · 2026-08-25
- Real-time voice AI hears emotion but ignores it: 119 of 120 runs followed the script — Once_ina_Lifetime · 2026-08-25
- SGL Releases Qwen3.8-27B NVFP4 Checkpoint with BF16 LM Head for Higher Accuracy — EAccelerate_42 · 2026-08-25
- User complains about ChatGPT over-censorship, plans to switch to Copilot — Halberd96 · 2026-08-25
- Optimizing Qwen3-ASR Latency to 70ms to Beat Deepgram — Comprehensive_Quit67 · 2026-08-25