Qwen4 internal tests reportedly put it near Opus 5.5 on frontend coding
julianharris · x · 2026-09-28
Unverified leak: early internal tests of Qwen4 reportedly show frontend coding roughly in the Opus 5.5/Astra range, with better visual taste than DeepSeek 0820; a Qwen4-27B variant is also mentioned, with October as the expected window. Julian Harris quips that the classic "pelican on a bicycle" benchmark is now saturated and needs a replacement.
More from Models
- Musk confirms Grok 'upgrades' as users notice dramatic speed boost — elonmusk · 2026-09-28
- "System 2 models built the brain, but System 1 is building the nervous system" — ai · 2026-09-28
- TeleOCR Trends on Hugging Face: A Qwen2.5-VL-Based Chinese Document OCR Model — XingChen-AGI · 2026-09-28
- Kaggle Game Arena: Evaluating LLMs via Head-to-Head Chess, Poker, and Werewolf — kaggle · 2026-09-28
- Perplexity CEO: still using sol 6 for knowledge work — cheap, fast, great compaction — gabriel1 · 2026-09-28
- NerfBench's First Results Find No Nerf: Claude Opus 5.5 Dips Just 0.8% vs Launch — alejandroll10 · 2026-09-28