Alibaba's newly previewed Qwen 3.8 was put through a 23-build coding gauntlet against GPT-5.6 Sol, Fable 5 and Kimi K3, with the independent evaluation showing a mixed picture rather than a single clear winner. The test suite, known as GoldyBench, spanned games, landing pages, physics simulations, UI work and 3D rendering, and its results have reignited debate over how quickly Chinese models are closing the gap with frontier Western systems.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.