Kimi-K3 Tops Frontend Arena, Trails Sol on Terminal Bench
Get the Tech newsletter
Daily tech — startups, AI labs, chips, the launches that shape the next decade. Free.
- Moonshot AI released Kimi-K3, which climbed to #1 on the Frontend Code Arena benchmark, surpassing Claude Fable 5
- Kimi-K3 scored 88.3 on Terminal Bench 2.1, trailing only GPT-5.6 Sol's 88.8 among the models measured
Why it matters: Moonshot AI—a Beijing-based startup backed by Alibaba—plants itself at the top of one coding benchmark while landing within half a point of the leader on another. For US frontier model developers, the close Terminal Bench margin signals the competitive gap on coding-specific tasks has thinned to fractions of a point.
