Kimi-K3 is now #1 on the Frontend Code Arena benchmark, surpassing Claude Fable 5; the model scored 88.3 on Terminal Bench 2.1, only below GPT-5.6 Sol's 88.8 (Michael Nuñez/VentureBeat)
Get the Tech newsletter
Daily tech — startups, AI labs, chips, the launches that shape the next decade. Free.
- Kimi-K3 reached #1 on the Frontend Code Arena benchmark, surpassing Claude Fable 5, in a release by Beijing-based Moonshot AI, a startup backed by Alibaba.
- Kimi-K3 scored 88.3 on Terminal Bench 2.1, placing it just 0.5 points behind GPT-5.6 Sol's 88.8 — the highest score on that benchmark among named models.
Why it matters: Two independent coding benchmarks now place Kimi-K3 alongside or above frontier U.S. models — a #1 ranking over Claude Fable 5 on Frontend Code Arena, and a 0.5-point gap to GPT-5.6 Sol on Terminal Bench 2.1 — putting Alibaba-backed Moonshot AI directly into the agentic-coding leaderboard conversation.
