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)
Moonshot’s Kimi-K3 posted a benchmark win in frontend coding while landing just shy of the top Terminal Bench score.
Techmeme’s note says Kimi-K3 reached No. 1 on Frontend Code Arena with 1679 points, ahead of Claude Fable 5. Arena also reported a 76% pairwise win rate for Kimi-K3, compared with 63% for Fable 5 and 58% for GPT-5.6 Sol. The same note says Kimi-K3 scored 88.3 on Terminal Bench 2.1, behind only GPT-5.6 Sol’s 88.8. Techmeme's note
Techmeme’s note says Kimi-K3 reached No. 1 on Frontend Code Arena with 1679 points, ahead of Claude Fable 5. Arena also reported a 76% pairwise win rate for Kimi-K3, compared with 63% for Fable 5 and 58% for GPT-5.6 Sol. The same note says Kimi-K3 scored 88.3 on Terminal Bench 2.1, behind only GPT-5.6 Sol’s 88.8. Techmeme's note
score 8