Models · The Decoder ·

Moonshot's Kimi K3 outperforms Fable 5 in frontend code but lags far behind in complex math

Moonshot's Kimi K3 outperforms Fable 5 in frontend code but lags far behind in complex math

Moonshot’s Kimi K3 ranked first in Code Arena’s Frontend category, ahead of Claude Fable 5 and GPT-5.6 Sol. It scored about 39% on FrontierMath Tier 4, compared with nearly 90% for leading OpenAI and Anthropic models.

Read the full story at The Decoder →