Woofun AI data shows that Kimi K3 scored 57 on the Intelligence Index v4.1, placing it below Claude Fable 5 and GPT-5.6 Sol but comparable to Claude Opus 4.8 and GPT-5.5. The model achieved 1668 Elo in real-world tasks and ranked first in automated SaaS workflows.

Kimi K3 operates at an average cost of $0.94 per task, undercutting GPT-5.6 Sol and Opus 4.8.

However, its knowledge reliability test hallucination rate increased from 39% to 51%, while accuracy improved from 33% to 46%.