Moonshot AI

Kimi K3

Jul 16, 2026ReasoningOpen weightsHugging Face

Compare

Intelligence

30.1

#124 of 744Rank 124 of 744 measured models

Coding

72.0

#42 of 298Rank 42 of 298 measured models

Output speed

42.6 t/s

#354 of 403Rank 354 of 403 measured models

Price/1M

$6

#587 of 659Rank 587 of 659 measured models

Context window

1M

#84 of 1199Rank 84 of 1199 measured models

Cost per task

$1.15

#139 of 193Rank 139 of 193 measured models

Kimi K3 (Low) scores 30.1 on the Artificial Analysis Intelligence Index, ranking 124th of 744 measured models. The closest models on this index are DeepSeek V4 Pro 0424 (30.4), GPT-5.2 (30.4), and Claude Sonnet 4.6 (batch) (30.1). At $6 per million tokens (3:1 input/output blended price), it is more expensive than DeepSeek V4 Pro 0424 ($0.544) and GPT-5.2 ($4.81). With an output speed of 42.6 t/s, it is slower than DeepSeek V4 Pro 0424 (83.1 t/s) and GPT-5.2 (73.8 t/s).