Claude 3 Haiku vs Kimi K2.7 Code
Compare Claude 3 Haiku by Anthropic against Kimi K2.7 Code by Moonshot AI, context windows of 200K vs 262K, tested across 54 shared challenges.
Our Verdict
Kimi K2.7 Code
Claude 3 HaikuRunner-up
No community votes yet. On paper, Kimi K2.7 Code has the edge — bigger model tier, newer.
Claude 3 Haiku is 3.2x cheaper per token — worth considering if cost matters.
Too close to call
API pricing
Cost per 1M tokens
Claude 3 Haiku
Input
$0.25
3.8× cheaper
Output
$1.25
3.2× cheaper
Kimi K2.7 Code
Input
$0.95
Output
$4.00
Claude 3 Haiku is cheaper on both — 3.8× input, 3.2× output
Writing DNA
Style Comparison
Similarity
59%
Kimi K2.7 Code uses 76.3x more headings
Claude 3 Haiku
Kimi K2.7 Code
50%Vocabulary57%
22wSentence Length19w
0.71Hedging0.51
0.3Bold4.7
5.9Lists3.3
0.00Emoji0.00
0.00Headings0.76
0.08Transitions0.05
Based on 13 + 27 text responses
Research
What we learned reading every model
FAQ
