Comparing 2 models

Claude Sonnet 5 vs Kimi K3

Facts first, then task-specific rankings. A highlighted cell is better only for that row, not universally.

metric
Model 1Claude Sonnet 5
Model 2Kimi K3
Best for
Agentic Coding (#5)
a General Assistant (#1)
Provider
anthropic
moonshotai
Context
1M
1.0MBest
Input / 1M
$2Best
$3
Output / 1M
$10Best
$15
Tool use
yesBest
yesBest
Vision
yesBest
yesBest
Reasoning
yesBest
yesBest
Open-weight
Released
Jun 30, 2026
Jul 16, 2026