Claude Sonnet 4.6 vs Kimi K2 Thinking

Claude Sonnet 4.6 edges ahead on overall intelligence (RunFree 66.2 vs 45.2). Here's how they stack up on benchmarks, price and specs.

Claude Sonnet 4.6
Anthropic
Kimi K2 Thinking
MoonshotAI

Shared benchmarks (5)

Loading chart…
Claude Sonnet 4.6Kimi K2 Thinking
RunFree Score66.245.2
Blended price / 1M$6.00$1.07
Input / 1M$3.00$0.60
Output / 1M$15.00$2.50
Context window1M262K
Max output128K262K
Reasoning modelYesYes
AIME 202595.6%94.5%
GPQA Diamond89.9%84.5%
Humanity's Last Exam33.2%23.9%
SWE-Bench Verified79.6%71.3%
Terminal-Bench59.1%47.1%
Wins74

A blank means the metric is tied or one model has no verified data. Prices are blended 3:1 input:output.

Compare more: Claude Sonnet 4.6 card · Kimi K2 Thinking card · full leaderboard