Claude Sonnet 4.6 vs DeepSeek V4 Flash

Claude Sonnet 4.6 edges ahead on overall intelligence (RunFree 66.2 vs 59.1). Here's how they stack up on benchmarks, price and specs.

Claude Sonnet 4.6
Anthropic
DeepSeek V4 Flash
DeepSeek

Shared benchmarks (4)

Loading chart…
Claude Sonnet 4.6DeepSeek V4 Flash
RunFree Score66.259.1
Blended price / 1M$6.00$0.11
Input / 1M$3.00$0.09
Output / 1M$15.00$0.18
Context window1M1.0M
Max output128K66K
Reasoning modelYesYes
GPQA Diamond89.9%88.1%
Humanity's Last Exam33.2%34.8%
SWE-Bench Verified79.6%79%
Terminal-Bench59.1%56.9%
Wins55

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 · DeepSeek V4 Flash card · full leaderboard