Compare / Claude Sonnet 5.5 vs Kimi K2.7 Code

Claude Sonnet 5.5 vs Kimi K2.7 Code

7 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.

Claude Sonnet 5.5: Anthropic · profile
Kimi K2.7 Code: Moonshot AI · profile
Results compared: 7
Shared sources: 3

Benchmark	Metric	Claude Sonnet 5.5	Kimi K2.7 Code
APEX-Agentsreported	Tasks passed% of tasks	75.5%	37.6%
Artificial Analysisreported	Artificial Analysis Intelligence Indexindex score	56.0	25.8
Artificial Analysisreported	Humanity's Last Exam% of questions	55.0%	35.0%
Artificial Analysisreported	Long-context reasoning (AA-LCR)% of questions	82.7%	79.3%
Artificial Analysisreported	SciCode% of problems	61.0%	47.8%
Artificial Analysisreported	Terminal-Bench 4.0% of tasks	63.6%	1.0%
SimpleQA Verified (Epoch AI)reported	Correct answers% of questions	46.5%	36.5%

Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.