Compare / Claude Opus 5.5 vs Kimi K2.7 Code

Claude Opus 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 Opus 5.5
Anthropic · profile
Kimi K2.7 Code
Moonshot AI · profile
Results compared
7
Shared sources
3
BenchmarkMetricClaude Opus 5.5Kimi K2.7 Code
APEX-AgentsreportedTasks passed% of tasks 73.5%37.6%
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 57.625.8
Artificial AnalysisreportedHumanity's Last Exam% of questions 61.4%35.0%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 84.7%79.3%
Artificial AnalysisreportedSciCode% of problems 66.9%47.8%
Artificial AnalysisreportedTerminal-Bench 4.0% of tasks 59.6%1.0%
SimpleQA Verified (Epoch AI)reportedCorrect answers% of questions 72.2%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.