Compare / Claude Opus 4.6 vs Claude Sonnet 5.5

Claude Opus 4.6 vs Claude Sonnet 5.5

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

Claude Opus 4.6
Anthropic · profile
Claude Sonnet 5.5
Anthropic · profile
Results compared
5
Shared sources
3
BenchmarkMetricClaude Opus 4.6Claude Sonnet 5.5
APEX-AgentsreportedTasks passed% of tasks 46.3%75.5%
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 31.956.0
Artificial AnalysisreportedHumanity's Last Exam% of questions 39.9%55.0%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 78.0%82.7%
SimpleQA Verified (Epoch AI)reportedCorrect answers% of questions 47.0%46.5%

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.