Compare / Claude Sonnet 5.5 vs GPT-5.4

Claude Sonnet 5.5 vs GPT-5.4

5 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
GPT-5.4
OpenAI · profile
Results compared
5
Shared sources
3
BenchmarkMetricClaude Sonnet 5.5GPT-5.4
APEX-AgentsreportedTasks passed% of tasks 75.5%52.4%
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 56.039.0
Artificial AnalysisreportedHumanity's Last Exam% of questions 55.0%43.7%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 82.7%82.0%
SimpleQA Verified (Epoch AI)reportedCorrect answers% of questions 46.5%45.1%

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.