Introducing Claude Sonnet 4.5
Open paper
Benchmark
Model
Rank
Results
code-generation-on-humaneval
Claude Sonnet 4.5 Thinking
–
Pass@1: 97.6
code-generation-on-swe-bench-pro
claude-4-5-Sonnet
–
Resolved: 43.60
Rank counts only results with a code link.