Claude Sonnet 4

anthropic · Ranked across 4 benchmarks · best rank #4

Benchmark scores

BenchmarkCategoryRankScoreCaptured
SWE-bench Verified agents #4 76.8% 2025-08-04
Aider Polyglot code #11 61.3% 2025-05-24
OpenRouter · Weekly Usage usage #23 #52 2026-05-02
Chatbot Arena chat #37 1348 2026-04-30