Claude Opus 4

anthropic · Ranked across 6 benchmarks · best rank #3

Benchmark scores

BenchmarkCategoryRankScoreCaptured
OpenRouter · Weekly Usage usage #3 #9 2026-06-09
AA Coding Index code #3 56.7% 2026-06-15
Aider Polyglot code #7 72.0% 2025-05-25
SWE-bench Verified agents #10 73.2% 2025-05-22
METR Time Horizon agents #12 1h40m 2025-05-22
Chatbot Arena chat #12 1473 2026-06-10