Claude 3 Opus

anthropic · Ranked across 4 benchmarks · best rank #9

Benchmark scores

BenchmarkCategoryRankScoreCaptured
METR Task Horizon (HCAST) agents #9 8m 2025-07-12
SWE-bench Verified agents #32 15.8% 2024-04-02
Chatbot Arena chat #54 1262 2026-04-30
OpenRouter · Weekly Usage usage #58 #660 2026-05-02