Anthropic: Claude Opus 4.5

Anthropic Best for: agentic

Compare this model →

radar chart — all benchmarks

benchmark scores Scores from Mar 2026

		Categories
Agentic	59.6
Intelligence	49.7
Coding	47.8

pricing — per 1M tokens via openrouter

Data unavailable

latency percentiles — time to first token (ms)

Data unavailable

model specifications

Data unavailable