Claude Opus 4

llm

Anthropic's flagship model from the Claude 4 generation, positioned at launch as its best coding model. Scores are extended-thinking, single attempt, no tools.

Metadata

org	Anthropic
released	2025-05-22
license	proprietary
kind	llm

Blog ↗

Benchmarks

GPQA	79.6	source ↗
AIME 2025	75.5	source ↗
SWE-bench	72.5	source ↗

Lineage

No recorded lineage — root or standalone model.

view in full graph →