Coral's AgentRadio lifted coding-agent accuracy to 62% at sixfold cost
Four Opus 4.6 agents beat one Opus 4.8 agent on a codebase benchmark, though a newer model has already edged past the result.
By Ryan Merket · Published
Primary source: VentureBeat
Why it matters
AgentRadio shows that orchestration can extract a model-generation-sized gain from existing coding agents. The commercial tradeoff is a roughly sixfold increase in inference cost.
Caelum Forder and Peter Carroll, the founders of Coral AI Labs, have produced evidence that the architecture surrounding an AI model can matter as much as upgrading the model itself. Their researchers' AgentRadio paper, published July 30th, reports that four Claude Code agents running Anthropic's Opus 4.6 resolved 62.1% of a demanding codebase-understanding benchmark when they could exchange discoveries during execution.…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.