00:56
2026-08-08
runtimewire.com
artificial-intelligence
Coral's AgentRadio lifted coding-agent accuracy to 62% at sixfold cost
Coral AI Labs founders Caelum Forder and Peter Carroll released evidence that four Claude Code agents running Anthropic's Opus 4.6 resolved 62.1% of a codebase-understanding benchmark, compared to 32.…