https://coder-eval.comhttps://coder-eval.com/docshttps://coder-eval.com/docs/ab-experimentshttps://coder-eval.com/docs/agents/antigravityhttps://coder-eval.com/docs/agents/claude-codehttps://coder-eval.com/docs/agents/codexhttps://coder-eval.com/docs/ci-gatehttps://coder-eval.com/docs/comparisonhttps://coder-eval.com/docs/datasetshttps://coder-eval.com/docs/dialog-modehttps://coder-eval.com/docs/docker-isolationhttps://coder-eval.com/docs/extendinghttps://coder-eval.com/docs/report-schemahttps://coder-eval.com/docs/task-definition-guidehttps://coder-eval.com/docs/tutorialshttps://coder-eval.com/docs/tutorials/01-first-evaluationhttps://coder-eval.com/docs/tutorials/02-ci-pipelinehttps://coder-eval.com/docs/tutorials/03-evalboard-localhttps://coder-eval.com/docs/tutorials/04-writing-a-taskhttps://coder-eval.com/docs/tutorials/05-comparing-modelshttps://coder-eval.com/docs/tutorials/06-use-docker-isolationhttps://coder-eval.com/docs/user-guide