How we compare model quality in Cursor · Cursor

Developers are asking coding agents to take on longer, more complex tasks that span multiple files, tools, and steps. As these requests grow in scope, the evals that measure agent performance need to evolve with them. At Cursor, we use a hybrid online-offline eval process to keep our understanding of model quality aligned with what developers actually do. The offline part uses CursorBench, our int

[misshiki]

CursorがAIコーディングエージェント評価ベンチマーク「CursorBench」を公開。実際のリポジトリ操作や複数ステップの開発タスクで、エージェントがどれだけ問題解決できるかを測定する。GPTが強い。