Correctness in Unreal depends on the engine, not just the diff. A patch can compile, look plausible, and still fail because it misses replicated state, mishandles an actor lifecycle transition, or breaks a gameplay ability system it never touched directly. Each task gives the agent a buildable start state, a behavior specification, and a scoped set of editable files — then programmatic tests and judge auditing check whether the resulting behavior is actually correct at runtime.

• →The strongest configuration, Claude Fable 5 (max), now solves a majority of the task set at 55.5% calibrated pass@1 — but every other evaluated configuration stays under 30%.
• →Partial progress is consistently far ahead of full-task success: GPT-5.5 xhigh reaches 29.1% pass@1 but 80.4% mean requirement satisfaction; Claude Opus 4.8 max reaches 23.6% pass@1 but 77.9% requirement satisfaction.
• →The hard part is runtime integration, not syntax — strong models usually compile and reach execution; the remaining failures are authority mistakes, replication/state-sync errors, actor lifecycle bugs, and incomplete integration with surrounding gameplay systems.
• →Failure is not evenly spread — save/persistence has the largest unresolved share, with weapons/combat, serialization, and AI/world orchestration also retaining unsolved tasks.
• →79 of 110 tasks are solved by at least one configuration; 31 remain unsolved by every configuration evaluated — model capabilities are complementary rather than strictly nested.