completion rates

AppWizard
September 18, 2026
Google has released version 2.0 of Android Bench, which focuses on managing complex development tasks rather than minor adjustments. The new version evaluates tasks that may take engineers days or weeks to complete, such as adding features and building applications. A continuous scoring method has replaced the previous pass or fail system, assessing completion rates based on functionality, visual fidelity, and adherence to instructions. Various AI models have been tested, with GPT-6 Astra achieving a 28% pass rate, significantly lower than the previous scores around 90%. No model has achieved a 100% pass rate in porting cross-platform applications, with the best reaching 80%. AI performs better in writing new code than in refactoring existing code, facing challenges with architectural complexity and runtime validation. Android Bench utilized agents from model providers for evaluations and plans to incorporate various model combinations in future updates.
AppWizard
March 25, 2026
Hideo Kojima set a benchmark for player engagement in Death Stranding 2, aiming for a fulfilling experience that encourages completion. Feedback from playtesters led Kojima to enhance the game's playability while avoiding conventional gaming tropes. In the original Death Stranding, completion rates were low, with about 40% of PS4 players, 34% of PS5 players, and 20% of Steam players finishing the game. Initial data for Death Stranding 2 shows over 62% of players completing the final chapter, attributed to easier navigation with vehicles and tools. To address concerns about reduced challenge, a difficulty setting called To the Wilder was introduced in the PC release. Kojima Productions aims to balance enjoyment and accessibility with depth and complexity in the game.
Search