leaderboard

AppWizard
September 19, 2026
Google has launched Android Bench 2.0, an upgraded benchmark for evaluating AI coding agents, which now includes 30 long-horizon tasks that can take human engineers days or weeks to complete. The best pass rate for these tasks is around 28%, down from approximately 91% in the previous version. The benchmark measures both pass rates and completion rates, acknowledging partial progress rather than just failures. It assesses various challenges, including app creation and feature integration, using a comprehensive scoring methodology that evaluates functionality, regression checks, and visual fidelity. AI models perform better with new code than with modifications to existing systems, facing challenges in runtime validation and cross-platform conversions. The current leaderboard shows OpenAI’s GPT-6 Astra leading with a 28% pass rate, while Gemini 3.8 Flash has an 8% pass rate. Developers using AI agents should be aware that while AI can generate significant portions of applications, further refinements will require human input. The benchmark is available on Google’s Android Bench leaderboard.
AppWizard
September 18, 2026
Google has launched Android Bench 2.0, a benchmark for evaluating large language models (LLMs) and AI agents on complex Android development tasks. This version focuses on long-horizon tasks (LHTs) that are more intricate than those assessed by the original benchmark. Key tasks include upgrading dependencies, adding major new features, and building Android apps from scratch. The new grading system uses continuous scoring instead of a binary pass-or-fail method, providing a more detailed performance evaluation. Currently, GPT-6 Astra leads the leaderboard with a 28% pass rate, followed by Gemini 3.8 Flash at 8%. Other evaluated models include Claude Fable 5.1, GPT-5.6 Sol, and Claude Opus 5. Google plans to expand the leaderboard with more models and results.
AppWizard
September 15, 2026
BPMG released a demo version of its cooking simulation game, Cooking Adventure, for Steam PC on the 15th. The game, known as My Little Chef in South Korea, allows players to act as chefs in various themed restaurants, with a mobile version that has 33 million downloads. The demo features two restaurants (Grill House and Sushi House) with 20 stages total. The full version, launching in November, will include 12 restaurants, 540 stages, cooking contests, and leaderboard competitions. BPMG aims to gather feedback from demo players and promote the game through videos and influencer collaborations.
AppWizard
July 30, 2026
OneBlock is a Minecraft game mode where players start with a single block that evolves through 29 phases, offering valuable loot. It includes multiplayer features, daily and weekly quests for XP, and the ability to own multiple islands. Players can engage in monster islands for rare drops, unlock custom enchantments, and utilize worker minions for automation. The game also offers extensive customization options for islands and characters, a player-driven economy, a leaderboard system, and server-wide events. Future updates are expected to introduce more phases, blocks, and items.
AppWizard
July 24, 2026
Two friends visited an arcade filled with games and competed for leaderboard positions, winning prizes such as cosmetic items and food. They announced the release of the free Chaos Cubed: Pixel Party add-on by Hogskull Labs, which includes a quest to find the Arcade Cave containing five unique arcade machines. Players can engage in minigames that utilize sulfur cube physics, such as Netherball, Metal Mania, Paint Frenzy, and Void Pinball. Completing challenges in these games can earn players collectible pet spawners, while the Rewards Kiosk offers cosmetics, plushies, and consumables based on performance. The add-on also provides tools for creative players to build their own arcade experiences in Creative Mode. The add-on is available at the Minecraft Marketplace and requires Minecraft: Bedrock Edition.
BetaBeacon
July 10, 2026
Androids are spread throughout Stella Montis in ARC Raiders, with MetaforgeAndroids located on both the upper and lower floors. Players need three stars and 3000 points to complete the trial, with each Android search yielding 400 points. Stella Montis is the guaranteed map to complete this trial, as it is a major ARC research facility filled with Androids. Players should be prepared with weapons to deal with other enemies present in the area.
AppWizard
June 20, 2026
Forza Horizon 6 has lost its position as the top-selling game on Steam to Meccha Chameleon, a hide-and-seek game released on June 9, which has sold five million copies in ten days. Meccha Chameleon is priced affordably and has an 85% approval rating from over 6,000 user reviews. The top five best-selling games between June 9 and June 16 are Meccha Chameleon, Forza Horizon 6, Path of Exile 2, EA Sports FC 26, and Final Fantasy 7 Remake Intergrade. The rankings for positions six through ten include 007 First Light, Gothic Remake, Burglin’ Gnomes, Rust, and Voidling Bound. Titles in spots ten through twenty are Dead by Daylight, Resident Evil 4, Road to Empress II, Subnautica 2, Hearts of Iron IV, Paralives, Monster Hunter Wilds, Witchspire, Gamble With Your Friends, and Resident Evil Requiem.
BetaBeacon
June 17, 2026
Players take control of King Alden in the game "Kings Do Not Fall" as he fights through six levels against monsters like goblins, orcs, and the undead. The game features classic arcade-inspired visuals, fast-paced side-scrolling combat, and the ability to unlock achievements and compete on a leaderboard.
Search