SuperCLUE November 2026: Category Leaders and the Full 19-Model Score Ranking
FINAL-Bench
• • 7NEW Articles from Team or Enterprise organizations will get promoted to the main section.
58th Floor AI Video: A Case Study in Two-Person, Audio-Guided Video Generation
softroyals
• • 3Egocentric-EMG-Force: First-Person RGB-D With Forearm EMG, in FiftyOne
harpreetsahota
• Choosing the Right Tasks for AI Agent Evaluation
phranzia
• • 2Lemonade: one local server for LLMs, speech, images and NPUs
Bekhouche
• • 2Qwen Image Generator: Turn a Text Prompt into Images You Can Reuse
gamedevelop
• Outstanding Tiny Desk Meme Meaning: Origin, Original Song and Best AI Edits
akagease
• Six Browser-Only Writing Tools: What Can Be Counted in a Scene, and What Cannot
leventbulut
• • 1SimReady Central: How Lightwheel Brings Physical Accuracy to Shared Simulation Assets
LightwheelAI
• • 2LeRobot v0.7.0: From Terabytes to Prompting Robots
lerobot
• • 9Why your environment variable disappears after you deploy
hal9
• • 2Pretraining Anvaya-1B From Scratch on Two T4 GPUs
Vijayendra
• How to Make an I'm Sorry I Lied Video from Your Photo (and Why Your Photo Matters)
LeFu9527
• • 1Tiny Desk AI Video: Choosing Photos for 1, 3 or 5 People
bertle
• 🧶 Guardián colombiano: safety-preserving fine-tuning of Tiny Aya for Colombian-Spanish moderation
aquilu
• Can Off-the-Shelf Speech AI Speak Lebanese?
Bilalz
• GPT Image 2.6 Explained: How an Image Model Creates GIFs
a2aprotocol
• • 1From Chatbot to Phone Agent: Adding Voice to Your LLM Support Bot
citrusbug
• Sand3D: 106,094 3D objects in one code substrate for language models
Sandflow
• • 2LingYu Real-World Robotics Dataset: Bimanual First-Person Teleoperation Data
LingYu-Robotics
• • 4