AI Model Library: LLMs, Agents & Dev Tools
Curated reviews of mainstream AI models, agents, and dev tools — capabilities, use cases, and how they compare.
Tag: AI Coding
170 article(s) found · Clear tag
AngelSpec – An End-to-End Speculative Decoding Training Framework Open-Sourced by Tencent HunYuan Team
AngelSpec is an end-to-end speculative decoding training framework open-sourced by the Tencent HunYuan team, built upon TorchSpec. It supports six types of draft architectures, including MTP autoregre...
Ling 3.0 Flash – A Lightweight MoE Inference Model Launched by Ant Bailing
Ling 3.0 Flash is a lightweight Mixture-of-Experts (MoE) inference model introduced by the Bailing large model team at Ant Group. With a total parameter count of 124B, it activates only 5.1B parameter...
BigMac – Xiaohongshu's Open-Source Framework for Pipeline-Parallel Training of Multimodal Large Models
BigMac is an open-source pipeline-parallel training framework for multimodal large models developed by the dots infra team at Xiaohongshu. It aims to address the fundamental contradiction between comp...
WorkBuddy Bench – Tencent's Open-Source Code Agent Evaluation Suite
WorkBuddy Bench is an open-source evaluation suite for code agents developed by Tencent, designed to provide standardized capability assessments for AI agents in four real-world scenarios: code, web d...
MineExplorer – Meituan's Open-World Minute-Level Long-Horizon Task Evaluation Benchmark
MineExplorer is the first open-world minute-level long-horizon task evaluation benchmark introduced by Meituan's LongCat team, based on Minecraft. This benchmark includes 813 manually verified instanc...
Nanbeige4.2-3B – A General-Purpose Agent Small Model from Nanbeige Lab
Nanbeige4.2-3B is a general-purpose agent small model from BOSS Zhipin’s Nanbeige Lab. With only 3B parameters, it surpasses larger models such as Qwen3.5-9B and Gemma4-12B on code agents, office work
Macaron-V1 – MindLab's Post-training Multi-capability Model System
Macaron-V1 is a post-training multi-capability model system introduced by MindLab, built upon the GLM 5.2 base model. It employs LoRA fine-tuning on approximately 0.5% of core parameters through reinf...
img2threejs – Open-Source AI Skill for Converting Single Images into Three.js 3D Models
img2threejs is an open-source AI Skill developed by developer hoainho, capable of automatically converting a single reference image into an interactive Three.js 3D model. This tool deeply analyzes the...
CodeBuddy NPC – Tencent Cloud's AI Agent for Enterprise R&D Workflows
CodeBuddy NPC is a cloud-based AI agent introduced by Tencent Cloud, designed specifically for enterprise R&D workflows. It deeply integrates with the CNB platform, actively participating in code repo...
Cursor Router – Cursor Introduces Intelligent Model Router for Teams and Enterprises
Cursor Router is Cursor's intelligent model router designed for teams and enterprises. Trained on over 600,000 real requests, it automatically routes each programming query to the most suitable model....
Subscribe to AI Model Reviews
Get in-depth reviews the moment a new AI model drops. Know its capabilities and use cases.
We never share your email. Unsubscribe anytime.