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: Reasoning Model
25 article(s) found · Clear tag
Intern-S2-Preview – Shanghai AI Lab Open Scientific Multimodal LLM
Intern-S2-Preview is Shanghai AI Laboratory's open scientific multimodal LLM preview, delivering trillion-class scientific capability at 35B parameters. Its "general–specialist fusion" training pipeli...
General365 – Meituan LongCat Team's Open General Reasoning Benchmark
General365 is an open general reasoning benchmark from Meituan's LongCat team, designed to evaluate large language models (LLMs) purely on logical reasoning in everyday scenarios. The benchmark includ...
9Router – Free Open-Source AI Router: Smart Fallback for Claude Code, Cursor & Codex
9Router is a free open-source AI router that connects Claude Code, Cursor, Codex, Cline & Copilot to 40+ providers with 3-tier auto-fallback (subscription → cheap → free), proxy pools and RTK token savings of 20-40%. Install via npm, never hit rate limits again.
AI Job Search – Open-Source AI Job Framework for Matching and Search
AI Job Search is an open-source job-hunting framework built on Claude Code. It builds deep structured career profiles for intelligent job matching and customized application materials. A draft–review ...
WebWorld – Alibaba Qwen Team's Open-Source Large-Scale Web World Model Series
WebWorld is an open-source large-scale web world model series from Alibaba's Qwen team, built on the Qwen3 foundation and available in 8B, 14B, and 32B parameter sizes. By predicting web state transit...
ERNIE 5.1 – Baidu's Flagship Large Language Model
ERNIE 5.1 (文心5.1) is Baidu's flagship LLM built on ERNIE 5.0 knowledge distillation and the Once-for-All elastic training framework, cutting pretraining cost to about 6% of same-scale industry models ...
Ring-2.6-1T – Ant Bailing's Trillion-Parameter Deep Reasoning Model
Ring-2.6-1T is Ant Group Bailing's trillion-parameter deep reasoning LLM in the Ring series, focused on "slow thinking" for math competitions, code generation, and other hard cognitive tasks. MoE arch...
Composer 2.5 – Cursor's In-House Agentic Coding Model
Composer 2.5 is Cursor's in-house Agentic coding model with major gains in intelligence and behavior over Composer 2. On SWE-Bench Multilingual (79.8%) and CursorBench v3.1 (63.2%) it sits in the same...
SkyClaw-v1.0 – Kunlun Wanwei Skywork's High-Performance Agent Model
SkyClaw-v1.0 is Kunlun Wanwei's Skywork AI team agent-specialized model for multi-step real workflows. It offers million-token context, native fit with OpenClaw, Hermes, Claude Code, Codex, and simila...
Science Skills – Google DeepMind's Open-Source Scientific Skills Toolkit
Science Skills is Google DeepMind's open-source scientific skills toolkit that reshapes life-science research workflows through standardized, modular AI agent architecture. It integrates 30+ databases...
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.