AI Model Library: LLMs, Agents & Dev Tools

Curated reviews of mainstream AI models, agents, and dev tools — capabilities, use cases, and how they compare.

Expert analysisUpdated regularlyRSS Feed

Tag: Model Inference

84 article(s) found · Clear tag

4 months agoMultimodalSpeech AIModel Inference

Qwen3.5-LiveTranslate – Alibaba Tongyi's Real-Time Simultaneous Interpretation Model

Qwen3.5-LiveTranslate is Alibaba Tongyi's next-generation real-time simultaneous interpretation model. It breaks the latency ceiling of traditional cascaded translation pipelines. Through an innovativ...

Read more
Qwen3.5-LiveTranslate – Alibaba Tongyi's Real-Time Simultaneous Interpretation Model cover image
4 months agoAI AgentAI CodingModel Inference

Qwen3.7-Max – Alibaba Tongyi's Next-Generation Flagship Foundation Model

Qwen3.7-Max is Alibaba Tongyi Qianwen's next-generation flagship foundation model for the Agent era, positioned as an all-round Agent base. Deeply optimized for frontier programming, office automation...

Read more
Qwen3.7-Max – Alibaba Tongyi's Next-Generation Flagship Foundation Model cover image
4 months agoAI AgentMultimodalModel Inference

Gemini 3.5 Flash – Google's Next-Generation AI Foundation Model

Gemini 3.5 Flash is Google's next-generation AI foundation model, positioned around "frontier intelligence + action capability," marking a major breakthrough in efficient inference and Agent capabilit...

Read more
Gemini 3.5 Flash – Google's Next-Generation AI Foundation Model cover image
4 months agoVideo AIModel Inference

Xiaomi Auto World Model – Xiaomi's Assisted-Driving World Model

Xiaomi Auto's assisted-driving world model (Xiaomi Auto World Model) is the first to deeply couple 3D reconstruction (WorldRec) with video generation (WorldGen) into one driving-scene understanding an...

Read more
Xiaomi Auto World Model – Xiaomi's Assisted-Driving World Model cover image
4 months agoAI AgentAI CodingModel Inference

Webwright – Microsoft’s Terminal-Native Web Agent Framework

Webwright is Microsoft Research’s open terminal-native web agent framework—~1,000 lines of harness letting models write Playwright scripts, run bash, read logs, and iterate until complex browser jobs ...

Read more
Webwright – Microsoft’s Terminal-Native Web Agent Framework cover image
4 months agoVideo AIModel InferenceBenchmark

WBench – Meituan’s Interactive Video World Model Multi-Turn Benchmark

WBench is Meituan LongCat’s first systematic multi-turn benchmark for interactive video world models—289 test cases, 1,058 interaction rounds, six scene types (nature, city, indoor, workspace, fantasy...

Read more
WBench – Meituan’s Interactive Video World Model Multi-Turn Benchmark cover image
4 months agoAI AgentModel InferenceLLM

VitaBench 2.0 – Meituan LongCat’s Long-Horizon Dynamic Agent Benchmark

VitaBench 2.0 from Meituan’s LongCat team is the first benchmark for long-horizon dynamic user modeling in real-life agent scenarios. It ships 56 statistically grounded synthetic users, 819 lifecycle-...

Read more
VitaBench 2.0 – Meituan LongCat’s Long-Horizon Dynamic Agent Benchmark cover image
4 months agoAI AgentModel InferenceTool Calling

SwarmFlow – openJiuwen’s Open Multi-Agent Workflow Orchestration Framework

SwarmFlow is openJiuwen’s open-source framework for controllable multi-agent workflow orchestration. Its core idea separates orchestration from reasoning: collaboration flows run as predefined scripts...

Read more
SwarmFlow – openJiuwen’s Open Multi-Agent Workflow Orchestration Framework cover image
4 months agoAI CodingAI SafetyModel Inference

Software Copyright Materials Skill – Open-Source Skill for Software Copyright Application Materials

Software Copyright Materials Skill is an open-source AI Skill designed to run in the Codex intelligent programming environment. It reads a developer's local project source code and automatically gener...

Read more
Software Copyright Materials Skill – Open-Source Skill for Software Copyright Application Materials cover image
4 months agoMultimodalVideo AIModel Inference

Seedance 2.0 Mini – ByteDance's Lightweight Video Generation Model

Seedance 2.0 Mini is a cost-efficient lightweight video generation model from ByteDance Volcano Engine for high-frequency short-video production, marketing asset iteration, and early-stage drafts. It ...

Read more
Seedance 2.0 Mini – ByteDance's Lightweight Video Generation Model cover image
Page 7 of 9 (84 articles total)

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.