-
WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation
Paper • 2605.25874 • Published • 81 -
meituan-longcat/WBench
Benchmark • Updated • 867 • 2.11k • 26 -
meituan-longcat/WBench-weights
Other • Updated • 11 -
meituan-longcat/WBench-examples
Viewer • Updated • 447 • 281 • 4
AI & ML interests
None defined yet.
Recent Activity
Papers
LongCat-DeepResearch Technical Report
DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory
🔦😽🪄✨✨
【New】 LongCat-DeepResearch
LongCat-DeepResearch combines a LongCat model enhanced for deep research with a research harness for open-ended investigation and evidence-grounded report generation. The system outperforms the evaluated deep-research offerings from ChatGPT, Claude, and Gemini across DeepResearchBench, DeepResearchBench II, and ResearchRubrics. These model improvements are intended to be incorporated into the next general-purpose LongCat model release.
Welcome to LongCat Home
Open foundation models for long-context reasoning, agentic coding, and scalable AI systems. Home of LongCat-2.0.
LongCat is a large language model family built by Meituan. We're working on making AI more useful in the physical world — one small step at a time. We continuously release LLMs, multimodal models, and other AI projects here. Feel free to visit LongCat and enjoy our latest models!
Latest innovations
- LongCat-DeepResearch: Technical Report | GitHub | Blog
- LongCat-2.0: Technical Report/Demo | Github |
- LongCat-Video-Avatar-1.5: Technical Report | Project Page
- LongCat-Next: Technical Report | Github | Project Page | Demo
- LongCat-AudioDiT: Technical Report | Github | Demo
- LongCat-Flash-Prover: Technical Report | Github
- LongCat-Video: Technical Report | Github | Project Page
- LongCat Video-avatar: Technical Report | Github | Project Page
- LongCat-Flash-Omni: Technical Report | Github
- LongCat-Image: Technical Report | Github
- LongCat-Flash-Chat: Technical Report | Github
Explore More
-
WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation
Paper • 2605.25874 • Published • 81 -
meituan-longcat/WBench
Benchmark • Updated • 867 • 2.11k • 26 -
meituan-longcat/WBench-weights
Other • Updated • 11 -
meituan-longcat/WBench-examples
Viewer • Updated • 447 • 281 • 4