Over 10,000 engineers powering China’s leading lifestyle services e‑commerce platform. Supporting hundreds of millions of consumers, millions of merchants across 2,000+ industries. This is the public channel for the tech teams behind Meituan, Dianping, Meituan Waimai, Meituan Select, and related services.
Meeseeks, a new benchmark released by Meituan’s M17 team, systematically evaluates large language models’ instruction‑following ability with a three‑tier framework, multi‑round self‑correction, and extensive real‑world data, revealing performance gaps among models such as OpenAI o‑series, Claude, DeepSeek and Qwen2.5.
The article introduces Meituan’s trusted experiment analysis engine, detailing its rich methodological library, system architecture, integration options, and a step‑by‑step offline analysis case that together empower teams to conduct reliable, efficient A/B tests without deep statistical expertise.
Meituan’s first smart‑helmet article details hardware innovations that tackle delivery riders’ safety, comfort, and efficiency, covering stricter safety standards, sensor‑driven alerts, lightweight structures, advanced ventilation, three‑times longer battery life, noise‑cancelling audio, IPX6 waterproofing, and a data‑driven production line.
This article details Meituan’s smart helmet R&D, explaining how active and passive safety features—such as high‑quality call performance, an AI voice assistant, and collision‑fall monitoring—combine to protect delivery riders, improve efficiency, and set the stage for next‑generation multimodal AI integration.
Meituan’s retail advertising introduces a novel ‘fundraising auction’ mechanism for joint marketing, enabling multiple parties to co‑bid on the same ad slot, evolving through rule‑based, model‑based, and holistic stages, and leveraging AI‑driven models like JAMA, JRegNet, and JTransNet to boost ROI and platform revenue.
Meituan’s research team showcases eight ACL 2025 papers spanning generative retrieval, multi‑objective preference alignment, rich‑text image understanding, cross‑language transfer, multimodal math reasoning, and more, offering insights and breakthroughs that can inspire and aid fellow researchers.
The Meituan‑M17 team and Shanghai Jiao Tong University introduced two new benchmarks, OIBench and CoreCodeBench, to more accurately evaluate large language models' algorithmic and engineering coding abilities, revealing a substantial gap between claimed performance and actual capability across a range of tasks and models.
Observational research methods—synthetic control, matching, and Causal Impact—offer powerful alternatives to randomized experiments, enabling businesses like Meituan to assess policy effects despite legal and operational constraints, with detailed principles, applications, advantages, limitations, and practical case studies illustrated throughout the guide.
This article explains the key new features of JDK 17, demonstrates how Meituan upgraded core services to JDK 17 with ZGC, and shares detailed performance, stability and cost‑reduction results, along with migration steps, compatibility fixes and practical JVM tuning advice.
This article, part of the Trusted Experiment Whitepaper series, introduces quasi‑experimental design and focuses on the Difference‑in‑Differences (DID) method, explaining its principles, evaluation models, parallel‑trend testing, extensions, and a concrete Meituan fulfillment case study illustrating practical implementation.
