# ![@Meituan_LongCat Avatar](https://lunarcrush.com/gi/w:26/cr:twitter::1961699105434210304.png) @Meituan_LongCat Meituan LongCat

Meituan LongCat posts on X about meituan, agentic, model, inference the most. They currently have [-----] followers and [--] posts still getting attention that total [--] engagements in the last [--] hours.

### Engagements: [--] [#](/creator/twitter::1961699105434210304/interactions)
![Engagements Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1961699105434210304/c:line/m:interactions.svg)

- [--] Week [-----] -77%
- [--] Month [-------] +3.30%

### Mentions: [--] [#](/creator/twitter::1961699105434210304/posts_active)
![Mentions Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1961699105434210304/c:line/m:posts_active.svg)

- [--] Month [--] no change

### Followers: [-----] [#](/creator/twitter::1961699105434210304/followers)
![Followers Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1961699105434210304/c:line/m:followers.svg)

- [--] Week [-----] +0.43%
- [--] Month [-----] +11%

### CreatorRank: [---------] [#](/creator/twitter::1961699105434210304/influencer_rank)
![CreatorRank Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1961699105434210304/c:line/m:influencer_rank.svg)

### Social Influence

**Social category influence**
[technology brands](/list/technology-brands)  78.05% [finance](/list/finance)  2.44% [stocks](/list/stocks)  2.44% [social networks](/list/social-networks)  2.44%

**Social topic influence**
[meituan](/topic/meituan) #22, [agentic](/topic/agentic) 12.2%, [model](/topic/model) 12.2%, [inference](/topic/inference) 12.2%, [llm](/topic/llm) 9.76%, [deep](/topic/deep) 4.88%, [key](/topic/key) 4.88%, [environment](/topic/environment) 4.88%, [open ai](/topic/open-ai) 4.88%, [realtime](/topic/realtime) 4.88%

**Top accounts mentioned or mentioned by**
[@eliebakouch](/creator/undefined) [@lmsysorg](/creator/undefined) [@007killpop](/creator/undefined) [@fredsakay55580](/creator/undefined) [@xeophon](/creator/undefined) [@kimimoonshot](/creator/undefined) [@adinayakup](/creator/undefined) [@xianbao_qian](/creator/undefined) [@32](/creator/undefined) [@41](/creator/undefined) [@google](/creator/undefined) [@alibabaqwen](/creator/undefined) [@xianbaoqian](/creator/undefined) [@zaiorg](/creator/undefined) [@thorisop2345](/creator/undefined) [@astrodevil](/creator/undefined) [@airesearch12](/creator/undefined) [@zcbtrak](/creator/undefined) [@artificialanlys](/creator/undefined) [@zephyrz9](/creator/undefined)

**Top assets mentioned**
[Alphabet Inc Class A (GOOGL)](/topic/$googl)
### Top Social Posts
Top posts by engagements in the last [--] hours

"🚀 Introducing LongCat-Flash-Thinking-2601 A version built for deep and general agentic thinking. ✨ Highlights: 🤖 Top Tier Agent Capabilities 🔹 Performance: Top tier benchmark results (TIR / Agentic Search / Agentic Tool Use) ; superb generalization ability outperforming Claude in complex random tasks 🔹 Env Scaling: Multiple automaticly constructed high-quality environments; dense dependency graph 🔹 Multi-Env RL: Extended DORA (our RL infra) supporting large-scale multi-environment agentic training 🛡 Real-World Robustness 🔹 Performance: Solid performance in messy uncertain scenarios"  
[X Link](https://x.com/Meituan_LongCat/status/2011515214521647603)  2026-01-14T19:06Z [----] followers, 82.3K engagements


"🚀 LongCat-Flash-Thinking-2601 Technical Report Now Fully Released Key insights: 🌍 Large-scale agentic RL (14 pages of deep dives) 🔹 Environment scaling: A detailed look at our automated pipeline that builds 10000+ executable verifiable environments across 20+ domains. 🔹 RL infrastructure: An upgraded DORA framework that supports async training with 32000+ concurrent environments tackling stability issues in long-tail and highly heterogeneous tasks. 🛡 Robustness in the wild 🔹 Noise injection: No more "greenhouse" agents. We systematically analyze real-world noise (user/tool noise) and"  
[X Link](https://x.com/Meituan_LongCat/status/2014700094453342638)  2026-01-23T14:01Z [----] followers, 48.5K engagements


"🚀 Scaling embeddings not just expertsintroducing a new path for efficient LLMs. Key Finding: In high-sparsity scenarios N-gram embeddings yield a better Pareto frontier than just adding more MoE experts. Therefore we introduce LongCat-Flash-Litethe first opensource model built on this insight. ⚙ 68.5B Total Params(37.13B non-embedding) 2.9B4.5B Active 📊 High Performance: SWE-Bench [----] -Bench [----] TerminalBench [-----] 📃 256K Context Window (YARN-powered) ✨ Optimized for Agentic/Coding strong in general reasoning ⚡ [---] tokens/s peak inference speed The result: Achieves competitive"  
[X Link](https://x.com/Meituan_LongCat/status/2016548500457357324)  2026-01-28T16:26Z [----] followers, 70.5K engagements


"LongCat-Flash-Lite now supports API access (500700 tps generation speed depends on data distribution) You can apply on the LongCat API page. For now the model has unlimited quota. Later on Lite will offer a free tier with [--] million tokens per day. 🌐 Official site: ⚙ LongCat API Platform: Inference code for LongCat Series is also open-sourced. Thanks to the SGLang community @lmsysorg for the solid work. GitHub: https://github.com/meituan-longcat/SGLang-FluentLLM https://longcat.chat/platform/usage https://longcat.ai https://github.com/meituan-longcat/SGLang-FluentLLM"  
[X Link](https://x.com/Meituan_LongCat/status/2019773072849637725)  2026-02-06T14:00Z [----] followers, 11.6K engagements


"🔥 LongCat API Platform is LIVE Developers: Claim your [------] FREE tokens per day and leverage our cutting-edge LLM capabilities. 🛠 LongCat API Platform is compatible with two leading API formats - choose OpenAI API or Anthropic API based on your needs Build test and deploy AI solutions with unmatched efficiency. 🚀 Start building today: https://longcat.chat/platform https://longcat.chat/platform https://longcat.chat/platform https://longcat.chat/platform"  
[X Link](https://x.com/Meituan_LongCat/status/1964330726381539473)  2025-09-06T14:11Z [----] followers, [---] engagements


"🎉LongCat's Latest Updates: [--] API Access: LongCat-Flash-Thinking is now available via API (Claude Code integration compatible) [--] Daily Free Quota: Increased from [------] [------] tokens/day [--] Apply for More: Submit request on "Usage Info" page for 5M tokens/day after approval [--] New Docs: Change Log & Claude Code Configuration 🔄 Updated: API Docs Quick Start Guide FAQ Explore the speed & power of LongCat with ease ⚡ 🔗 LongCat API Platform: 🤗 HuggingFace: 💻 GitHub: https://github.com/meituan-longcat/LongCat-Flash-Thinking https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking"  
[X Link](https://x.com/Meituan_LongCat/status/1970495838725247486)  2025-09-23T14:29Z [----] followers, [---] engagements


"🚀 LongCat-Flash-Chat Launches 560B Total Params 18.6B-31.3B Dynamic Activation Trained on 20T Tokens 100+ tokens/sec Inference High Performance: TerminalBench [----] -Bench [----] 🔗 Model: 💻 Try Now: https://longcat.ai https://huggingface.co/meituan-longcat/LongCat-Flash-Chat https://longcat.ai https://huggingface.co/meituan-longcat/LongCat-Flash-Chat"  
[X Link](https://x.com/anyuser/status/1961827385667690965)  2025-08-30T16:24Z [----] followers, 299.8K engagements


"@eliebakouch Appreciate the deep dive"  
[X Link](https://x.com/anyuser/status/1962387758984622521)  2025-09-01T05:31Z [----] followers, [----] engagements


"@lmsysorg 🚀 Heartfelt thanks to SGLang Team for your exceptional inference acceleration framework"  
[X Link](https://x.com/anyuser/status/1962731670311968796)  2025-09-02T04:17Z [----] followers, [---] engagements


"🔥 LongCat API Platform is LIVE Developers: Claim your [------] FREE tokens per day and leverage our cutting-edge LLM capabilities. 🛠 LongCat API Platform is compatible with two leading API formats - choose OpenAI API or Anthropic API based on your needs Build test and deploy AI solutions with unmatched efficiency. 🚀 Start building today: https://longcat.chat/platform https://longcat.chat/platform"  
[X Link](https://x.com/anyuser/status/1964332140600185257)  2025-09-06T14:17Z [----] followers, 33.7K engagements


"🚀 LongCat-Flash-Thinking: Smarter reasoning leaner costs 🏆Performance: SOTA open-source models on Logic/Math/Coding/Agent tasks 📊 Efficiency: 64.5% fewer tokens to hit top-tier accuracy on AIME25 with native tool use agent-friendly ⚙Infrastructure: Async RL achieves a 3x speedup over Sync frameworks 🔗Model: 💻 Try Now: https://longcat.ai https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking https://longcat.ai https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking"  
[X Link](https://x.com/anyuser/status/1969823529760874935)  2025-09-21T17:58Z [----] followers, 152.1K engagements


"🎉LongCat's Latest Updates: [--] API Access: LongCat-Flash-Thinking is now available via API (Claude Code integration compatible) [--] Daily Free Quota: Increased from [------] [------] tokens/day [--] Apply for More: Submit request on "Usage Info" page for 5M tokens/day after approval [--] New Docs: Change Log & Claude Code Configuration 🔄 Updated: API Docs Quick Start Guide FAQ Explore the speed & power of LongCat with ease ⚡ 🔗 LongCat API Platform: 🤗 HuggingFace: 💻 GitHub: https://github.com/meituan-longcat/LongCat-Flash-Thinking https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking"  
[X Link](https://x.com/anyuser/status/1970496746313916881)  2025-09-23T14:33Z [----] followers, 17.4K engagements


"🎉 LongCat-Audio-Codec is officially OPEN SOURCED 🚀 -an audio codec solution optimized specifically for Speech LLMs. Key Breakthroughs: [--]. Dual Tokens: Semantic and Acoustic Tokens are extracted in parallel at a low frame rate (16.7Hz / 60ms).This ensures both efficient modeling and full information integrity. [--]. Ultra-Efficiency: LongCat-Audio-Codec maintains high intelligibility even at an extremely low bitrate such as [----] kbps. [--]. Real-Time Ready: Features a low-latency streaming decoder architecture. Latency is controlled to the hundred-millisecond level for real-time interaction. The"  
[X Link](https://x.com/anyuser/status/1979185632392913014)  2025-10-17T14:00Z [----] followers, 29.2K engagements


"🔥 Meituan LongCat Team introduces VitaBench An Agent Benchmark for Complex Real-Life Scenarios VitaBench focuses on three high-frequency real-life domains: Food Delivery Restaurants and Travel Services systematically and quantitively measuring agents' ability in Reasoning Tool Use and Adaptive Interaction. We believe that our data construction procedure shares some valuable insight about controllably building up high-quality & difficult agentic training tasks. Across 20+ top models success rates remain low: cross-scenario Avg@4: 30% single-scenario Avg@4: 48.3% cross-scenario Pass@4(1"  
[X Link](https://x.com/anyuser/status/1980273045697703978)  2025-10-20T14:01Z [----] followers, 12.8K engagements


"🚀 LongCat-Video Now Open-Source: Text/Image-to-Video + Video Continuation in One Model 🏆 Text/Image-to-Video Performance Hits Open-Source SOTA 🎬 Minutes-Long High-Quality Videos: No Color Drift/Quality Loss (Industry-Standout) ⚙ 13.6B Params Strong Open-Source DiT-Based Unified Multitask Video Base Model ⚡ C2F Pipeline + Block Sparse Attention: 720p/30fps Video in Minutes 🤗 Open-Source Links: Hugging Project https://meituan-longcat.github.io/LongCat-Video/ https://huggingface.co/meituan-longcat/LongCat-Video https://github.com/meituan-longcat/LongCat-Video"  
[X Link](https://x.com/anyuser/status/1982083998852763838)  2025-10-25T13:57Z [----] followers, 44.1K engagements


"🔥 LongCat-Flash-Omni: Multimodal + Low-Latency 🏆 Leading Performance among Open-Source Omni-modal Models ☎ Real-time Spoken Interaction: Millisecond-level E2E latency 🕒 128K context + Supports 8min real-time AV interaction 🎥 Multimodal I/O: Arbitrary Combination of Text/Image/Audio/Video Input Text/Speech Output (w/ LongCat-Audio-Codec) ⚙ ScMoE architecture on LongCat-Flash: 560B Parameters 27B Active 🧠 Training: Novel Early-Fusion Omni-modal training paradigm - No Single Modality Left Behind 🚀 Efficient Infrastructure: With optimized modality-decoupled parallel training Omni sustains"  
[X Link](https://x.com/anyuser/status/1984398560973242733)  2025-10-31T23:14Z [----] followers, 194.7K engagements


"@xeophon Your LLM deliveryhas arrived Please remember to leave a five-star review. 🐱miao"  
[X Link](https://x.com/anyuser/status/1984572798921293987)  2025-11-01T10:46Z [----] followers, 51.7K engagements


"Explore UNO-Bench: A Unified Omni-Modal Benchmark 🚀 Unified Framework: Efficient uni/omni-modal understanding evaluation 📊 Comprehensive Evaluation: [--] task types across [--] modality combinations; Perception & Reasoning coverage 🗒 High-Quality Dataset: human centric construction with 98% cross-modality solvable ⚡ Efficiency: +90% faster datasets via auto-compression at 98% consistency (18 benchmarks) 🔥 Real-World Relevance: Authentic Chinese contexts & Multi-Step Open-Ended Questions for reliable assessment 🤖 Universal scoring model: supporting 6-type questions; 95% OOD model accuracys 🧠"  
[X Link](https://x.com/anyuser/status/1986074355181424959)  2025-11-05T14:13Z [----] followers, 14.7K engagements


"🔥 LongCat-Flash-Omni: Multimodal + Low-Latency 🏆 Leading Performance among Open-Source Omni-modal Models ☎ Real-time Spoken Interaction: Millisecond-level E2E latency 🕒 128K context + Supports 8min real-time AV interaction 🎥 Multimodal I/O: Arbitrary Combination of Text/Image/Audio/Video Input Text/Speech Output (w/ LongCat-Audio-Codec) ⚙ ScMoE architecture on LongCat-Flash: 560B Parameters 27B Active 🧠 Training: Novel Early-Fusion Omni-modal training paradigm - No Single Modality Left Behind 🚀 Efficient Infrastructure: With optimized modality-decoupled parallel training Omni sustains"  
[X Link](https://x.com/Meituan_LongCat/status/1984394973400498301)  2025-10-31T23:00Z [----] followers, [---] engagements


"🔥 Introducing AMO-Bench: Challenging the Boundary of LLM Reasoning on IMO-Level Problems Original Problems: [--] brand-new problems designed by human experts Guaranteed Difficulty: Cross-validated to ensure at least IMO-level difficulty Automatic Grading: Hybrid grading algorithm with 99.2% scoring accuracy Human-Annotated CoT: Facilitate further case analysis to improve model Key Findings: @Kimi_Moonshot (🏆Kimi-k2-Thinking) achieved 56% SOTA performance followed by GPT-5-thinking (high) and Qwen3-235B-A22B-Thinking-2507; The majority of results are below 40%. Welcome to try AMO-Bench and"  
[X Link](https://x.com/Meituan_LongCat/status/1991137131578745231)  2025-11-19T13:31Z [----] followers, 82.4K engagements


"@Kimi_Moonshot Amazing BenchmarkCongrats"  
[X Link](https://x.com/Meituan_LongCat/status/1991140727888171418)  2025-11-19T13:45Z [----] followers, [---] engagements


"New on LongCat App Video Call + Deep Think Mode are here Feature 1: Visual Interaction Intelligence Built for Real Life 👔 Smart outfit matching ✈ On-the-go travel guidance 🔨 Instant help with everyday tasks ⛅ Emotional support for daily life Feature 2: Deep Think Mode Depth Meets Speed 🧠 More reasoning. More clarity. ⚡ Powerful. Precise. Still Fast. Experience the next level of AI interaction. 📲 Now live in the LongCat App (Available only in China Region) #AI #Multimodal"  
[X Link](https://x.com/Meituan_LongCat/status/1992956621308281183)  2025-11-24T14:01Z [----] followers, [---] engagements


"New on LongCat App Video Call + Deep Think Mode are here Feature 1: Visual Interaction Intelligence Built for Real Life 👔 Smart outfit matching ✈ On-the-go travel guidance 🔨 Instant help with everyday tasks ⛅ Emotional support for daily life Feature 2: Deep Think Mode Depth Meets Speed 🧠 More reasoning. More clarity. ⚡ Powerful. Precise. Still Fast. Experience the next level of AI interaction. 📲 Now live in the LongCat App (Available only in China Region) #AI #Multimodal"  
[X Link](https://x.com/Meituan_LongCat/status/1992961957289509087)  2025-11-24T14:22Z [----] followers, [----] engagements


"🔥 AMO-Bench Leaderboard update @Google Gemini-3-Pro claims the crown at 63.1% (AVG@32) new SOTA @Alibaba_Qwen Qwen3-Max-Thinking surges to 2nd with 57.4% (AVG@32) hot on its heels. New insight: Although the current SOTA remains in closed-source models the most valuable insight is open-source models remarkable pace of catching up. Meanwhile at comparable performance levels Gemini-3-Pro has significantly fewer average output tokens (more concise outputs) demonstrating superior output efficiency. 😊Open-Source: Github Paper Project Page https://amo-bench.github.io"  
[X Link](https://x.com/Meituan_LongCat/status/1993318759843741838)  2025-11-25T14:00Z [----] followers, 77.4K engagements


"🚀 Experience the "Fast Real & Precise" Revolution with LongCat LongCat-Image's powerful text-to-image and image editing features are live in LongCat App and now 📸 True-to-Life Aesthetics Achieve "Photography-Level" texture. From skin pores and fabric folds to realistic lighting and physical logic every pixel is rendered with authentic beauty. Flawless Text Rendering The industry standard for Chinese text. Create shop signs posters and covers with zero typos. Whether it's complex calligraphy or modern fonts we ensure perfect layout and legibility. 🪄 Smart Instruction Editing Just type a"  
[X Link](https://x.com/Meituan_LongCat/status/1994405925340479750)  2025-11-28T14:00Z [----] followers, [----] engagements


"🚀 LongCat-Image is now open-source A bilingual (CN/EN) image generation & editing model with exceptional consistency clarity and text precision. 🔄 Superior editing performance with accurate visual alignment 📝 Renders complex Chinese characters incl. rare glyphs 🖼 Realistic rendering powered by data strategy and RL training ⚡ Fast low-VRAM lightweight inference ⚙ 6B hybrid DiT architecture achieves 20B+ MoE performance 📊 Objective benchmarks prove it LongCat-Image leads open-source: - Image Editing: ImgEdit [----] (open-source SOTA) GEdit CN/EN 7.60/7.64 rivals commercial ones; - Text"  
[X Link](https://x.com/Meituan_LongCat/status/1996950202687918586)  2025-12-05T14:30Z [----] followers, 112K engagements


"🚀Our Free LongCat APIs Backend Model Gets Updated LongCat-Flash-Chat New Update is arriving Building on "extreme efficiency" & "lightning-fast response" this upgrade reinforces long-context capability and real-task performance. 🔺 256K Context: Doubled from previous 128K with top-tier info capture accuracy. 🤖 Agentic coding: Built for developers who actually ship. Full-stack apps across mobile desktop and cross-platform. ⚙ SOTA Tool Use: High precision and robust execution even in non-thinking modes. 🌏 Multilingual Support: Enhanced support for [--] new languages (ES FR AR PT RU ID DE KO JA)."  
[X Link](https://x.com/Meituan_LongCat/status/2003103246177775968)  2025-12-22T14:00Z [----] followers, 15.5K engagements


"@xeophon Thanks So glad you like the [--] thinkers 😊"  
[X Link](https://x.com/Meituan_LongCat/status/2011516739113332743)  2026-01-14T19:12Z [----] followers, [----] engagements


"@Xianbao_QIAN Thanks for the shoutout 🎉The WeChat group will be the first to get hands-on access to our upcoming 1M-token context feature (powered by Zigzag Attention)"  
[X Link](https://x.com/Meituan_LongCat/status/2011643008769540297)  2026-01-15T03:34Z [----] followers, [---] engagements


"@Zai_org Appreciate the reminder 🙏 Well update to the latest logo in our technical reports and related media materials. Stay tuned for more updates and were always open to further discussions ❤"  
[X Link](https://x.com/Meituan_LongCat/status/2011669517672595710)  2026-01-15T05:19Z [----] followers, [----] engagements


"@eliebakouch You got it Yes that's exactly the paper. Stay tuned we're hyped too"  
[X Link](https://x.com/Meituan_LongCat/status/2011695911735627822)  2026-01-15T07:04Z [----] followers, [---] engagements


"@THORISOP2345 Thanks a lot More to come.🚀"  
[X Link](https://x.com/Meituan_LongCat/status/2011696084327022980)  2026-01-15T07:04Z [----] followers, [---] engagements


"@Astrodevil_ Thanks"  
[X Link](https://x.com/Meituan_LongCat/status/2011697960443338849)  2026-01-15T07:12Z [----] followers, [---] engagements


"@airesearch12 Thanks More awesome on the way. 😄"  
[X Link](https://x.com/Meituan_LongCat/status/2011698287360033062)  2026-01-15T07:13Z [----] followers, [---] engagements


"@zcbtrak @ArtificialAnlys Agreed"  
[X Link](https://x.com/Meituan_LongCat/status/2011699718251036916)  2026-01-15T07:19Z [----] followers, [---] engagements


"@eliebakouch Thankswell keep pushing deeper"  
[X Link](https://x.com/Meituan_LongCat/status/2011714055023837420)  2026-01-15T08:16Z [----] followers, [---] engagements


"@zephyr_z9 We are proud to be a part of the open-source community"  
[X Link](https://x.com/Meituan_LongCat/status/2011715338522775996)  2026-01-15T08:21Z [----] followers, [---] engagements


"🚀 LongCat-Flash-Thinking-2601 Technical Report Now Fully Released Key insights 🌍 Large-scale agentic RL (14 pages of deep dives) 🔹 Environment scaling: A detailed look at our automated pipeline that builds 10000+ executable verifiable environments across 20+ domains. 🔹 RL infrastructure: An upgraded DORA framework that supports async training with 32000+ concurrent environments tackling stability issues in long-tail and highly heterogeneous tasks. 🛡 Robustness in the wild 🔹 Noise injection: No more "greenhouse" agents. We systematically analyze real-world noise (user/tool noise) and"  
[X Link](https://x.com/Meituan_LongCat/status/2014699662343598293)  2026-01-23T14:00Z [----] followers, [--] engagements


"A huge thank you to the fantastic teams at @lmsysorg for the incredible day-0 support 🎉 LongCat-Flash-Thinking-2601 was built for deep and general agentic thinking and together with SGLangs high-performance inference engine they form a powerhouse duo. Cant wait to see what the community builds go try it and share your creations 🔥 🎉 Congrats to @Meituan_LongCat on releasing LongCat-Flash-Thinking-2601 a massive model built for deep general agentic reasoning. Were excited to announce day-0 support for LongCat-Flash-Thinking-2601 in SGLang🙌 If youre serving large-scale agent models with"  
[X Link](https://x.com/Meituan_LongCat/status/2011652492665499719)  2026-01-15T04:11Z [----] followers, [----] engagements


"@eliebakouch 🫰"  
[X Link](https://x.com/Meituan_LongCat/status/2014726783879590068)  2026-01-23T15:47Z [----] followers, [----] engagements


"Meet LongCat-Video-Avatar: a robust audio-driven avatar model that pushes the boundaries of long-form video generation. Compared with the previous InfiniteTalk LongCat-Video-Avatar delivers far better long-sequence stability and realism. New highlights ⚙ Built on the LongCat-Video architecture now supporting Audio-Text-to-Video (AT2V) Audio-Text-Image-to-Video (ATI2V) and Video Continuation modes. 🎭 Open-source SOTA Realism: Ranked 1st in overall anthropomorphism scores for both single and multi-subject scenarios in EvalTalker evaluations (492 participants [--] independent raters per video). ♾"  
[X Link](https://x.com/Meituan_LongCat/status/2000929976917615040)  2025-12-16T14:04Z [----] followers, 27.5K engagements

Limited data mode. Full metrics available with subscription: lunarcrush.com/pricing