Meituan

Longcat Flash Chat

Name: Meituan Longcat Flash Chat
Author: Meituan

Compare

2025-09-09

Compare

LongCat Flash Chat is a large-scale Mixture-of-Experts model from Meituan with 560 billion total parameters, dynamically activating 18.6B to 31.3B (averaging ~27B) based on contextual demands. Its shortcut-connected MoE design achieves over 100 tokens per second during inference while supporting a 128K-token context window. The model delivers highly competitive performance in reasoning, coding, and instruction following, with exceptional strengths in agentic tasks and complex multi-step tool-use interactions.

Open ModelMIT

Knowledge Cutoff

2025-03-31

The date this AI finished learning. It may not know about things that happened after this date.

Input → Output Format

The types of content this AI can receive, and what it can produce in return.

Context Memory

131KIN131KOUT

The maximum amount of text the AI can read and process in a single request. A larger number means it can handle longer documents or conversations.

Cost/1M Words

$0.2IN$0.8OUT

The cost of using this AI directly in your own application. Shown in USD per 1 million units of text (tokens).

Calculate Cost

AI Performance Evaluation

Arena Overall Score

1434

±6

As of 2026-04-23

Overall Rank

No.53

9,660 Votes

Arena by Ability

Hard Prompts

1455±8No.51

Expert Knowledge

1456±21No.50

Instruction Following

1408±11No.73

Conversation Memory

1416±15No.80

Creative

1390±16No.74

Coding

1496±12No.37

Math

1429±22No.54

Arena by Occupation

Creative Writing

1388±13No.87

Social Sciences

1453±15No.52

Media

1396±14No.63

Business

1432±14No.55

Healthcare

1462±24No.51

Legal

1433±22No.67

Software

1486±10No.36

Mathematics

1440±25No.52

Source:Arena Intelligence

Overall

AA Intelligence Index

24%↓14%

Reasoning & Math

GPQA Diamond

64%↓18%

HLE

6.0%↓11%

Coding

AA Coding Index

17%↓18%

TAU2

80%↑6%

TerminalBench

11%↓20%

SciCode

28%↓12%

Language & Instructions

IFBench

43%↓14%

AA-LCR

26%↓36%

Output Speed

Standard Mode

115tok/s↑33

First Output 4.66s

Source:Artificial Analysis

Meituan