NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/LongCat Flash Chat
meituan logo

LongCat Flash Chat

by meituan · Released Sep 2025

Open Source
53.4
avg score
Rank #125
Compare
Better than 60% of all models
Context
131K tokens (~66 books)
Input $/1M
$0.20
Output $/1M
$0.80
Type
text
License
Open Source
Benchmarks
7 tested
Data as of
About

LongCat-Flash-Chat is a large-scale Mixture-of-Experts (MoE) model with 560B total parameters, of which 18.6B–31.3B (≈27B on average) are dynamically activated per input. It introduces a shortcut-connected MoE design to reduce...

Tested on 7 benchmarks · BenchGecko score 53.4. Top scores: Chatbot Arena Elo — Overall (1401.1%), OpenCompass — IFEval (90.2%), OpenCompass — MMLU-Pro (81.0%).

Looking for similar performance at lower cost?
Gemma 4 31B scores 53.3 (100% as good) at $0.09/1M input · 55% cheaper
Capabilities
coding
48.2
#100 globally
math
61.0
#82 globally
knowledge
53.2
#101 globally
language
90.2
#13 globally
Benchmark Scores
Compare All
Tested on 7 benchmarks · Ranked across 5 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
OpenCompass — LiveCodeBenchV6

OpenCompass Live Code Bench v6. Fresh competitive programming problems to evaluate code generation without memorization.

48.2·
mathCompare math →
OpenCompass — AIME2025

OpenCompass evaluation on AIME 2025 problems. Tests mathematical reasoning on fresh competition problems.

61.0·
knowledgeCompare knowledge →
OpenCompass — MMLU-Pro

OpenCompass MMLU-Pro evaluation. Harder knowledge test with more answer choices.

81.0·
OpenCompass — GPQA-Diamond

OpenCompass evaluation of GPQA Diamond. PhD-level science questions from the hardest subset.

70.1·
OpenCompass — HLE

OpenCompass evaluation of Humanitys Last Exam. Expert-level cross-discipline knowledge test.

8.5·
Quick compare:Google DeepMind logovs Gemma 4 31BAlibaba Qwen logovs Qwen3.5-35B-A3Bz-ai logovs GLM 4.6
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
Google DeepMind logo
Gemma 4 31B
Google DeepMind
53.3$0.09/1M
Alibaba Qwen logo
Qwen3.5-35B-A3B
Alibaba Qwen
53.5$0.15/1M
z-ai logo
GLM 4.6
z-ai
53.6$0.43/1M
Links
Info
meituanPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@meituan
Source Code
GitHubHugging Face
BenchGecko API
longcat-flash-chat
Specifications
  • Typetext
  • Context131K tokens (~66 books)
  • ReleasedSep 2025
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.001
Available On
meituan logomeituan$0.20
Categories
codingmathknowledgelanguage
Learn More
context-windowtransformeropen weightstokens
Share & Export
Tweet
Related Models
Google DeepMind logoGemma 4 31B
53.3
Alibaba Qwen logoQwen3.5-35B-A3B
53.5
z-ai logoGLM 4.6
53.6
DeepSeek logoDeepSeek R1 Distill Llama 8B
53.1
LongCat Flash Chat is an open-source text AI model by meituan, released in September 2025. It has an average benchmark score of 53.4. Context window: 131K tokens.

Related Models

Gemma 4 31B · Google DeepMindQwen3.5-35B-A3B · Alibaba QwenGLM 4.6 · z-aiDeepSeek R1 Distill Llama 8B · DeepSeekGrok 3 Mini Beta · xAI

Benchmarks

Chatbot Arena Elo — OverallOpenCompass — IFEvalOpenCompass — MMLU-ProOpenCompass — GPQA-DiamondOpenCompass — AIME2025

Related Pages

meituan · Providermeituan · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-04-14

  • LongCat Flash Chat by meituan. BenchGecko score 53.4, rank 125 of 312 scored models (normalized average of public benchmark scores).
  • List price $0.20 input · $0.80 output per 1M tokens (as of 2026-04-14).

How to cite · data as of 2026-04-14

LongCat Flash Chat · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-14. https://benchgecko.ai/model/longcat-flash-chat

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP