Skip to main content

LongCat Flash Lite

LongCatOpen WeightMIT · Commercial OK

Description

LongCat-Flash-Lite is a lightweight MoE model from Meituan with 68.5B total parameters and only 2.9B-4.5B activated per token. It explores N-gram embedding expansion as a new scaling direction, supporting 256K context length via YaRN. Optimized for agent tooling and programming tasks, achieving 500-700 tokens per second inference speed while maintaining strong performance on coding, math, and agentic benchmarks.

Release Date
2026-01-28
Parameters
68.5B
Context Length
—
Modalities
text

Capability Radar

70
general
40
coding
80
reasoning
60
scienceest.
70
agents
0
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Chat

Tau2 Airline58.0%SR

Communication

Tau2 Retail73.1%SR
Tau2 Telecom72.8%SR

General

MMLU85.5%SR

Language

CMMLU82.5%SR
MMLU-Pro78.3%SR

Math

MATH-50096.8%SR
AIME 202472.2%SR
AIME 202563.2%SR

Reasoning

GPQANYU + Cohere + Anthropic (2023)66.8%SR
SWE-Bench Verified54.4%SR
SWE-bench Multilingual38.1%SR
Terminal-Bench33.8%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Language
80
Legal
80
Math
80
Finance
80
Healthcare
80
Physics
70
Reasoning
70
General
70
Biology
70
Chemistry
70
Communication
70
Tool Calling
70
Chat
60
Frontend Development
50
Code
40
Agents
30

Pricing

Input Price$0.1 / 1M tokens
Output Price$0.4 / 1M tokens
Blended Price (3:1)$0.175 / 1M tokens

Speed

No speed data available

Provider Price Ranking

Provider Price Ranking

2 providers

Cheapest: LongCatMost Expensive: Meituan
ProviderInputOutput
1LongCatPRIMARY
$0.1
$0.4
2Meituan
$0.1
$0.4

Compare pricing across different API providers for this model.

External Sources