LongCat Flash Lite

Creator

LongCat

Released

2026-01-28

Intelligence

17.2

Artificial Analysis Index

Coding

Artificial Analysis Index

In $/1M

$0.00

input tokens

Out $/1M

$0.00

output tokens

Blended $/1M

$0.00

3:1 blended

Speed

0

tokens / sec

Profile

License, openness, and modality — the governance layer.

License

MIT

commercial OK

Weights

Open

downloadable

Modalities

Text

Parameters

69B

total

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.

Capability profile

Category strength across 20 domains, via LLM Stats.

math
80legal
80finance
80language
80healthcare
80biology
70general
70physics
70
chemistry
70reasoning
70tool calling
70communication
70frontend development
50code
40agents
30
Via LLM Stats

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
64
Humanity’s Last Exam
6
MMLU-Pro
SciCode
28
LiveCodeBench
MATH-500
AIME 2025
τ²-Bench (agentic)
80
Terminal-Bench Hard
11
IFBench
43
Via Artificial Analysis

Providers

Inference hosts serving this model — their own pricing and measured performance, cheapest input first.

ProviderIn $/1MOut $/1MThroughputLatencyStatus
Meituan$0.10$0.405001.50active
All providers

1 host · via LLM Stats

© 2026 NYSGPT2525 LLC