跳转到主要内容

LongCat Flash Lite

LongCat开源权重MIT · 商用许可

描述

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.

发布日期
2026-01-28
参数规模
68.5B
上下文长度
支持模态
text

能力雷达图

15
general
28
coding
64
reasoning
40
science
70
agents
0
multimodal

排行榜排名

领域#排名分数来源
智能体能力模型榜68
47.0
LS
代码能力榜390
25.0
AA
通用能力榜294
44.0
AA
科学能力342
40.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Agents

Terminal-Bench33.8%自报

Biology

GPQANYU + Cohere + Anthropic (2023)66.8%自报

Code

SWE-Bench Verified54.4%自报
SWE-bench Multilingual38.1%自报

Communication

Tau2 Retail73.1%自报
Tau2 Telecom72.8%自报
Tau2 Airline58.0%自报

Finance

MMLU85.5%自报
MMLU-Pro78.3%自报

General

CMMLU82.5%自报

Math

MATH-50096.8%自报
AIME 202472.2%自报
AIME 202563.2%自报

AA 评测指数

(Artificial Analysis)
Intelligence Index(Artificial Analysis)
17.4
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.8
Gpqa(NYU + Cohere + Anthropic (2023))
0.6
Ifbench(Google Research (2023))
0.4
Lcr(Artificial Analysis)
0.3
Scicode(UIUC + Argonne National Lab (2024))
0.3
Terminalbench Hard(Stanford × Laude Institute (2026))
0.1
Hle(Center for AI Safety + Scale AI (2025))
0.1

LLM Stats 分类评分

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

定价

输入价格免费
输出价格免费
混合价格(3:1)免费

速度

Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s

供应商价格排行

供应商价格排行

1 个供应商

供应商输入输出
1Meituan
$0
$0

比较该模型在不同 API 供应商之间的定价。

外部链接