跳轉到主要內容

LongCat Flash Lite

LongCat開源權重MIT · 商用許可

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.

發布日期
2026-01-28
參數規模
68.5B
上下文長度
支援模態
text

能力雷達圖

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

排行榜排名

領域#排名分數來源
智慧體能力模型榜68
47.0
LS
程式碼能力榜390
25.0
AA
通用能力榜294
44.0
AA
科學能力342
40.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Agents

Terminal-Bench33.8%自報

Biology

GPQANYU + Cohere + Anthropic (2023)66.8%自報

Code

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

Communication

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

Finance

MMLU85.5%自報
MMLU-Pro78.3%自報

General

CMMLU82.5%自報

Math

MATH-50096.8%自報
AIME 202472.2%自報
AIME 202563.2%自報

AA 評測指數

(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 分類評分

(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

定價

輸入價格免費
輸出價格免費
混合價格(3:1)免費

速度

Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s

供應商價格排行

供應商價格排行

1 個供應商

供應商輸入輸出
1Meituan
$0
$0

比較該模型在不同 API 供應商之間的定價。

外部連結