跳转到主要内容

LongCat-Flash-Thinking

MeituanOpen WeightMIT · Commercial OK

描述

LongCat-Flash-Thinking is Meituan's reasoning model built on the LongCat-Flash foundation with 560B total parameters (MoE, ~27B activated). It introduces a training pipeline specifically tuned for advanced reasoning, featuring Re-thinking Mode that delivers parallel reasoning paths for sophisticated decision-making. Achieves strong performance on mathematical reasoning, agentic tool use, and formal theorem proving benchmarks.

发布日期
2025-09-22
参数规模
560.0B
上下文长度
支持模态
text

能力雷达图

80
general
70
coding
90
reasoning
68
science估算
70
agents
0
multimodal

Science 在缺少专门科学评测时使用推理能力代理估算。

排行榜排名

领域#排名分数来源
智能体与工具8
74.0
LS
推理能力59
62.0
LS

基准测试分数 (LLM Stats)

Agents

BFCL-v374.4%自报

Biology

GPQA81.5%自报

Code

LiveCodeBench79.4%自报
SWE-Bench Verified59.4%自报

Communication

Tau2 Telecom83.1%自报
Tau2 Retail71.5%自报
Tau2 Airline67.5%自报

Finance

MMLU-Pro82.6%自报

General

MMLU-Redux89.3%自报

Math

MATH-50099.2%自报
AIME 202493.3%自报
AIME 202590.6%自报

Reasoning

ZebraLogic95.5%自报
ARC-AGI50.3%自报

AA 评测指数

暂无 AA 评测数据

LLM Stats 分类评分

Language
90
Math
90
Biology
80
Chemistry
80
Finance
80
General
80
Healthcare
80
Legal
80
Physics
80
Reasoning
80
Structured Output
70
Tool Calling
70
Agents
70
Code
70
Communication
70
Frontend Development
60
Spatial Reasoning
50
Vision
50

定价

暂无定价数据

速度

暂无速度数据

可用提供商

(LS 内部计价单位)

暂无提供商数据

外部链接