LongCat-Flash-Lite

Name: LongCat-Flash-Lite
Author: Meituan

Meituan

LongCat Flash Lite is a lightweight variant of Meituan's LongCat model family, optimized for speed and minimal resource usage. It supports long-context processing while delivering fast inference, suitable for applications requiring efficient text processing at scale.

Key Specifications

Parameters

68.5B

Context

Release Date

February 4, 2026

Average Score

67.3%

API Documentation Model Weights

Timeline

Key dates in the model's history

Announcement

February 4, 2026

Last Update

February 17, 2026

Today

October 5, 2026

Technical Specifications

Parameters

68.5B

Training Tokens

Knowledge Cutoff

Family

Capabilities

MultimodalZeroEval

Benchmark Results

Model performance metrics across various tests and benchmarks

General Knowledge

Tests on general knowledge and understanding

MMLU

• Self-reported

86.0%

Programming

Programming skills tests

SWE-Bench Verified

Self-reported by the model provider • Self-reported

54.4%

Reasoning

Logical reasoning and analysis

GPQA

• Self-reported

66.8%

Other Tests

Specialized benchmarks

MATH-500

• Self-reported

97.0%

CMMLU

• Self-reported

82.0%

MMLU-Pro

• Self-reported

78.0%

Tau2 Retail

Avg@8 • Self-reported

73.0%

Tau2 Telecom

Avg@8 • Self-reported

73.0%

AIME 2024

avg@32 • Self-reported

72.2%

AIME 2025

avg@32 • Self-reported

63.2%

SWE-bench Multilingual

Self-reported by the model provider • Self-reported

38.1%

Tau2 Airline

avg@8 • Self-reported

58.0%

Terminal-Bench

Self-reported by the model provider • Self-reported

33.8%

License & Metadata

License

mit

Announcement Date

February 4, 2026

Last Updated

February 17, 2026

Similar Models

All Models

LongCat-Flash-Thinking

Meituan

560.0B

Best score:0.8 (TAU)

Released:Sep 2025

LongCat-Flash-Chat

Meituan

560.0B

Best score:0.9 (MMLU)

Released:Aug 2025

Llama 3.1 70B Instruct

Hermes 3 70B

Nous Research

70.0B

Best score:0.8 (MMLU)

Released:Aug 2024

Llama 3.1 Nemotron 70B Instruct

NVIDIA

70.0B

Best score:0.8 (MMLU)

Released:Oct 2024

Phi 4

Microsoft

14.7B

Best score:0.8 (MMLU)

Released:Dec 2024

Price:$0.07/1M tokens

Phi-3.5-MoE-instruct

Microsoft

60.0B

Best score:0.9 (ARC)

Released:Aug 2024

Magistral Small 2506

Mistral AI

24.0B

Best score:0.7 (GPQA)

Released:Jun 2025

Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.