LongCat-Flash-Chat

Name: LongCat-Flash-Chat
Author: Meituan

Meituan

LongCat Flash Chat is a conversational variant of Meituan's LongCat model, optimized for multi-turn dialogue and chat applications. It combines long-context understanding with fast inference speed, delivering responsive and coherent conversations.

Key Specifications

Parameters

560.0B

Context

Release Date

August 28, 2025

Average Score

74.0%

API Documentation Research Paper Repository Model Weights

Timeline

Key dates in the model's history

Announcement

August 28, 2025

Last Update

February 17, 2026

Today

September 10, 2026

Technical Specifications

Parameters

560.0B

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

90.0%

Programming

Programming skills tests

HumanEval

HumanEval+ Pass@1 • Self-reported

88.0%

SWE-Bench Verified

Self-reported by the model provider • Self-reported

60.4%

Reasoning

Logical reasoning and analysis

GPQA

• Self-reported

73.2%

DROP

F1 score • Self-reported

79.1%

Other Tests

Specialized benchmarks

MATH-500

• Self-reported

96.0%

IFEval

• Self-reported

90.0%

ZebraLogic

• Self-reported

89.0%

CMMLU

• Self-reported

84.0%

MMLU-Pro

• Self-reported

82.7%

AIME 2025

avg@10 • Self-reported

61.3%

LiveCodeBench

pass@1 • Self-reported

48.0%

Tau2 Airline

avg@4 • Self-reported

58.0%

Tau2 Retail

avg@4 • Self-reported

71.3%

Tau2 Telecom

avg@4 • Self-reported

73.7%

Terminal-Bench

Self-reported by the model provider • Self-reported

39.5%

License & Metadata

License

mit

Announcement Date

August 28, 2025

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-Thinking-2601

Meituan

560.0B

Best score:1.0 (TAU)

Released:Jan 2026

LongCat-Flash-Lite

Meituan

68.5B

Best score:0.9 (MMLU)

Released:Feb 2026

Command R+

Cohere

104.0B

Best score:0.8 (MMLU)

Released:Aug 2024

Price:$0.25/1M tokens

Kimi K2-Thinking-0905

Moonshot AI

1.0T

Best score:0.8 (GPQA)

Released:Sep 2025

Price:$0.60/1M tokens

Jamba 1.5 Large

AI21 Labs

398.0B

Best score:0.9 (ARC)

Released:Aug 2024

Price:$2.00/1M tokens

MiniMax M2

MiniMax

230.0B

Best score:0.8 (GPQA)

Released:Oct 2025

Price:$0.30/1M tokens

Llama 3.1 Nemotron Ultra 253B v1

NVIDIA

253.0B

Best score:0.8 (GPQA)

Released:Apr 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.