Meituan model product
LongCat Flash Chat
3B parameters (~27B average) based on contextual demands.
Updated Aug 12, 2026. Default version: LongCat-Flash-Chat
LLMBoard score36.9LongCat-Flash-Chat
Coverage100%16 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable
LongCat Flash Chat Specifications
Technical details for the model's default version.
- Version
- LongCat-Flash-Chat
- Released
- Aug 29, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 560B
- Context window
- 128K
- Max output
- 128K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- MIT
LongCat Flash Chat Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
LongCat Flash Chat Benchmark Results
Benchmark scores for LongCat-Flash-Chat.
| CMMLU | 84.3% | 03 | 6 | 60.0% | C | |
| ZebraLogic | 89.3% | 04 | 8 | 57.1% | C | |
| Terminal-Bench | 39.5% | 09 | 25 | 66.7% | C | |
| MMLU | 89.7% | 12 | 100 | 88.9% | C | |
| MATH-500 | 96.4% | 13 | 32 | 61.3% | C | |
| Tau2 Airline | 58.0% | 13 | 23 | 45.5% | C | |
| DROP | 79.1% | 16 | 30 | 48.3% | C | |
| HumanEval | 88.4% | 19 | 66 | 72.3% | C | |
| Tau2 Retail | 71.3% | 19 | 26 | 28.0% | C | |
| IFEval | 89.6% | 20 | 65 | 70.3% | C | |
| Tau2 Telecom | 73.7% | 24 | 35 | 32.4% | C | |
| MMLU-Pro | 82.7% | 33 | 129 | 75.0% | C | |
| LiveCodeBench | 48.0% | 48 | 73 | 34.7% | C | |
| SWE-Bench Verified | 60.4% | 79 | 105 | 25.0% | C | |
| AIME 2025 | 61.3% | 97 | 114 | 15.0% | C | |
| GPQA | 73.2% | 117 | 234 | 50.2% | C |
LongCat Flash Chat Arena Results
Preference and agent-evaluation results for the default version.
| text style control | overall | 81 | 1435.7 | 28,034 | N/A | |
| text | overall | 82 | 1425.9 | 28,034 | N/A | |
| text | overall | 89 | 1422.3 | 11,433 | N/A | |
| text factuality | overall | 100 | 1428.0 | 27,955 | N/A | |
| text style control | overall | 136 | 1401.0 | 11,433 | N/A |
LongCat Flash Chat Runtime Performance
Provider-specific output speed and catalog latency for LongCat-Flash-Chat. Runtime does not affect the capability score.
| Meituan | 100 tok/s | 3 s | 128K | 128K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
LongCat Flash Chat Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
LongCat Flash Chat Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| LongCat-Flash-Chat | 36.9 | 560B | 128K | 128K | No | MIT |
What is LongCat Flash Chat?
Key information about LongCat Flash Chat and its available data.
3B parameters (~27B average) based on contextual demands. It features Zero-Computation Experts for efficient routing and supports 128K context.
Optimized for conversational and agentic tasks, it shows competitive performance across reasoning, coding, instruction following, and domain benchmarks with particular strengths in tool use and complex multi-step interactions. Achieves over 100 tokens per second on H800 GPUs.
Data as of 2026-08-11.
LongCat Flash Chat vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to LongCat Flash Chat
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ME
LongCat Flash Lite
Meituan
ME
LongCat Flash Thinking
Meituan
MI
MiniMax M1 80K
MiniMax
AC
Qwen3 Next 80B A3B
Alibaba Cloud / Qwen Team
MA
Kimi K2
Moonshot AI
CO
North Mini Code 1.0
Cohere
FAQ
Common questions about LongCat Flash Chat.
When was LongCat Flash Chat released?
LongCat Flash Chat's default version was released on Aug 29, 2025.
How much does LongCat Flash Chat cost?
No official standard PAYG price is currently available for LongCat Flash Chat.
Who created LongCat Flash Chat?
LongCat Flash Chat was created by Meituan.
What is the context window for LongCat Flash Chat?
The default version has a 128K token context window.
Is LongCat Flash Chat open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer LongCat Flash Chat?
No provider offering is currently linked to the default version.
What models should I compare LongCat Flash Chat with?
Nearby ranked alternatives include North Mini Code 1.0, Kimi K2, MiniMax M1 80K.