Meituan model product
LongCat Flash Chat
LongCat Flash Chat is Meituan’s open-source 560B-parameter Mixture-of-Experts (MoE) model for conversational and agentic tasks.
Updated Sep 8, 2026. Default version: LongCat-Flash-Chat
LLMBoard Score35.9LongCat-Flash-Chat
Coverage60%16 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable
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.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkCMMLU | Score84.34% | Rank03 | Participants6 | Percentile60.00% | EvidenceC | Evaluated |
| BenchmarkZebraLogic | Score89.30% | Rank04 | Participants8 | Percentile57.14% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench | Score39.51% | Rank09 | Participants25 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score89.71% | Rank12 | Participants101 | Percentile89.00% | EvidenceC | Evaluated |
| BenchmarkMATH-500 | Score96.40% | Rank13 | Participants32 | Percentile61.29% | EvidenceC | Evaluated |
| BenchmarkTau2 Airline | Score58.00% | Rank13 | Participants24 | Percentile47.83% | EvidenceC | Evaluated |
| BenchmarkDROP | Score79.06% | Rank16 | Participants30 | Percentile48.28% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score88.41% | Rank19 | Participants66 | Percentile72.31% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score89.65% | Rank20 | Participants68 | Percentile71.64% | EvidenceC | Evaluated |
| BenchmarkTau2 Retail | Score71.27% | Rank20 | Participants27 | Percentile26.92% | EvidenceC | Evaluated |
| BenchmarkTau2 Telecom | Score73.68% | Rank24 | Participants36 | Percentile34.29% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score82.68% | Rank37 | Participants138 | Percentile73.72% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score48.02% | Rank50 | Participants75 | Percentile33.78% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,435.76 rating | Rank69 | Participants210 | Percentile67.46% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,426.03 rating | Rank71 | Participants210 | Percentile66.51% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,427.99 rating | Rank82 | Participants121 | Percentile32.50% | EvidenceA | Evaluated |
| BenchmarkSWE-Bench Verified | Score60.40% | Rank84 | Participants113 | Percentile25.89% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score61.25% | Rank101 | Participants119 | Percentile15.25% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score73.23% | Rank127 | Participants247 | Percentile48.78% | EvidenceC | Evaluated |
LongCat Flash Chat Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categoryindustry medicine and healthcare | Rank36 | Rating / score1,459.93 | Votes666 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank39 | Rating / score1,473.04 | Votes7,755 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank39 | Rating / score1,501.81 | Votes6,683 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank42 | Rating / score1,459.86 | Votes8,709 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank43 | Rating / score1,502.69 | Votes7,755 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank44 | Rating / score1,465.74 | Votes10,911 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank44 | Rating / score1,445.19 | Votes401 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank46 | Rating / score1,451.28 | Votes13,159 | ObservationsN/A | Result date |
| Arenatext factuality | Categorychinese | Rank46 | Rating / score1,480.57 | Votes1,381 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank47 | Rating / score1,458.33 | Votes182 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank49 | Rating / score1,477.69 | Votes7,661 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank50 | Rating / score1,488.59 | Votes10,911 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank53 | Rating / score1,440.81 | Votes686 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexpert | Rank53 | Rating / score1,465.52 | Votes1,978 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank53 | Rating / score1,435.48 | Votes1,219 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank53 | Rating / score1,481.30 | Votes10,236 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank54 | Rating / score1,451.78 | Votes2,605 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank55 | Rating / score1,443.20 | Votes542 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank55 | Rating / score1,482.79 | Votes1,719 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank55 | Rating / score1,458.76 | Votes13,159 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank55 | Rating / score1,475.53 | Votes8,709 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank57 | Rating / score1,427.87 | Votes1,391 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank58 | Rating / score1,452.90 | Votes13,063 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank59 | Rating / score1,428.25 | Votes2,149 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank62 | Rating / score1,384.62 | Votes470 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts | Rank63 | Rating / score1,460.10 | Votes17,806 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank63 | Rating / score1,388.15 | Votes252 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank64 | Rating / score1,466.11 | Votes1,719 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank66 | Rating / score1,439.25 | Votes17,806 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank66 | Rating / score1,465.17 | Votes2,605 | ObservationsN/A | Result date |
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 Runtime Performance
Provider-specific output speed and catalog latency for LongCat-Flash-Chat. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
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
- Yes
- License
- MIT
LongCat Flash Chat Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionLongCat-Flash-Chat | Released | LLMBoard35.85 | Parameters560B | Context128K | Max output128K | Open weightsYes | LicenseMIT |
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
MA
Kimi K2
Moonshot AI
XA
Grok Code Fast 1
xAI
OP
o1
OpenAI
What is LongCat Flash Chat?
Key information about LongCat Flash Chat and its available data.
3B parameters based on contextual demands. It supports a 128K context and is optimized for reasoning, coding, instruction following, tool use, and complex multi-step interactions.
Data as of 2026-09-08.
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?
Yes. The default version is marked as open weight under MIT.
How many API providers offer LongCat Flash Chat?
No provider offering is currently linked to the default version.