Skip to content

LongCat-Flash-Lite-Sparse

MeituanOpen weightsReasoningReleased Jul 31, 2026
Overall score
—
Not enough evidence to rank yet
Context window
1M
1,000,000 tokens
Price per 1M tokens
— in · — out
No price listed
Blended price
—
3:1 input:output tokens
Output speed
—
Not measured yet

Benchmark results (15)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Agentic & tool use

BrowseComp48.6#47 of 50
MCP Atlas45.6#39 of 42
Terminal-Bench 2.033.7#39 of 39
VITA-Bench21.7#8 of 11

Knowledge

MMLU-Pro79.2#37 of 67
MMLU85.3#13 of 28
C-Eval85.8#9 of 10
CMMLU84.3#1 of 1

Math

AIME2665.7#27 of 29
HMMT Feb 202640.5#23 of 24
MATH-50095.8#10 of 20
IMOAnswerBench49.4#9 of 9

Coding

SWE-bench Verified68.2#67 of 98
SWE-bench Pro40.6#65 of 69

Multilingual

SWE Multilingual59.3#40 of 46

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
List price———

Meituan publishes LongCat-Flash-Lite-Sparse under MIT for self-hosting and does not publish a first-party hosted token rate for this exact checkpoint. We represent the open-weight row as self-host/free-per-token before infrastructure costs.

Speed

Measured by us through OpenRouter (median of trials).

Not available on OpenRouter, so we cannot measure it yet.

Related models

Same family