Inference
EN
Meituan

LongCat-2.5

LongCat-2.5 is a reasoning model from Meituan. It has 12 scored results in 3 categories. It has no index.

  • New
  • Open weights
  • Reasoning
  • Input: text
  • Released 2026-11
UnrankedEnough results for an index.
IndexAll categories, out of 100.UnrankedMedian 51.0
CoverageIndex weight that has results.50%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.30Median $0.60
Output / 1MUS dollars per 1M output tokens.$1.20Median $2.55
ContextMaximum tokens in one request.1MMedian 262K
EloLMArena rating and rank.—Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.9 counted72.9—
CodingCode writing and repair.2 counted62.7—
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.1 counted66.9—
KnowledgeFacts and expert knowledge.None counted——
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.None counted——

Results

12 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Claw-EvalAgentic78.3%2 / 42
BrowseCompAgentic91.9%4 / 63
Terminal-Bench 2.1 · BenchLMAgentic88.4%8 / 86
JobBenchAgentic65.4%4 / 36
NL2RepoCoding60.5%5 / 36
CharXiv ReasoningMultimodal90.2%8 / 49
Humanity's Last Exam with toolsAgentic63.1%6 / 36
MCP AtlasAgentic83.1%10 / 52
AutomationBenchAgentic51.8%10 / 32
Agents' Last ExamAgentic38.5%10 / 21
DeepSWEAgentic64.6%35 / 59
ProgramBench: Can Language Models Rebuild Programs From Scratch?Coding25.5%17 / 19
MathVision with PythonMultimodal96.5%—
Video-MMEMultimodal85.2%—
GDPval rubricsAgentic84.8%—
PaperBenchCoding82.1%—
Vision2WebMultimodal78.6%—
FrontierScienceKnowledge77.0%—
SWE-Atlas Codebase QnACoding58.3%—
SpreadsheetBench 2Agentic34.9%—

Sources

BenchLMCC BY-NC 4.0

History

5 releases
Output / 1M$1.20 → $1.20
11 Nov 202612 Nov 2026

Questions

How much does LongCat-2.5 cost?
$0.30 per 1M input tokens, $1.20 per 1M output tokens.
What is the context window of LongCat-2.5?
1M tokens.
Is LongCat-2.5 open source?
Yes. Its weights are published.
When was LongCat-2.5 released?
November 2026.

More from Meituan

All models
LongCat-Flash-Lite-Sparse39.3LongCat-2.0Unranked