ModelsCompareBest forBenchmarksStatusPricingAPI

LongCat Flash Chat

Meituan LongCat·Pending·Released 2025-09-01text
Context128k
Max output-
Input / 1M-
Output / 1M-
Cached in-
Benchmarks31

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

LMArena Elo#35/621422.9 ↗
AceBench76.1% ↗
AIME 2024#1/770.42% ↗
AIME 2025#14/1561.25% ↗
ArenaHard-V286.5% ↗
BeyondAIME#3/343% ↗
C-Eval90.44% ↗
CMMLU84.34% ↗
COLLIE57.1% ↗
DROP#3/379.06% ↗
GPQA Diamond#49/7073.23% ↗
GraphWalks-128k51.05% ↗
HumanEval+#3/488.41% ↗
IFEval#6/889.65% ↗
LiveCodeBench#9/948.02% ↗
MATH50096.4% ↗
MBPP+#3/479.63% ↗
Meeseeks-zh43.03% ↗
MMLU#3/1489.71% ↗
MMLU-Pro#13/2982.68% ↗
Safety: Criminal91.24% ↗
Safety: Harmful83.98% ↗
Safety: Misinformation81.72% ↗
Safety: Privacy93.98% ↗
SWE-bench Verified#38/4560.4% ↗
Tau2-Bench (airline)58% ↗
Tau2-Bench (retail)71.27% ↗
Tau2-Bench (telecom)73.68% ↗
TerminalBench39.51% ↗
VitaBench24.3% ↗
ZebraLogic#2/289.3% ↗

Compare

vs GPT-6 Astravs GPT-5.6 Solvs GPT-5.6 Terravs GPT-5.6 Lunavs Claude Fable 5.1vs Claude Opus 5vs Claude Sonnet 5vs Claude Haiku 4.5

More from Meituan LongCat

LongCat 2.0

Access LongCat Flash Chat and every other model through one endpoint with automatic failover: Respan gateway.