Benchmark Almanac

LongCat-Flash-Chat

LongCat-Flash-Chat places in the top three on Arena-Hard v2.0.

Meituan Released 29 Aug 2025 Family LongCat-Flash The lab's model card
31
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Meituan Aug 2025

LongCat-Flash-Chat

Open weights Flagship

No Epoch Capabilities Index score yet
  • VITA-Bench 22.8% #9 /18
  • AMO-Bench 14.6% #15 /21
  • VitaBench 2.0 29.8% #15 /20

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
Arena-Hard v2.0 86.5% #2 of 24 Model card
MMLU 89.7% #17 of 127 Model card
IFEval 89.7% #29 of 126 Model card
MMLU-Pro 82.7% #51 of 151 Model card
LMArena (Elo) 1,401 #129 of 333 Official leaderboard
C-Eval 90.4% #16 of 38 Model card
Meeseeks 43% #1 of 2 Model card
CMMLU 84.3% #10 of 17 Model card
DROP 79.1% #26 of 40 Model card
COLLIE 57.1% #9 of 12 Model card
Longform Creative Writing (EQ-Bench) 35.1 #106 of 119 Official leaderboard
GraphWalks 51% #20 of 21 Model card

Math and science

BenchmarkScoreRankSource
ZebraLogic 89.3% #7 of 23 Model card
MATH-500 96.4% #29 of 67 Model card
GPQA Diamond 73.2% #149 of 284 Model card
AIME 2024 70.4% #62 of 87 Model card
AMO-Bench 14.6% #15 of 21 Official leaderboard
AIME 2025 61.3% #126 of 143 Model card
Beyond AIME 43% #14 of 14 Model card

Coding

BenchmarkScoreRankSource
MBPP+ 79.6% #6 of 15 Model card
HumanEval+ 88.4% #11 of 27 Model card
LiveCodeBench 48% #46 of 73 Model card
SWE-bench Verified 60.4% #109 of 150 Model card
LiveCodeBench v6 48% #71 of 76 Model card

Agents and tools

BenchmarkScoreRankSource
VITA-Bench 22.8% #9 of 18 Official leaderboard
Terminal-Bench 39.5% #12 of 22 Model card
SnakeBench 20 #128 of 183 Official leaderboard
VitaBench 2.0 29.8% #15 of 20 Official leaderboard
tau2-bench 67.7% #56 of 69 Model card
AceBench 76.1% #3 of 3 Model card

Safety and security

BenchmarkScoreRankSource
LongCat safety evaluation (Meituan) 87.7% #2 of 2 Model card

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

LongCat-Flash-Chat model card (Hugging Face) 29 Aug 2025

Its system card

Every result in the longer documents the lab published with it. 1 of them isn't in the launch post.