Meituan · mit

LongCat-Flash-Chat

LongCat-Flash-Chat by Meituan appears in 2 sources with Reasoning at 23.41. Best read for Code quality, Coding, High intelligence.

CreatorMeituan

Release date2025-08-29

Knowledge cutoffNot published

Context128K tokens

Input price$0.3/M tokens

Output price$1.2/M tokens

Modalitytext

CountryCN

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank44ranking · source_rank

Reasoning23.41reasoning · index_reasoning

Math22.7math · index_math

Coding15.74coding · index_code

Writing17.64writing · index_communication

Tool calling14.04tool_calling · index_tool_calling

Finance34.68domain · index_finance

Legal34.7domain · index_legal

Healthcare34.23domain · index_healthcare

GPQA73.23 %reasoning · gpqa_score

AIME 202561.25 %math · aime_2025_score

SWE-bench Verified60.4 %coding · swe_bench_verified_score

Code Arena1,038.95 %coding · coding_arena_score

Terminal Bench39.51 %coding · terminal_bench_score

Context128,000 tokenscontext · context

Speed137.48 c/sperformance · throughput

Latency4,900.91 msperformance · latency

Input price0.3 $/Mpricing · input_price

Output price1.2 $/Mpricing · output_price

Parameters560,000,000,000 paramsmodel · params

Arena Rating1,421.93metric

Arena Rank64metric

Vote Count11,406metric

Evidence

Citations and source overlap

Arena AILM Arena text leaderboard (overall) mirrored in the public leaderboard dataset.Retrieved 2026-05-20 LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is LongCat-Flash-Chat verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.