Meituan · mit

LongCat-Flash-Lite

LongCat-Flash-Lite by Meituan appears in 1 source with Reasoning at 23. Best read for Code quality, Low cost, Open weights.

CreatorMeituan

Release date2026-02-05

Knowledge cutoffNot published

Context256K tokens

Input price$0.1/M tokens

Output price$0.4/M tokens

Modalitytext

CountryCN

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank71ranking · source_rank

Reasoning23reasoning · index_reasoning

Math19.87math · index_math

Coding11.72coding · index_code

Writing18.58writing · index_communication

Tool calling14.91tool_calling · index_tool_calling

Finance22.03domain · index_finance

Legal22.07domain · index_legal

Healthcare21.66domain · index_healthcare

GPQA66.78 %reasoning · gpqa_score

AIME 202563.23 %math · aime_2025_score

SWE-bench Verified54.4 %coding · swe_bench_verified_score

Code Arena755.57 %coding · coding_arena_score

Terminal Bench33.75 %coding · terminal_bench_score

Context256,000 tokenscontext · context

Speed215.82 c/sperformance · throughput

Latency6,466 msperformance · latency

Input price0.1 $/Mpricing · input_price

Output price0.4 $/Mpricing · output_price

Parameters68,500,000,000 paramsmodel · params

Evidence

Citations and source overlap

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-Lite 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.