Meituan · mit

LongCat-Flash-Thinking

LongCat-Flash-Thinking by Meituan appears in 1 source with Reasoning at 35.89. Best read for Code quality, Math, Open weights.

CreatorMeituan

Release date2025-09-22

Knowledge cutoffNot published

ContextUnknown

Input priceUnknown

Output priceUnknown

Modalitytext

CountryCN

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank66ranking · source_rank

Reasoning35.89reasoning · index_reasoning

Math34.04math · index_math

Coding18.89coding · index_code

Writing23.71writing · index_communication

Vision16.07multimodal · index_vision

Tool calling21.18tool_calling · index_tool_calling

Finance36.28domain · index_finance

Legal32.15domain · index_legal

Healthcare31.9domain · index_healthcare

GPQA81.5 %reasoning · gpqa_score

AIME 202590.6 %math · aime_2025_score

SWE-bench Verified59.4 %coding · swe_bench_verified_score

Code Arena790.67 %coding · coding_arena_score

Parameters560,000,000,000 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-Thinking 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.