LongCat-Flash-Chat — benchmark results

Meituan LongCat Flash Chat model row. Provider: Meituan. Released 2025-09-01. Access: API.

Unified ELO 1592 ± 15, rank #497 of 1776 rated models, from 25 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Chatbot Arena (Text)1401Elo66.4
OpenCompass Research - IFEval90.2Score (%)66
BenchTable56.3Total Score (%)64.5
LiveSecBench57.1Overall Score (%)61.9
ZeroEval MATH-50096.4MATH-500 Score61.3
LLM Stats (CMMLU)84.34Score (%)60
AI Chess Leaderboard (Reasoning)701Elo57.2
LLM Stats (ZebraLogic)89.3Score (%)57.1
VitaBench22.8Cross-Scenario Avg@4 (%)55
LLM Stats (DROP)79.06Score (%)50
ZeroEval GPQA Diamond73.23GPQA Diamond Score50
SpeechMap Compliance60.4% Requests Completed45.5

Interactive version: theaggregate.ai/model?slug=longcat-flash-chat · How the rankings work · Data refreshed daily, snapshot 2026-07-22.