LFM2 24B A2B — benchmark results

Provider: Liquid AI. Released 2025-05-29. Access: Open.

Unified ELO 1388 ± 35, rank #1274 of 1776 rated models, from 42 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
UGI - Willingness (W/10)6W/10 Score53.7
AA IFBench45.85Accuracy (%)53.5
AI Chess Leaderboard (Continuation)483Elo33.7
CritPt0Accuracy (self-reported)30.3
UGI - Writing27.56Writing Score29.4
AI Chess Leaderboard (Reasoning)568Elo28.6
UGI Leaderboard28.98UGI Score28.6
AA CritPt0Accuracy (%)27.1
SpeechMap Compliance46.4% Requests Completed25.8
AA GPQA Diamond47.37Accuracy (%)24.3
AA Omniscience-59.07Score21.7
AA Humanity's Last Exam4.45Accuracy (%)21.4

Interactive version: theaggregate.ai/model?slug=lfm2-24b-a2b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.