LFM2 8B A1B — benchmark results

Provider: Liquid AI. Released 2025-11-28. Access: Open.

Unified ELO 1352 ± 29, rank #1403 of 1776 rated models, from 52 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
UGI - Willingness (W/10)5.8W/10 Score49.3
CritPt0Accuracy (self-reported)30.3
AA Humanity's Last Exam4.87Accuracy (%)30.1
AI Chess Leaderboard (Reasoning)571Elo29.8
AA CritPt0Accuracy (%)27.1
AA AIME 202525.33Accuracy (%)26.7
AI Chess Leaderboard (Continuation)443Elo25.1
UGI Leaderboard26.81UGI Score22.9
SnakeBench15.1TrueSkill Rating18.9
AA LiveCodeBench15.13Pass@1 (%)15.5
AA MMLU-Pro50.54Accuracy (%)15.1
AA GPQA Diamond34.44Accuracy (%)12.8

Interactive version: theaggregate.ai/model?slug=lfm2-8b-a1b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.