LFM2 24B A2B: benchmark results
Provider: Liquid AI. Released 2025-05-29. Access: Open.
Unified ELO 1438 ± 1, rank #998 of 1392 rated models, from 75 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MERA Code - CodeCorrectness | 81.26 | Accuracy (%) | 78.5 |
| MERA - BPS | 97 | Accuracy (%) | 65.4 |
| UGI - Willingness (W/10) | 6 | W/10 Score | 54.2 |
| AA IFBench | 45.85 | Accuracy (%) | 53.6 |
| MERA - SimpleAr | 97.9 | EM (%) | 50.2 |
| MERA - ruMultiAr | 30.66 | EM (%) | 48.1 |
| MERA - MathLogicQA | 42.43 | Accuracy (%) | 40.2 |
| MERA Code - UnitTests | 16.99 | CodeBLEU (%) | 40 |
| MERA - ruWorldTree | 83.05 | Accuracy (%) | 37.8 |
| MERA - ruHateSpeech | 64.53 | Accuracy (%) | 36.5 |
| MERA - MaMuRAMu | 57.16 | Accuracy (%) | 34 |
| MERA - ruMMLU | 48.42 | Accuracy (%) | 33.5 |
Interactive version: theaggregate.ai/model?slug=lfm2-24b-a2b · How It Works · Data refreshed daily, snapshot 2026-09-05.