LFM2.5-1.2B-Base: benchmark results
Provider: Liquid AI. Released 2026-01-05. Access: Open.
Aggregate Rating 1225 ± 31, rank #9450 of 10916 rated models, from 240 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Catalan NLU - ScaLA CA | 0.47 | Matthews correlation coefficient (%) | 37.4 |
| EuroEval Portuguese NLU - SST-2 PT | 68.6 | Matthews correlation coefficient (%) | 34.5 |
| EuroEval Norwegian Knowledge - Idioms NO | 0.7 | MCC (x100) | 32.9 |
| EuroEval English Knowledge | 50.05 | Knowledge Average Score (%) | 31.3 |
| EuroEval Latvian NLU - ScaLA LV | 1.71 | Matthews correlation coefficient (%) | 30.6 |
| EuroEval Italian NLU - MultiNERD IT | 47.85 | Micro F1 excluding MISC (%) | 29.5 |
| EuroEval Spanish NLU - Sentiment Headlines ES | 28.36 | Matthews correlation coefficient (%) | 28.9 |
| EuroEval Portuguese NLU - HAREM | 34.05 | Micro F1 excluding MISC (%) | 28.6 |
| EuroEval Estonian NLU - Grammar ET | 1.02 | Matthews correlation coefficient (%) | 26.5 |
| EuroEval Polish NLU - Polemo2 | 71.68 | Matthews correlation coefficient (%) | 26.2 |
| EuroEval French NLU - Allocine | 78.99 | Matthews correlation coefficient (%) | 25.8 |
| EuroEval Spanish Knowledge | 16.85 | Knowledge Average Score (%) | 25.7 |
Interactive version: theaggregate.ai/model?slug=lfm2-5-1-2b-base · How It Works · Data refreshed daily, snapshot 2026-11-08.