LFM2 2.6B: benchmark results
Provider: Liquid AI. Released 2025-11-28. Access: Open.
Unified ELO 1386 ± 1, rank #1185 of 1392 rated models, from 333 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Spanish NLU - Sentiment Headlines ES | 46.63 | Sentiment classification Score (%) | 75.7 |
| MERA - LCS | 16.2 | Accuracy (%) | 66 |
| MERA Code - CodeCorrectness | 75.39 | Accuracy (%) | 63.1 |
| MERA Code - stRuCom | 25.91 | chrF (%) | 63.1 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 70.53 | Reading comprehension Score (%) | 60.6 |
| EuroEval Spanish | 44.67 | Average Score (%) | 59 |
| EuroEval Portuguese Knowledge | 45.69 | Knowledge Average Score (%) | 56.6 |
| EuroEval Spanish Common Sense Reasoning | 46.43 | Common Sense Reasoning Average Score (%) | 56.5 |
| EuroEval Spanish NLU | 44.13 | NLU Average Score (%) | 56.1 |
| EuroEval Italian Common Sense Reasoning | 42.83 | Common Sense Reasoning Average Score (%) | 55.7 |
| EuroEval Portuguese | 47.02 | Average Score (%) | 55.3 |
| EuroEval Italian NLU - Sentipolc16 | 51.5 | Sentiment classification Score (%) | 55.2 |
Interactive version: theaggregate.ai/model?slug=lfm2-2-6b · How It Works · Data refreshed daily, snapshot 2026-09-05.