LFM2.5-2.6B: benchmark results
Provider: Liquid AI. Released 2026-07-28. Access: Open.
Unified ELO 1494 ± 1, rank #718 of 1392 rated models, from 41 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (Multi-IF) | 80.07 | Score (%) | 95.5 |
| AA Omniscience | -10.95 | Score | 71 |
| MERA v2 - IFHardBench | 24.7 | Score (%) | 50 |
| LLM Stats (Claw-Eval) | 62.85 | Score (%) | 46.2 |
| LLM Stats Score | 19.17 | LLM Stats Score (conservative rating) | 44.4 |
| AA Humanity's Last Exam | 6.21 | Accuracy (%) | 40.3 |
| MERA v2 - Agentic | 7 | Score (%) | 40.3 |
| Artificial Analysis Intelligence Index | 5.31 | Intelligence Index | 35.4 |
| AA GPQA Diamond | 55.76 | Accuracy (%) | 29.8 |
| AA CritPt | 0 | Accuracy (%) | 24.4 |
| MERA v2 | 0.12 | Total score | 22.2 |
| MERA v2 - Characters | 33 | Score (%) | 22.2 |
Interactive version: theaggregate.ai/model?slug=lfm2-5-2-6b · How It Works · Data refreshed daily, snapshot 2026-09-05.