LFM2.5-8B-A1B — benchmark results
Provider: Liquid AI. Access: Open.
Unified ELO 1445 ± 45, rank #1022 of 1776 rated models, from 34 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA IFBench | 53.47 | Accuracy (%) | 63.7 |
| AA Omniscience | -33.27 | Score | 60.7 |
| AA MATH-500 | 84.44 | Accuracy (%) | 52.5 |
| AA Humanity's Last Exam | 6.9 | Accuracy (%) | 50.1 |
| CritPt | 0 | Accuracy (self-reported) | 30.3 |
| AA Terminal-Bench Hard | 4.55 | Accuracy (%) | 29.2 |
| AA CritPt | 0 | Accuracy (%) | 27.1 |
| Artificial Analysis Intelligence Index | 8.32 | Intelligence Index | 26.8 |
| BenchLM | 41.4 | Overall Score | 17.3 |
| AA Omniscience - Science, Engineering & Mathematics | 15.8 | Accuracy (%) | 16.6 |
| AA TAU-2 Bench | 16.08 | Accuracy (%) | 14 |
| AA Omniscience - Software Engineering (SWE) - Rust | 32 | Accuracy (%) | 13.1 |
Interactive version: theaggregate.ai/model?slug=lfm2-5-8b-a1b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.