LFM2.5-8B-A1B: benchmark results
Provider: Liquid AI. Released 2026-05-28. Access: Open.
Aggregate Rating 1478 ± 36, rank #2692 of 10916 rated models, from 22 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA IFBench | 55.65 | Accuracy (%) | 66.9 |
| AA Humanity's Last Exam | 6.86 | Accuracy (%) | 39.7 |
| AA Terminal-Bench Hard | 4.55 | Accuracy (%) | 29.2 |
| AA GPQA Diamond | 51.31 | Accuracy (%) | 24.8 |
| AA CritPt | 0 | Accuracy (%) | 20.9 |
| AA Omniscience - Software Engineering (SWE) - Dart | 10 | Accuracy (%) | 18.4 |
| AA Omniscience - Software Engineering (SWE) - HTML | 18 | Accuracy (%) | 17.1 |
| AA Omniscience - Software Engineering (SWE) - Go | 6 | Accuracy (%) | 14 |
| AA Omniscience - Software Engineering (SWE) - R | 2 | Accuracy (%) | 14 |
| AA TAU-2 Bench | 16.08 | Accuracy (%) | 14 |
| AA Omniscience - Software Engineering (SWE) - Rust | 30 | Accuracy (%) | 13.3 |
| AA Omniscience - Software Engineering (SWE) - PHP | 8 | Accuracy (%) | 11.1 |
Interactive version: theaggregate.ai/model?slug=lfm2-5-8b-a1b · How It Works · Data refreshed daily, snapshot 2026-11-08.