LFM2.5-VL-1.6B — benchmark results
Provider: Liquid AI. Released 2025-06-17. Access: Open.
Unified ELO 1321 ± 40, rank #1490 of 1776 rated models, from 42 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AI for Education Visual Reasoning - match (process) | 30.6 | Accuracy (%) | 36.3 |
| AA Humanity's Last Exam | 5.14 | Accuracy (%) | 35.7 |
| CritPt | 0 | Accuracy (self-reported) | 30.3 |
| AI for Education Visual Reasoning - pattern completion (2d) | 31.5 | Accuracy (%) | 27.4 |
| AA CritPt | 0 | Accuracy (%) | 27.1 |
| AA IFBench | 33.13 | Accuracy (%) | 21.8 |
| AA Omniscience - Software Engineering (SWE) - R | 2 | Accuracy (%) | 11.9 |
| AI for Education Visual Reasoning - reasoning by analogy | 26 | Accuracy (%) | 11.3 |
| HarmVideoBench | 66.8 | Macro Avg. (self-reported) | 10 |
| AA-LCR | 0 | Score (self-reported) | 8.9 |
| AA Omniscience - Software Engineering (SWE) - Julia | 0 | Accuracy (%) | 7.9 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 5.56 | Accuracy (%) | 7.5 |
Interactive version: theaggregate.ai/model?slug=lfm2-5-vl-1-6b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.