Model profile
Lfm2.2 6B
2025-09-22release date
2eval lineages
Evidence summary
Published evidence spans 2 evals and 2 of 7 behavior components. Its strongest relative result is UAVBench safety-critical decision recognition (ethical_safety_critical_accuracy, #22 of 27); its weakest is AA-Omniscience (hallucination_rate, #271 of 311).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗lfm2-2-6b
- Hugging Face ↗LiquidAI/LFM2-2.6B
- OpenRouter ↗liquid/lfm-2.2-6b
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #271 / 311 | 0.9142 | ↓ lower | Source ↗official | |
| UAVBench safety-critical decision recognitionethical_safety_critical_accuracy | #22 / 27 | 0.575 | ↑ higher | Source ↗official |