Model creator
Liquid AI
Every Liquid AI model in the BenchSift catalogue, with its scores, ranks, prices and capabilities as the sources publish them.
- Models
- 10
- Open weights
- 9
- 9 of 10 models
- Latest release
- Aug 4, 2026
- LFM2.5-2.6B · First dated model: Sep 30, 2024
- Median price
- Not published
Models
10Reasoning levels are folded into one entry. The rank is the whole catalogue's: sorting does not change it.
- LFM2.5-2.6B8.4#511 of 782——
Text · Reasoning · Open weights · Aug 4, 2026
- LFM2.5-8B-A1B7.2#584 of 782——
Text · Reasoning · Open weights · May 28, 2026
- LFM2 24B A2B5.9#670 of 782——
Text · Open weights · Feb 25, 2026
- LFM 40B5.4#712 of 782——
Text · Sep 30, 2024
- LFM2.5-1.2B-Thinking5.2#728 of 782——
Text · Reasoning · Open weights · Jan 20, 2026
- LFM2.5-1.2B-Instruct5.2#728 of 782——
Text · Open weights · Jan 5, 2026
- LFM2 2.6B5.2#728 of 782——
Text · Open weights · Sep 23, 2025
- LFM2 8B A1B4.9#753 of 782——
Text · Open weights · Oct 7, 2025
- LFM2.5-VL-1.6B4.8#757 of 782——
Text · Open weights · Jan 5, 2026
- LFM2 1.2B4.8#757 of 782——
Text · Open weights · Jul 10, 2025
Where these figures come from
Each catalogue model is tied to its creator by the identity Artificial Analysis publishes, or OpenRouter's and Models.dev's for models it does not track. Counts fold the reasoning levels of one model together. Ranks compare each measure with every measured model in the catalogue, configurations included, as model pages do. The price is the published blended price (3 input tokens to 1 output token).
Figures computed by BenchSift from the catalogue: Artificial Analysis, OpenRouter, Models.dev and Hugging Face. A value no model carries is not shown.
Data retrieved on Nov 12, 2026.