---
last_updated: 2026-11-22
source_url: https://opper.ai/liquid-ai/lfm2-5-2-6b
title: "LFM2.5-2.6B by Liquid AI"
description: "Liquid AI released LFM2.5-2.6B on 4 Aug 2026."
---

# LFM2.5-2.6B

By [Liquid AI](https://opper.ai/liquid-ai).

Released 4 Aug 2026 · 68 days after [LFM2.5-8B-A1B](https://opper.ai/liquid-ai/lfm2-5-8b-a1b).

## Benchmarks

Independent benchmark scores via [Artificial Analysis](https://artificialanalysis.ai) ([view on AA](https://artificialanalysis.ai/models/lfm2-5-2-6b)). Indices and domain scores are out of 100, Omniscience runs from −100 to 100, Briefcase is an Elo rating, and the other evaluation scores are the share of tasks solved.

- Global rank: #326 of 520 LLMs on the [LLM leaderboard](https://opper.ai/llm-leaderboard)
- Tier: Efficient
- Intelligence Index (previous version): 8.4

### Coding

- SciCode: 14%

### Agentic & knowledge work

- GDPval: 0%

### Science & reasoning

- Humanity's Last Exam: 6%
- GPQA Diamond: 56%
- Long-context reasoning: 6%

## Available routes

No routes currently available — LFM2.5-2.6B isn't routed through the Opper gateway right now. It's tracked here for its release history. Contact [hello@opper.ai](mailto:hello@opper.ai) about this model.
