Liquid LFM2.5-2.6B Card - AA-Omniscience-Public Index: leaderboard
Artificial Analysis' Omniscience knowledge-reliability evaluation on its public question set, run by Liquid AI with vLLM for the LFM2.5-2.6B model card. The index rewards correct answers and penalizes incorrect ones, so it ranges from -100 to 100; higher is better. Thinking modes of the Gemma and Qwen models are not stated.
Metric: Omniscience Index (-100 to 100). Source: huggingface.co. Saturation forecast: Around September 2028. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | LFM2.5-2.6B | -29.5 | #836 |
| 2 | gemma-4-E4B-it | -49.03 | #577 |
| 3 | Qwen 3.5 9B | -50.43 | #391 |
| 4 | Qwen 3.5 4B | -54.3 | #514 |
| 5 | Gemma 4 E2B (IT) | -74.47 | #779 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=liquid-lfm2-5-2-6b-card-aa-omniscience-public-index · How It Works · Data refreshed daily, snapshot 2026-11-05.