AA-Omniscience accuracy (public) leaderboard
As of November 14, 2026, among the results listed here, LiquidAI LFM2.5-2.6B has the highest reported AA-Omniscience accuracy (public) score, 8.8, published by Liquid, ahead of LiquidAI LFM3-1.7B at 7.1. 2 models have a AA-Omniscience accuracy (public) result in our records.
Scores as the model makers published them, not re-run by us; each row links to its announcement.
2 models ranked · 1 maker
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | LFM2.5-2.6BRetired | 8.8 | Not published | Liquid | November 6, 2026 (model release) |
| 2 | LFM3-1.7B | 7.1 | Not published | Liquid | November 6, 2026 (model release) |
How much to trust these numbers
- Source
- Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
- Settings
- All ranked results use the same reported setting.
- Spread
- 8.8 to 7.1 across 2 models.
- Freshness
- Published November 6, 2026.
What AA-Omniscience accuracy (public) measures
AA-Omniscience accuracy (public) appears in the release announcements of Liquid. We have not found a public write-up of the benchmark itself yet.