Knowledge Benchmark

AA-Omniscience Index (public set)

AA-Omniscience Index (public set) - calibrated knowledge index from Aleph Alpha's Omniscience suite, centered at 0 and comparable across models; can be negative. Raw index value as printed on the Kolibri card.

Category

Knowledge

Score type

index

Scale

100.0

higher is better

Models tested

9

What is AA-Omniscience Index (public set)?

AA-Omniscience Index (public set) is a benchmark for broad factual and academic knowledge. The official description says: "AA-Omniscience Index (public set) - calibrated knowledge index from Aleph Alpha's Omniscience suite, centered at 0 and comparable across models; can be negative". Below we describe in simple words what benchmarks of this type generally examine.

What does it test?

AA-Omniscience Index (public set) measures broad factual and academic knowledge. In detail, it checks:

  • facts and concepts from many academic fields at once
  • harder variants with several plausible answer options
  • knowledge that goes beyond the model's training-set surface forms
  • resisting the plausible-but-wrong answers deliberately included

How to read the score

The score is a composite index published by the benchmark organiser rather than a plain percentage. Interpret it only against the other models in the table — higher is better.

Official methodology note: AA-Omniscience Index (public set) - calibrated knowledge index from Aleph Alpha's Omniscience suite, centered at 0 and comparable across models; can be negative. Raw index value as printed on the Kolibri card.

Frequently asked questions

What is the AA-Omniscience Index (public set) benchmark?

AA-Omniscience Index (public set) is a benchmark for broad factual and academic knowledge. The official description says: 'AA-Omniscience Index (public set) - calibrated knowledge index from Aleph Alpha's Omniscience suite, centered at 0 and comparable across models; can be negative'. Below we describe in simple words what benchmarks of this type generally examine.

What does AA-Omniscience Index (public set) test?

AA-Omniscience Index (public set) mainly measures broad factual and academic knowledge. Concretely, it checks: facts and concepts from many academic fields at once; harder variants with several plausible answer options; knowledge that goes beyond the model's training-set surface forms.

How is the AA-Omniscience Index (public set) score calculated?

The score is a composite index published by the benchmark organiser rather than a plain percentage. Interpret it only against the other models in the table — higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get AA-Omniscience Index (public set) data and scores?

The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/aa-omniscience-index/scores) or pull it directly from the Open LLM Radar API with any HTTP client.

Model scores 9 models tested

Reset
# Model Score Date Source Verified
1 Muse-Spark-Open-816B-A42B
Meta Superintelligence Lab
25 idx
15.10.2026 Report Verified
2 Raon-1 mini
KRAFTON AI
3.5 idx
21.10.2026 Report Verified
3 LFM3-1.7B
LiquidAI
0.5 idx
— Report Verified
4 Qwen3.8-27B
Qwen Team (Alibaba Cloud)
-0.5 idx
21.10.2026 Report Unverified
5 Qwen3.6-35B-A3B
Qwen Team (Alibaba Cloud)
-7.2 idx
21.10.2026 Report Unverified
6 LFM2.5-24B-A2B
LiquidAI
-24.9 idx
13.10.2026 Report Verified
7 Kolibri-1
Aleph Alpha
-32.8 idx
03.10.2026 Report Verified
8 Muse-Glimmer-30B
Meta Superintelligence Lab
-34.7 idx
21.10.2026 Report Unverified
9 Gemma4-26B-A4B
Google
-46.6 idx
21.10.2026 Report Unverified

What now?

You've seen how models score on AA-Omniscience Index (public set) — here's what to do next.