OmniScience Accuracy
OmniScience Accuracy - scientific knowledge accuracy benchmark.
Category
Knowledge
Score type
percent
Scale
100%
higher is better
Models tested
7
What is OmniScience Accuracy?
OmniScience Accuracy is a benchmark for broad factual and academic knowledge. The official description says: "OmniScience Accuracy - scientific knowledge accuracy benchmark". Below we describe in simple words what benchmarks of this type generally examine.
What does it test?
OmniScience Accuracy 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 accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.
Official methodology note: OmniScience Accuracy - scientific knowledge accuracy benchmark.
Frequently asked questions
What is the OmniScience Accuracy benchmark?
OmniScience Accuracy is a benchmark for broad factual and academic knowledge. The official description says: 'OmniScience Accuracy - scientific knowledge accuracy benchmark'. Below we describe in simple words what benchmarks of this type generally examine.
What does OmniScience Accuracy test?
OmniScience Accuracy 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 OmniScience Accuracy score calculated?
The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.
Where do I get OmniScience Accuracy 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/omniscience-accuracy/scores) or pull it directly from the Open LLM Radar API with any HTTP client.
Benchmark data & downloads
Where to get, inspect and reuse the data behind this benchmark.
Benchmark dataset
The question/task data itself — download and evaluate locally
Benchmark metadata (JSON)
This page's benchmark record from the Open LLM Radar API
All model scores (JSON download)
Full score table as JSON; paginate with limit/offset params
Open LLM Radar API docs
Swagger UI to explore and reuse all radar API endpoints
Model scores 7 models tested
| # | Model | Score | Date | Source | Verified |
|---|---|---|---|---|---|
| 1 |
DeepSeek-V4-Pro
DeepSeek
|
46.8%
|
04.06.2026 | Report | Unverified |
| 2 |
DeepSeek-V4-Flash
DeepSeek
|
39.9%
|
04.06.2026 | Report | Unverified |
| 3 |
Kimi K2.6
Moonshot AI
|
35.5%
|
04.06.2026 | Report | Unverified |
| 4 |
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
NVIDIA
|
24.1%
|
04.06.2026 | Report | Verified |
| 5 |
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB
NVIDIA
|
16.9%
|
15.10.2026 | Report | Verified |
| 6 |
Kolibri-1
Aleph Alpha
|
14.8%
|
03.10.2026 | Report | Verified |
| 7 |
LFM3-1.7B
LiquidAI
|
7.07%
|
— | Report | Verified |