STEM & Reasoning Benchmark

Overall (DE)

Kolibri card composite 'Overall (DE)': unweighted mean of the German category averages (Knowledge, Math, Agentic Retrieval, Industry RAG). Evaluation via Aleph Alpha eval-framework; Kolibri at reasoning effort high.

Category

STEM & Reasoning

Score type

percent

Scale

100%

higher is better

Models tested

1

What is Overall (DE)?

Overall (DE) is a benchmark for hard reasoning in science, technology, engineering and math. The official description says: "Kolibri card composite 'Overall (DE)': unweighted mean of the German category averages (Knowledge, Math, Agentic Retrieval, Industry RAG)". Below we describe in simple words what benchmarks of this type generally examine.

What does it test?

Overall (DE) measures hard reasoning in science, technology, engineering and math. In detail, it checks:

  • graduate- and expert-level questions in science and math
  • multi-step derivations where each step must be correct
  • problems written to defeat memorisation (novel or recent exam problems)
  • correct use of formulas, units and logical inference

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: Kolibri card composite 'Overall (DE)': unweighted mean of the German category averages (Knowledge, Math, Agentic Retrieval, Industry RAG). Evaluation via Aleph Alpha eval-framework; Kolibri at reasoning effort high.

Frequently asked questions

What is the Overall (DE) benchmark?

Overall (DE) is a benchmark for hard reasoning in science, technology, engineering and math. The official description says: 'Kolibri card composite 'Overall (DE)': unweighted mean of the German category averages (Knowledge, Math, Agentic Retrieval, Industry RAG)'. Below we describe in simple words what benchmarks of this type generally examine.

What does Overall (DE) test?

Overall (DE) mainly measures hard reasoning in science, technology, engineering and math. Concretely, it checks: graduate- and expert-level questions in science and math; multi-step derivations where each step must be correct; problems written to defeat memorisation (novel or recent exam problems).

How is the Overall (DE) 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 Overall (DE) 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/overall-de/scores) or pull it directly from the Open LLM Radar API with any HTTP client.

Model scores 1 model tested

Reset
# Model Score Date Source Verified
1 Kolibri-1
Aleph Alpha
70.8%
03.10.2026 Report Verified

What now?

You've seen how models score on Overall (DE) — here's what to do next.