FLEURS

FLEURS is a benchmark for performance in languages other than English. The official description says: "FLEURS - Few-shot Learning Evaluation of Universal Representations of Speech". Below we describe in simple words what benchmarks of this type generally examine.

FLEURS measures performance in languages other than english. In detail, it checks:

• understanding and answering in many different languages
• translation quality between language pairs
• keeping math and reasoning quality when the question is not in English
• treating low-resource languages fairly instead of defaulting to English

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: FLEURS - Few-shot Learning Evaluation of Universal Representations of Speech. Lower is better (error rate).

What is the FLEURS benchmark?

FLEURS is a benchmark for performance in languages other than English. The official description says: 'FLEURS - Few-shot Learning Evaluation of Universal Representations of Speech'. Below we describe in simple words what benchmarks of this type generally examine.

What does FLEURS test?

FLEURS mainly measures performance in languages other than English. Concretely, it checks: understanding and answering in many different languages; translation quality between language pairs; keeping math and reasoning quality when the question is not in English.

How is the FLEURS 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 FLEURS 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/fleurs/scores) or pull it directly from the Open LLM Radar API with any HTTP client.