Benchmark
FLEURS Benchmark
What is FLEURS?
Few-shot Learning Evaluation of Universal Representations of Speech - a parallel speech dataset in 102 languages built on FLoRes-101 with approximately 12…
- Released
- 2022-05-25
- Modality
- audio
- Evaluates
- speech to text, language
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 6
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/fleurs?top_n=500
FLEURS results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Gemini 1.0 Pro | 0.936 | 2024-02-15 | evidence | |
| Gemini 1.5 Flash | 0.904 | 2024-05-01 | evidence | |
| Gemini 1.5 Flash 8B | 0.864 | 2024-03-15 | evidence | |
| Gemini 1.5 Pro | 0.933 | 2024-05-01 | evidence | |
| Gemma 4 12B | 0.931 | 2026-05-23 | evidence | |
| Qwen2.5-Omni-7B | Qwen | 0.959 | 2025-03-27 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.