BlogLLM Benchmark Scores as Published, Side by Side
FLEURS: Results as Published
Every result the catalog holds for FLEURS: 3 models from 1 developer, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Multimodal UnderstandingMaintainer GoogleIntroduced 2022Data version 2026103001, as of 2026-10-30
FLEURS is a multilingual speech benchmark with about 12 hours of speech in each of 102 languages, parallel across languages because it is read from the FLoRes-101 translation sentences. It is used for speech recognition, language identification, translation and retrieval. For speech recognition the usual score is the word error rate, where lower is better.
FLEURS (metric not stated)
lower is better
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Gemma 4 12BGoogle, released 2026-04-02 | 0.069 | Google, Gemma 4 model cardchecked 2026-10-15 | - |
| Gemma 4 E2BGoogle, released 2026-04-02 | 0.09 | Google, Gemma 4 model cardchecked 2026-10-15 | - |
| Gemma 4 E4BGoogle, released 2026-04-02 | 0.08 | Google, Gemma 4 model cardchecked 2026-10-15 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.