Belebele leaderboard
As of November 14, 2026, among the results listed here, SmolLM3-3B-Base has the highest reported Belebele score, 40.2 (Base Pre-Trained Model; Arabic), published by HuggingFaceTB. 1 model has a Belebele result in our records.
Scores as the model makers published them, not re-run by us; each row links to its announcement.
Best reported score
40.2
Reported by HuggingFaceTB · Base Pre-Trained Model; Arabic
1 model ranked · 1 maker
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | H SmolLM3-3B-Base | 40.2 | Base Pre-Trained Model; Arabic | HuggingFaceTB | Publication date not reported |
Other reported runs
| Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|
| H SmolLM3-3B-Base | 43.8 | Base Pre-Trained Model; Chinese | HuggingFaceTB | Publication date not reported |
| H SmolLM3-3B-Base | 51 | Base Pre-Trained Model; French | HuggingFaceTB | Publication date not reported |
| H SmolLM3-3B-Base | 48.4 | Base Pre-Trained Model; German | HuggingFaceTB | Publication date not reported |
| H SmolLM3-3B-Base | 47.4 | Base Pre-Trained Model; Russian | HuggingFaceTB | Publication date not reported |
| H SmolLM3-3B-Base | 47 | Base Pre-Trained Model; Spanish | HuggingFaceTB | Publication date not reported |
How much to trust these numbers
- Source
- Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
- Settings
- All ranked results use the same reported setting.
What Belebele measures
Belebele appears in the release announcements of HuggingFaceTB. We have not found a public write-up of the benchmark itself yet.