Global MMLU (CF) leaderboard
As of November 14, 2026, among the results listed here, SmolLM3-3B-Base has the highest reported Global MMLU (CF) score, 28.6% (Base Pre-Trained Model; Arabic), published by HuggingFaceTB. 1 model has a Global MMLU (CF) 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
28.6%
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 | 28.6% | Base Pre-Trained Model; Arabic | HuggingFaceTB | Publication date not reported |
Other reported runs
| Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|
| H SmolLM3-3B-Base | 36.2% | Base Pre-Trained Model; Chinese | HuggingFaceTB | Publication date not reported |
| H SmolLM3-3B-Base | 38.4% | Base Pre-Trained Model; French | HuggingFaceTB | Publication date not reported |
| H SmolLM3-3B-Base | 35.1% | Base Pre-Trained Model; German | HuggingFaceTB | Publication date not reported |
| H SmolLM3-3B-Base | 37.0% | Base Pre-Trained Model; Italian | HuggingFaceTB | Publication date not reported |
| H SmolLM3-3B-Base | 36.9% | Base Pre-Trained Model; Portuguese | HuggingFaceTB | Publication date not reported |
| H SmolLM3-3B-Base | 36.5% | Base Pre-Trained Model; Russian | HuggingFaceTB | Publication date not reported |
| H SmolLM3-3B-Base | 38.5% | 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 Global MMLU (CF) measures
Global MMLU (CF) appears in the release announcements of HuggingFaceTB. We have not found a public write-up of the benchmark itself yet.