Natural Language Understanding on Chinese Evaluation Suite Aggregate
42.36Aggregate Normalized Accuracy1B Model (Multilingual classifier)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| 1B Model (Multilingual classifier)Filtering Strategy=Multilingual (ML), Model Scale=1B2026.04 | 42.36 | 1.31 | |
| 1B Model (HQ filtering)Filtering Strategy=Monolingual high-quality (HQ), Model Scale=1B2026.04 | 41.9 | 1.77 | |
| 1B Model (No filtering)Filtering Strategy=No filtering, Model Scale=1B2026.04 | 40.24 | 2.85 |