Multi-task Language Understanding on Spanish Comprehensive Benchmark Suite
38.97Aggregate Normalized AccuracyML (15%)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ML (15%)Filtering strategy=ML (15%)2026.04 | 38.97 | 2.71 | |
| ML (Q3)Filtering strategy=ML (Q3)2026.04 | 38.87 | 2.14 | |
| MLFiltering strategy=ML2026.04 | 38.55 | 3.57 | |
| HQ seedFiltering strategy=HQ seed2026.04 | 38.36 | 3.71 | |
| MKC-eFiltering strategy=MKC-e2026.04 | 38.01 | 4.14 | |
| HQFiltering strategy=HQ2026.04 | 37.53 | 5.14 | |
| No filteringFiltering strategy=No filtering2026.04 | 36.35 | 6.29 |